CN120282081A - Abnormality detection method and device for voice equipment and electronic equipment - Google Patents

Abstract

The embodiment of the present application provides an abnormality detection method, device and electronic device for voice equipment, which relates to the field of audio detection technology and is used to improve the accuracy of abnormality detection of voice equipment. The method includes: obtaining an audio test signal; controlling the at least one speaker to play the audio test signal in sequence, and when each speaker plays, controlling each of the at least one pickup to collect the currently played audio test signal respectively, and obtaining the collection result corresponding to each speaker; wherein the collection result includes at least one sub-collection result, and the at least one sub-collection result corresponds to the at least one pickup one by one; any two speakers in the at least one speaker do not play the audio test signal at the same time; based on the collection results corresponding to each of the at least one speaker, determine the abnormality detection results of the at least one speaker and the at least one pickup.

Description

Abnormality detection method and device for voice equipment and electronic equipment

Technical Field

The present application relates to the field of audio detection technologies, and in particular, to a method and an apparatus for detecting an abnormality of a voice device, and an electronic device.

Background

With the gradual development of monitoring technology, the application of an acoustic monitoring system combined with a monitoring system and an acoustic system in a plurality of industries is rapidly growing, and particularly in the fields of safety, smart home, medical treatment, industry and the like. Advances in technology have enabled sound monitoring systems to be more and more intelligent, efficient, and capable of being combined with other technologies (e.g., artificial intelligence, internet of things).

The combination of the monitoring system and the sound system can enable the monitoring system to provide more safety options and functions for the sound system, and the sound system provides better tone quality and more entertainment for the monitoring system. The most important pickup and speaker are the most basic in the sound monitoring system, and whether the function is normal is a precondition for determining whether the sound monitoring can work normally.

In the related art, a pickup or a speaker in an acoustic monitoring system is usually detected, which is often subject to interference of environmental noise, and the noise affects the accuracy of the acoustic monitoring system, resulting in lower accuracy of detection.

Disclosure of Invention

The embodiment of the application provides an abnormality detection method and device for voice equipment and electronic equipment, which are used for improving the abnormality detection accuracy of the voice equipment.

In a first aspect, an embodiment of the present application provides an abnormality detection method for a voice device, the voice device including at least one speaker and at least one pickup, the method including:

Acquiring an audio test signal;

Controlling the at least one loudspeaker to sequentially play the audio test signals, and controlling each sound pickup in the at least one sound pickup to acquire the audio test signals played currently respectively when each loudspeaker plays the audio test signals to acquire acquisition results corresponding to each loudspeaker, wherein the acquisition results comprise at least one sub-acquisition result which corresponds to the at least one sound pickup one by one;

and determining an abnormality detection result of the at least one speaker and the at least one pickup based on the acquisition results corresponding to the at least one speaker.

In a possible implementation manner, the method for acquiring the audio test signal comprises the steps of selecting a plurality of pieces of audio signals from a plurality of pre-stored audio signals according to the frequency range supported by the at least one loudspeaker, and combining the plurality of pieces of audio signals in a random arrangement mode to generate the audio test signal.

In a possible implementation manner, the method for combining the multi-item audio signals according to the random arrangement manner to generate the audio test signal includes randomly selecting a group from a plurality of pre-stored candidate playing parameters as a test playing parameter, adjusting respective gains of the multi-item audio signals according to the test playing parameter, and combining the adjusted multi-item audio signals according to the random arrangement manner to generate the audio test signal.

In a possible implementation manner, when the voice device comprises a loudspeaker and a pickup, the determining of the abnormality detection result of the at least one loudspeaker and the at least one pickup based on the collection result corresponding to the at least one loudspeaker respectively comprises determining that the loudspeaker and/or the pickup are abnormal when the collection result represents that the audio test signal is not collected, analyzing the collected audio test signal included in the collection result to obtain a collection signal parameter and a collection play parameter when the collection result represents that the audio test signal is collected, matching the collection signal parameter with a test signal parameter of the audio test signal, matching the collection play parameter with a test play parameter of the audio test signal, and determining that the loudspeaker and/or the pickup are abnormal when the collection signal parameter or the collection play parameter fails to match, and determining that the loudspeaker and the pickup are not abnormal when the collection signal parameter and the collection play parameter are both successfully matched.

In a possible implementation manner, when the voice equipment comprises a loudspeaker and a plurality of pickups, the method comprises the steps of determining an abnormal detection result of the at least one loudspeaker and the at least one pickups based on the acquisition result corresponding to each sub-acquisition result of the at least one loudspeaker respectively, determining that the loudspeaker and/or the plurality of pickups are abnormal when any sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired, analyzing the acquired audio test signal corresponding to each sub-acquisition result according to the acquired audio test signal included in each sub-acquisition result when the acquisition result included in the acquisition result represents that the audio test signal is acquired, respectively, matching the acquired signal parameters corresponding to each sub-acquisition result with the test signal parameters of the audio test signal, respectively, matching the acquired play parameters corresponding to each sub-acquisition result with the test signal parameters of the audio test signal, determining that the loudspeaker and/or the plurality of pickups are not successfully matched when any acquisition signal parameters or any sub-acquisition result represents that the audio test signal is acquired, respectively, and determining that the audio test signal and/or the plurality of pickups are abnormally matched with each other.

In a possible implementation manner, the determining that the speaker or the plurality of sound pickups is abnormal when any sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired includes determining that the speaker or the plurality of sound pickups is abnormal when some sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired, and determining that the speaker or the plurality of sound pickups is abnormal when all sub-acquisition results included in the acquisition result represent that the audio test signal is not acquired.

In a possible implementation manner, when the voice equipment comprises a plurality of speakers and a sound pickup, the abnormal detection results of the at least one speaker and the at least one sound pickup are determined based on the acquisition results corresponding to the at least one speaker respectively, and the voice equipment comprises the following steps of matching the acquisition signal parameters with the test signal parameters of the audio test signals, matching the acquisition playing parameters with the test playing parameters of the audio test signals, determining that the speaker and/or the sound pickup corresponding to any acquisition result are abnormal when the audio test signals are not acquired according to the characteristics of any acquisition result, analyzing the acquired audio test signals included in any acquisition result to obtain the acquisition signal parameters and the acquisition playing parameters when the characteristics of any acquisition result are characterized in that the audio test signals are acquired, and determining that the acquisition signal parameters and the acquisition playing parameters of any sound pickup corresponding to any acquisition result are not matched when the acquisition signal parameters or the playing parameters of any acquisition result fail.

In a possible implementation manner, when the voice equipment comprises a plurality of speakers and a plurality of pickups, the abnormal detection results of the at least one speaker and the at least one pickups are determined based on the acquisition results corresponding to the at least one speaker respectively, and the method comprises the steps of analyzing and obtaining acquisition signal parameters and acquisition playing parameters corresponding to each sub-acquisition result respectively for any one acquisition result in the acquisition results corresponding to the plurality of speakers respectively, determining that the speaker and/or the plurality of pickups corresponding to the arbitrary one acquisition result are abnormal when any one sub-acquisition result included in the arbitrary one acquisition result represents that the audio test signal is acquired, determining that the audio test signal corresponding to the arbitrary one acquisition result and/or the plurality of pickups corresponding to the plurality of sub-acquisition result is/are abnormal when the audio test signal is acquired by the sub-acquisition result included in the arbitrary one acquisition result, respectively matching the acquisition signal parameters and the acquisition playing parameters corresponding to the plurality of sub-acquisition results respectively with the audio test signal parameters corresponding to the sub-acquisition result, respectively, and respectively matching the audio test signal parameters when the audio test signal corresponding to the sub-acquisition result and the audio test signal corresponding to the plurality of sub-acquisition result and the audio test signal corresponding to the sub-acquisition result respectively is/and the audio test signal corresponding to the sub-acquisition parameters respectively, and determining that the loudspeaker corresponding to any one acquisition result and the plurality of sound pick-up devices are not abnormal.

In a possible implementation manner, after determining the abnormality detection result of the at least one speaker and the at least one pickup, the method further includes reporting the abnormality detection result when the abnormality detection result characterizes that the at least one speaker or the at least one pickup is abnormal.

In a second aspect, an embodiment of the present application provides an abnormality detection apparatus for a voice device including at least one speaker and at least one pickup, the apparatus including:

The acquisition unit is used for acquiring the audio test signal;

The processing unit is used for controlling the at least one loudspeaker to sequentially play the audio test signals, controlling each sound pickup in the at least one sound pickup to acquire the audio test signals played currently respectively when each loudspeaker plays the audio test signals, and obtaining acquisition results corresponding to each loudspeaker, wherein the acquisition results comprise at least one sub-acquisition result which corresponds to the at least one sound pickup one by one, any two loudspeakers in the at least one loudspeaker do not play the audio test signals at the same moment, and determining abnormal detection results of the at least one loudspeaker and the at least one sound pickup based on the acquisition results corresponding to the at least one loudspeaker.

In a possible implementation manner, the acquiring unit is specifically configured to acquire an audio test signal, select a multi-item audio signal from a plurality of pre-stored audio signals according to a frequency range supported by the at least one speaker, and combine the multi-item audio signal according to a random arrangement manner to generate the audio test signal.

In a possible implementation manner, the processing unit combines the multi-item audio signals according to a random arrangement manner to generate the audio test signal, and is specifically configured to randomly select a group from a plurality of pre-stored candidate playing parameters as a test playing parameter, adjust respective gains of the multi-item audio signals according to the test playing parameter, and combine the adjusted multi-item audio signals according to the random arrangement manner to generate the audio test signal.

In a possible implementation manner, when the voice device comprises a loudspeaker and a pickup, the processing unit determines an abnormality detection result of the at least one loudspeaker and the at least one pickup based on the collection result corresponding to each of the at least one loudspeaker, and is specifically used for determining that the loudspeaker and/or the pickup are abnormal when the collection result represents that the audio test signal is not collected, analyzing the collected audio test signal included in the collection result to obtain a collection signal parameter and a collection play parameter when the collection result represents that the audio test signal is collected, matching the collection signal parameter with a test signal parameter of the audio test signal, matching the collection play parameter with a test play parameter of the audio test signal, and determining that the loudspeaker and/or the pickup are abnormal when the collection signal parameter or the collection play parameter fails to match, and determining that the loudspeaker and the pickup are not abnormal when the collection signal parameter and the collection play parameter are successfully matched.

In a possible implementation manner, when the voice equipment comprises a loudspeaker and a plurality of pickups, the processing unit is used for determining an abnormal detection result of the at least one loudspeaker and the at least one pickups based on the acquisition result corresponding to each of the at least one loudspeaker, and is specifically used for determining that the loudspeaker and/or the plurality of pickups are abnormal when any one sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired, analyzing the acquired audio test signal corresponding to each sub-acquisition result according to the acquired audio test signal included in each sub-acquisition result when the acquisition result included in the acquisition result represents that the audio test signal is acquired, respectively obtaining an acquisition signal parameter and an acquisition playing parameter corresponding to each sub-acquisition result, respectively matching the acquisition signal parameters corresponding to each of the sub-acquisition results with the test signal parameters of the audio test signal, respectively matching the acquisition playing parameters corresponding to each of the sub-acquisition results with the test signal, and determining that the loudspeaker and/or the plurality of pickups are not successfully matched when any one signal parameter or any one of the sub-acquisition result represents that the audio test signal is acquired, respectively determining that the audio test signal is not matched with the audio test signal.

In a possible implementation manner, the processing unit is used for determining that the loudspeaker or the plurality of sound collectors are abnormal when any sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired, and is specifically used for determining that the part of sound collectors in the plurality of sound collectors are abnormal when the part of sub-acquisition result included in the acquisition result represents that the audio test signal is not acquired, and determining that the loudspeaker or the plurality of sound collectors are abnormal when all the plurality of sub-acquisition results included in the acquisition result represent that the audio test signal is not acquired.

In a possible implementation manner, when the voice equipment comprises a plurality of speakers and a sound pickup, the processing unit determines an abnormal detection result of the at least one speaker and the at least one sound pickup based on the acquisition result corresponding to each of the at least one speaker, and is specifically used for matching a test signal parameter of the acquisition signal parameter with a test play parameter of the audio test signal, and determining that the speaker and/or the sound pickup corresponding to any one acquisition result are abnormal when the audio test signal is not acquired by the characterization of any one acquisition result, analyzing the acquired audio test signal included in any one acquisition result to obtain the acquisition signal parameter and the acquisition play parameter when the audio test signal is acquired by the characterization of any one acquisition result, and matching the acquisition signal parameter with the test play parameter of the audio test signal, and determining that the speaker and/or the sound pickup corresponding to any one acquisition result are not successful when the acquisition signal parameter or the play parameter fails.

In a possible implementation manner, when the voice equipment comprises a plurality of speakers and a plurality of pickups, the processing unit determines an abnormal detection result of the at least one speaker and the at least one pickups based on the acquisition result corresponding to each of the at least one speaker, and is specifically configured to analyze and obtain an acquisition signal parameter and an acquisition playing parameter corresponding to each sub-acquisition result for any one of the acquisition results corresponding to each of the plurality of speakers, when any one sub-acquisition result included in the any one acquisition result represents that the audio test signal is not acquired, determine that the speaker and/or the plurality of pickups corresponding to the any one acquisition result are abnormal, when the plurality of sub-acquisition results included in the any one acquisition result represent that the audio test signal is acquired, respectively analyze and obtain the acquisition signal parameter and the acquisition playing parameter corresponding to each sub-acquisition result, respectively match the acquisition signal parameter corresponding to each sub-acquisition result with the audio test signal parameter, and when the plurality of sub-acquisition result and/or the plurality of pickups corresponding to each sub-acquisition result are matched with the audio test signal, respectively match the audio test signal and the plurality of abnormal acquisition parameters when the sub-acquisition result and the plurality of pickups corresponding to each other sub-acquisition result are/or the audio test signal is/are matched, and determining that the loudspeaker corresponding to any one acquisition result and the plurality of sound pick-up devices are not abnormal.

In a possible implementation manner, after determining the abnormality detection results of the at least one speaker and the at least one pickup, the processing unit is further configured to report the abnormality detection results when the abnormality detection results indicate that the at least one speaker or the at least one pickup is abnormal.

In a third aspect, an embodiment of the present application provides an electronic device, including:

A memory for storing computer instructions;

A processor coupled to the memory for executing computer instructions in the memory and for implementing the method of any one of the first aspects when the computer instructions are executed.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium comprising:

The computer readable storage medium stores computer instructions which, when run on a computer, cause the computer to perform the method according to any of the first aspects.

In a fifth aspect, embodiments of the present application also provide a computer program product comprising computer instructions which, when executed by a processor, implement a method as claimed in any of the first aspects.

The application has the following beneficial effects:

The embodiment of the application provides an abnormality detection method and device for voice equipment and electronic equipment, wherein the method comprises the steps of obtaining an audio test signal, controlling at least one loudspeaker to sequentially play the audio test signal, controlling each pickup in at least one pickup to respectively collect the audio test signal which is played currently when each loudspeaker plays the audio test signal, obtaining a collection result corresponding to each loudspeaker, wherein the collection result comprises at least one sub-collection result, the at least one sub-collection result corresponds to the at least one pickup one by one, playing the audio test signal at the same moment by any two loudspeakers in the at least one loudspeaker, and determining an abnormality detection result of the at least one loudspeaker and the at least one pickup based on the collection result corresponding to each loudspeaker.

Based on the above scheme, in the abnormality detection method for voice equipment provided by the embodiment of the application, the self-detection between the speaker and the pickup can be realized through the speaker and the pickup, so that the occurrence of excessive noise during abnormality detection through the additional external speaker and the pickup in the related art can be avoided, and the accuracy of abnormality detection is further improved. In addition, the method can also cover the configuration scenes of the single loudspeaker Shan Sheyin, the multi-loudspeaker single pickup, the single-loudspeaker multi-pickup and the multi-loudspeaker multi-pickup, so that the self-checking requirements of most voice equipment can be met, and compared with the self-checking scheme in the related technology, the method has wider coverage.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application.

Fig. 1 is a schematic diagram of a system architecture to which an abnormality detection method for a voice device according to an embodiment of the present application is applied;

Fig. 2 is an exemplary flowchart of a method for detecting an abnormality of a voice device according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application;

FIG. 5 is a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application;

FIG. 6 is a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application;

Fig. 7 is a schematic diagram of an abnormality detection apparatus for a voice device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to facilitate understanding of the technical solution provided by the embodiments of the present application, the following describes the technical terms related to the embodiments of the present application.

(1) And a loudspeaker, namely a sound box and other equipment for playing audio signals.

(2) Pickup, microphone, etc.

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the technical solutions of the present application, but not all embodiments. All other embodiments, based on the embodiments described in the present document, which can be obtained by a person skilled in the art without any creative effort, are within the scope of protection of the technical solutions of the present application.

The terms "first" and "second" in embodiments of the application are used to distinguish between different objects and are not used to describe a particular sequence. Furthermore, the term "include" and any variations thereof is intended to cover non-exclusive protection. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The term "plurality" in the present application may mean at least two, for example, two, three or more, and embodiments of the present application are not limited.

In addition, the term "and/or" is merely an association relation describing the association object, and means that three kinds of relations may exist, for example, a and/or B, and that three kinds of cases where a exists alone, while a and B exist alone, exist alone. The character "/" herein generally indicates that the associated object is an "or" relationship unless otherwise specified.

Fig. 1 is a schematic diagram of a system architecture to which an abnormality detection method for a voice device according to an embodiment of the present application is applied. The system 100 may include a signal preparer 110, at least one speaker 120, at least one pickup 130, and a determiner 140.

The signal preparation device 110 is configured to obtain an audio test signal, and send a test signal parameter and a test playing parameter corresponding to the audio test signal to the determination device 140. At least one speaker 120 is configured to sequentially play the audio test signals, and at least one pickup 130 is configured to collect the audio test signals currently played when each speaker is played, so as to obtain a collection result corresponding to each speaker. The collection result may include at least one sub-collection result, where the at least one sub-collection result corresponds to the at least one pickup 130 one-to-one. Any two speakers 120 of the at least one speaker 120 do not play audio test signals at the same time.

The determiner 140 is configured to determine an abnormality detection result of the at least one speaker 120 and the at least one pickup 130 based on the respective collection results of the at least one speaker 120.

Optionally, an alarm 150 may be further included in the system, for reporting the abnormality detection result when the abnormality detection result indicates that there is an abnormality in at least one speaker 120 and/or at least one pickup 130, for example, a maintenance signal may be sent to a corresponding staff member.

It should be noted that the structure shown in fig. 1 is merely an example, and the embodiment of the present application is not limited thereto.

Referring to fig. 2, an exemplary flowchart of a method for detecting an abnormality of a voice device according to an embodiment of the present application may be applied to the system shown in fig. 1, and may include the following procedures:

S201, acquiring an audio test signal.

In one possible implementation manner, after the system starts the self-checking function, the signal preparation device of the system firstly acquires the audio test signal, and in a specific implementation manner, the signal preparation device can select multiple target audio signals from the prestored multiple audio signals according to the frequency range supported by at least one loudspeaker. Then, the multi-item mark audio signals are combined in a random arrangement mode to generate an audio test signal.

In some embodiments, when the signal preparation device combines the multi-item audio signals according to a random arrangement mode to generate the audio test signal, a group of pre-stored candidate playing parameters can be selected randomly to be used as a test playing parameter, then the gains of the multi-item audio signals are adjusted according to the test playing parameter, and the adjusted multi-item audio signals are combined according to the random arrangement mode to generate the audio test signal.

After the audio test signal is generated, the signal preparation device can also send the test signal parameters and the test playing parameters corresponding to the audio test signal to the judgment device for subsequent signal judgment.

In some embodiments, the pre-stored plurality of audio signals may be self-contained in the system or may be self-uploaded by the user. The plurality of audio signals can be single-frequency audio signals with different frequencies, fixed decibels covering the full frequency band and fixed duration. The signal preparation device may preset sequence numbers corresponding to different frequencies, for example, the frequencies of the audio signals include 1000Hz, 2000Hz, 3000Hz, 4000Hz, 5000Hz, 6000Hz, 7000Hz, 8000Hz, 9000Hz and 10000Hz, and then the sequence numbers corresponding to each frequency may be determined according to the sequence from small to large in sequence of 0-9. I.e. 0 corresponds to 1000Hz,1 corresponds to 2000Hz, and so on.

After the system starts the self-checking function, the signal preparation device can generate a random sequence number according to the frequency range supported by at least one loudspeaker, then select an audio signal as a target audio signal according to the frequency corresponding to each sequence number in the sequence, and then combine the target audio signals according to the sequence of each sequence number to generate an audio test signal. It should be appreciated that the number of sequence numbers included in the random sequence number sequence may be set according to practical situations, for example, may be 10, 5, etc., which is not limited in the present application.

For example, assuming that the generated random number is 8154609372, the target audio signals may be combined according to 9000Hz->2000Hz->6000Hz->5000Hz->7000Hz->1000Hz->10000Hz->4000Hz->8000Hz->3000Hz in such a way that each signal has a duration of 10 seconds and an amplitude of 8192 at maximum, and a long signal formed by connecting ten single-frequency signals having a total duration of 100 seconds and an amplitude of 8192 at maximum is generated as the audio test signal

In another example, the signal preparer may also randomly select a group from the pre-stored plurality of candidate play parameters as the test play parameter. For example, pre-stored candidate playout parameters may include 20dB down, 15dB down, 10dB down, 5dB up, 10dB up, 15dB up, etc., then the randomly selected test playout parameter may be 10dB down. At this time, the gain of each item of the selected audio signal can be adjusted according to the test playing parameter, and the adjusted 10 items of audio signals are combined according to the sequence of the random sequence numbers to generate the audio test signal.

Then, the signal preparation device can send the test signal parameters corresponding to the audio test signal and the selected test playing parameters to the judgment device. The test signal parameters may include signal basic information such as the frequency of each item of target audio signal, the arrangement sequence of target audio signals, the amplitude of each item of target audio signal, and the duration of each item of target audio signal included in the audio test signal.

When the signal preparation device presets the sequence numbers corresponding to different frequencies, the sequence numbers may be set in the order of 0 to 9 from the larger frequency to the smaller frequency, or the sequence numbers may be set randomly, which is not limited in the present application.

Based on the scheme, the prestored plurality of audio signals are audio signals with different frequencies and cover fixed decibels and fixed duration of the full frequency band, so that various scenes can be covered, and the detection range is wider. In addition, the application can prevent the interference of other signals in the scene by randomly generating the sequence number and then enabling the target audio signal to form a long signal according to the randomly generated sequence number, thereby improving the detection accuracy.

S202, controlling at least one loudspeaker to sequentially play audio test signals, and controlling each pickup in at least one pickup to acquire the audio test signals played currently respectively when each loudspeaker plays, so as to obtain an acquisition result corresponding to each loudspeaker.

The acquisition result comprises at least one sub-acquisition result, wherein the at least one sub-acquisition result corresponds to the at least one pickup one by one, and any two speakers in the at least one speaker play audio test signals at the same time.

For example, assume that 2 speakers, speaker A1 and speaker A2, and 2 pickups, pickup B1 and pickup B2, are included in the voice device. Then speaker A2 does not play while speaker A1 plays the audio test signal. Taking the playing sequence as the loudspeaker A1- > the loudspeaker A2 as an example, when the loudspeaker A1 plays the audio test signal, the pickup B1 and the pickup B2 collect the audio test signal played by the loudspeaker A1 in real time, the pickup B1 can obtain the sub-collection result a11, the pickup B2 can obtain the sub-collection result a12, and then the sub-collection result a11 and the sub-collection result a12 can be combined into a collection result A1 corresponding to the loudspeaker A1. Likewise, when the speaker A2 plays the audio test signal, the pickup B1 and the pickup B2 collect the audio test signal played by the speaker A2 in real time, the pickup B1 may obtain the sub-collection result a21, the pickup B2 may obtain the sub-collection result a22, and then the sub-collection result a21 and the sub-collection result a22 may be combined into the collection result A2 corresponding to the speaker A2.

In some embodiments, each pickup may send the obtained sub-collection result to the determiner after obtaining the sub-collection result each time, so that the determiner performs analysis and determination on each sub-collection result according to the test signal parameter and the test play parameter of the test audio signal, thereby determining the abnormal detection result of at least one speaker and at least one pickup, and a specific analysis and determination method will be described in detail in S203.

S203, determining an abnormality detection result of the at least one loudspeaker and the at least one pickup based on the acquisition results corresponding to the at least one loudspeaker.

Based on the above scheme, in the abnormality detection method for voice equipment provided by the embodiment of the application, the self-detection between the speaker and the pickup can be realized through the speaker and the pickup, so that the occurrence of excessive noise during abnormality detection through the additional external speaker and the pickup in the related art can be avoided, and the accuracy of abnormality detection is further improved.

The judging device can be divided into the following four cases when determining the abnormal detection results of the at least one loudspeaker and the at least one pickup based on the acquisition results corresponding to the at least one loudspeaker respectively:

in one aspect, a speech device includes a speaker and a microphone.

Referring to fig. 3, a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application is shown. It is assumed that the speech device comprises a loudspeaker and a sound pick-up, respectively, a loudspeaker 1 and a sound pick-up 1. After the self-checking function is started, the signal preparation device firstly generates an audio test signal, sends the test signal parameters and the test playing parameters to the judgment device, can control the loudspeaker 1 to play the audio test signal, simultaneously controls the pickup 1 to collect the audio test signal played by the loudspeaker 1 in real time as a collection result corresponding to the loudspeaker 1, and sends the collection result to the judgment device.

The judging device can determine that the abnormality detection result is that the loudspeaker 1 is abnormal, or the pickup 1 is abnormal, or both the loudspeaker 1 and the pickup 1 are abnormal, when the collection result represents that the audio test signal is not collected, because the audio test signal is not collected and possibly the loudspeaker 1 plays the audio test signal but the pickup 1 cannot collect, and also the pickup 1 cannot collect the audio test signal when the loudspeaker 1 does not play the audio test signal.

And analyzing the collected audio test signals included in the collection result to obtain collection signal parameters and collection playing parameters after the collection result represents the collected audio test signals.

Specifically, when the collection result is analyzed, the signal size of the collected audio test signal can be determined, the signal size is used as a collection playing parameter, the signal frequency, the arrangement sequence of the signal frequencies and the amplitude of the signals contained in the collected audio test signal can be determined, and the contained signal frequency, the arrangement sequence of the signal frequencies and the amplitude of the signals are used as collection signal parameters.

And then matching the collected signal parameters with the test signal parameters of the audio test signal, matching the collected playing parameters with the test playing parameters of the audio test signal, and determining that the abnormality detection result is that the speaker or the pickup is abnormal when the collected signal parameters or the collected playing parameters are failed to match.

Specifically, when the pickup 1 collects an audio test signal, but the collected signal parameter is not matched with the test signal parameter of the audio test signal, that is, the collected signal frequency is not matched with the signal frequency of the audio test signal, and/or the collected signal amplitude is not matched with the signal amplitude of the audio test signal, it may be determined that the abnormality detection result is that the pickup 1 is abnormal. When the sound pickup 1 collects the audio test signal, but the collected playing parameter is not matched with the test playing parameter of the audio test signal, that is, the collected signal size is not matched with the signal size of the audio test signal, the abnormal detection result can be determined to be that the sound pickup 1 and/or the loudspeaker 1 are abnormal.

In contrast, when the collected signal parameters and the collected playing parameters are successfully matched, it can be determined that the abnormality detection result is that no abnormality exists in the loudspeaker and the pickup.

For example, the failure of matching the parameters of the collected signals may be one or more signals in the audio test signal, where the frequency of the collected signals is different from the actual frequency of the signal. For example, if a certain signal in the audio test signals has a frequency of 1000Hz, but the frequency of the acquired signal is 2000Hz, it may be determined that the acquired signal parameter fails to match.

Illustratively, the failure to collect the playing parameters may be that the collected signal is different in size from the test playing parameters. For example, the size of the audio test signal before adjustment is 50dB, the test playing parameter is reduced by 10dB, but the size of the collected audio test signal is 55dB, and is not equal to 40dB, and at this time, it can be determined that the collection playing parameter fails to match.

When it is determined that the abnormality detection result indicates that the speaker and/or the pickup is abnormal, the determiner may report the abnormality detection result, for example, may report the abnormality detection result to the alarm, so that the alarm may notify a relevant worker of overhauling the voice equipment by sending an overhauling signal.

Optionally, when reporting the abnormality detection result, the reporting information may include related information such as an abnormality cause, an abnormality occurrence device, and the like. For example, the reason for the abnormality may be that the sound pickup 1 does not collect the audio test signal, and the device with the abnormality may be identified by an identifier, for example, the speaker is 1, the sound pickup is 2, and the device with the abnormality may be identified by 3 when the specific abnormality cannot be determined.

In case two, the speech device comprises a loudspeaker and a plurality of microphones.

Referring to fig. 4, a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application is shown. The speech device is assumed to comprise a loudspeaker and a plurality of sound pickups, loudspeaker 1 and sound pickups 1-sound pickups S, respectively, where S is larger than 1. After the self-checking function is started, the signal preparation device firstly generates an audio test signal, sends test signal parameters and test playing parameters to the judgment device, then can control the loudspeaker 1 to play the audio test signal, simultaneously controls the pickup 1-the pickup S to collect the audio test signal played by the loudspeaker 1 in real time, obtains sub-collection results 1-sub-collection results S corresponding to the pickup 1-the pickup S respectively, combines the sub-collection results 1-the sub-collection results S into collection results corresponding to the loudspeaker 1, and sends the collection results to the judgment device.

The determiner may determine that the one or more sound pickups do not collect the audio test signal when any one of the sub-collection results included in the collection result represents that the audio test signal is not collected, so that it may be determined that the abnormality detection result is that the speaker 1 and/or the sound pickups 1-S are abnormal.

Specifically, when the partial sub-acquisition results included in the acquisition results represent that the audio test signal is not acquired, as the partial pickup can acquire the audio test signal, it can be determined that the abnormality detection result is that the partial pickup in the pickup 1-pickup S is abnormal, that is, the pickup corresponding to each of the partial sub-acquisition results is abnormal.

For example, assuming that the sub-collection result 2 and the sub-collection result 3 represent that the audio test signal is not collected, the other sub-collection results all represent that the audio test signal is collected, and the sub-collection result 2 is collected by the sound pick-up 2, and the sub-collection result 3 is collected by the sound pick-up 3, it may be determined that the abnormality detection result is that the sound pick-up 2 and the sound pick-up 3 are abnormal.

When all the sub-collection results included in the collection result represent that the audio test signal is not collected, and the audio test signal may not be played by the loudspeaker 1, or the audio test signal is played by the loudspeaker 1 but none of the pickup 1 and the pickup S can be collected, or the audio test signal is not played by the loudspeaker 1, and at the same time, none of the pickup 1 and the pickup S can be collected, so that it can be determined that the abnormality detection result is that the loudspeaker 1 is abnormal, or that the pickup 1 and the pickup S are abnormal, or that the loudspeaker 1 and the pickup S are abnormal.

When the plurality of sub-acquisition results included in the acquisition result represent the acquired audio test signals, the judging device can respectively analyze the acquired audio test signals respectively included in the plurality of sub-acquisition results to obtain acquisition signal parameters and acquisition playing parameters corresponding to each sub-acquisition result. The process of analyzing each sub-acquisition result can be referred to the related description in the case one, and will not be described herein.

And then, respectively matching the acquired signal parameters corresponding to the sub-acquisition results with the test signal parameters of the audio test signal, respectively matching the acquired playing parameters corresponding to the sub-acquisition results with the test playing parameters of the audio test signal, and determining that the loudspeaker and/or the plurality of pickups are abnormal when any one of the acquired signal parameters or any one of the acquired playing parameters fails to be matched.

Specifically, when the collected signal parameters and the collected playing parameters are respectively matched, if the collected playing parameters corresponding to the sub-collected results are inconsistent, that is, the sizes of the signals collected by the sound collectors are inconsistent, it can be determined that the abnormality detection result is that abnormality exists in part of the sound collectors. If the collected playing parameters corresponding to the sub-collected results are consistent, but the collected playing parameters are not matched with the tested playing parameters, it can be determined that the abnormality detection result is that the speaker 1 is abnormal, or that the sound pick-up 1-sound pick-up S is abnormal, or that the speaker 1 and the sound pick-up 1-sound pick-up S are abnormal. Further, if the collected play parameters corresponding to the sub-collected results are consistent, and the collected play parameters are matched with the test play parameters, but the collected signal parameters are not matched with the test signal parameters, the judging device can determine that the abnormality detection result is that at least one pickup in the pickup 1-the pickup S is abnormal.

For example, it is assumed that a voice apparatus includes a speaker 1, a sound pickup 2, and a sound pickup 3. The test playing parameter is raised by 5dB, the size of the audio test signal before adjustment is 50dB, and the random sequence number sequence of the frequency is 8153. The frequency corresponding to each sequence number is exemplified by the embodiment given in S201.

If the signal size collected by the sound pick-up 1 is 50dB, the signal size collected by the sound pick-up 2 is 45dB, and the signal size collected by the sound pick-up 3 is 45dB, it can be determined that at least one of the sound pick-up 1-3 is abnormal due to inconsistent collected signal sizes.

If the size of the signal collected by the sound pick-up 1 is 50dB, the size of the signal collected by the sound pick-up 2 is 50dB, and the size of the signal collected by the sound pick-up 3 is 50dB, the collected signal is consistent, but the collected playing parameters are not matched with the tested playing parameters, so that it can be determined that the speaker 1 may be abnormal, or the sound pick-up 1-3 may be abnormal, or the speaker 1, the sound pick-up 2 and the sound pick-up 3 may be abnormal.

If the sizes of the signals collected by the sound collectors are consistent, and the collected playing parameters are matched with the tested playing parameters, but the frequency sequence number determined by the sound collector 1 is 8133, the frequency sequence number determined by the sound collector 2 is 8153, and the frequency sequence number determined by the sound collector 3 is 8153, the collected signal parameters of the sound collector 1 are not matched with the tested signal parameters, so that the sound collector 1 is determined to be abnormal.

In contrast, when the acquired signal parameters and the acquired play parameters corresponding to the sub-acquired results are successfully matched, the judging device can determine that the abnormality detection result is that the speaker and the sound pickup are not abnormal.

Optionally, when the abnormality detection result is that any device has an abnormality, the abnormality detection result may be reported, and the abnormality detection flow may be ended. Under the condition, after the alarm is reported to the relevant staff, the relevant staff can manually overhaul all speakers and all pickups included in the voice equipment, so that abnormal but undetected conditions of some equipment are avoided, and user experience is improved.

Optionally, when reporting the abnormal detection result, if the reporting information includes related information such as an abnormal reason, abnormal equipment, etc., then in this case, after the alarm reports to the relevant staff, the relevant staff can also manually overhaul the equipment involved in the reporting information, thereby performing more accurate overhaul and reducing the workload of the relevant staff.

In case three, the voice device includes a plurality of speakers and a sound pickup.

Referring to fig. 5, a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application is shown. The speech device is assumed to comprise a loudspeaker and a plurality of sound pickups, loudspeaker 1-loudspeaker T and sound pickups 1, respectively, where T is larger than 1. After the self-checking function is started, the signal preparation device firstly generates an audio test signal, sends test signal parameters and test playing parameters to the judging device, and then can firstly control the loudspeaker 1 to play the audio test signal, simultaneously control the pickup 1 to collect the audio test signal played by the loudspeaker 1 in real time to obtain a sub-collection result 1 corresponding to the pickup 1, and takes the sub-collection result 1 as a collection result 1 corresponding to the loudspeaker 1, and sends the collection result 1 to the judging device. And then sequentially executing the process of collecting the audio test signals played by the loudspeaker 1 according to the sequence of the loudspeaker 2-loudspeaker T, so as to obtain the collection results 2-collection results T corresponding to the loudspeaker 2-loudspeaker T respectively, and sending the collection results 2-collection results T to the judging device respectively.

In some embodiments, the determiner may perform the following for each of the acquisition results 1-acquisition result T:

When any one of the acquisition result characterization does not acquire the audio test signal, determining that the abnormality detection result is that the loudspeaker and/or the pickup corresponding to any one of the acquisition result is abnormal. For example, if any of the collection results is collection result 1, it may be determined that there is an abnormality in the speaker 1 and/or the pickup 1 when the collection result 1 indicates that no audio test signal is collected.

When any one of the acquisition result characterizes the acquired audio test signal, analyzing the acquired audio test signal included in any one of the acquisition result to obtain acquisition signal parameters and acquisition playing parameters. Then, the judging device matches the collected signal parameters with the test signal parameters of the audio test signal, matches the collected playing parameters with the test playing parameters of the audio test signal, and determines that the abnormal detection result is that the loudspeaker and/or the pickup 1 corresponding to any one of the collected results is abnormal when the collected signal parameters or the collected playing parameters are failed to match.

Conversely, when the collected signal parameters and the collected playing parameters are successfully matched, the judging device can determine that the abnormal detection result is that the loudspeaker and the pickup corresponding to any one of the collected results are not abnormal.

The specific matching process of each acquisition result is the same as that of the case one, so reference may be made to the description related to the case one, and details thereof are not repeated here.

Optionally, when the judging device determines that the abnormal detection result is that the speaker and/or the pickup is abnormal according to any one of the collection results, the abnormal detection result may be reported before the analysis and judgment operation is performed on the next collection result, so that the related staff can manually overhaul the speaker and the pickup corresponding to any one of the collection results. In this case, since the pickup has been inspected, there is no abnormality, and it is ensured that when the analysis and judgment operation is performed on the subsequent collection result, the abnormality detection can be completed by judging whether or not there is an abnormality in the speaker, thereby reducing the calculation amount of the judgment device and improving the judgment efficiency.

For example, assuming that the collected result 1 is determined that the abnormality detection result is that the speaker and/or the pickup is abnormal, the abnormality detection result may be reported, so that a related worker manually overhauls the speaker and the pickup 1 corresponding to any one of the collected results. When analyzing and judging the acquisition result 2-acquisition result T, the default that the all-purpose pick-up 1 is not abnormal can be adopted, namely whether the acquisition result 2-acquisition result T acquires signals or not and whether the acquisition playing parameters are matched with the test playing parameters or not can be judged.

In fig. 5, the case where the pickup 1 is inspected before the analysis and judgment of the acquisition result corresponding to the speaker T is only shown, and if the pickup 1 is not inspected before the analysis and judgment of the acquisition result corresponding to the speaker T, the pickup 1 is processed so as to analyze and judge the acquisition result corresponding to the speaker 1.

In addition, the timing of playing the audio test signal by each speaker may be set according to the actual situation, for example, when the determiner completes analysis and determination on the audio test signal played by the previous speaker, or may immediately control the next speaker to play the audio test signal after the previous speaker completes playing the audio test signal.

In case four, the voice device includes a plurality of speakers and a plurality of sound pickup.

Referring to fig. 6, a schematic diagram of an abnormality detection result determination flow provided in an embodiment of the present application is shown. The speech device is assumed to comprise a plurality of loudspeakers and a plurality of pickups, namely a loudspeaker 1-loudspeaker T and a pickup 1-pickup S, respectively, where S and T are both larger than 1. In this case, for each speaker, playing and collecting the audio test signal are performed according to the second case mode, that is, after the self-checking function is started, the signal preparation device firstly generates the audio test signal and sends the test signal parameter and the test playing parameter to the judging device, then the speaker 1 can be controlled to play the audio test signal, meanwhile, the pickup 1-the pickup S are controlled to collect the audio test signal played by the speaker 1 in real time, sub-collection results 1-sub-collection results S corresponding to the pickup 1-the pickup S are obtained, the sub-collection results 1-sub-collection results S are combined into a collection result 1 corresponding to the speaker 1, and the collection result 1 is sent to the judging device. And then sequentially executing the process of collecting the audio test signals played by the loudspeaker 1 according to the sequence of the loudspeaker 2-loudspeaker T, so as to obtain the collection results 2-collection results T corresponding to the loudspeaker 2-loudspeaker T respectively, and sending the collection results 2-collection results T to the judging device respectively. Wherein each acquisition result comprises a sub-acquisition result 1-a sub-acquisition result S.

For each of the acquisition results 1-T, the following operations are performed:

When any one sub-acquisition result characterization included in any one acquisition result does not acquire an audio test signal, determining that the loudspeaker and/or the plurality of sound pickups corresponding to any one acquisition result are abnormal.

When the plurality of sub-acquisition results included in any one acquisition result represent the acquired audio test signals, respectively analyzing the acquired audio test signals respectively included in the plurality of sub-acquisition results to obtain acquisition signal parameters and acquisition playing parameters corresponding to each sub-acquisition result;

The method comprises the steps of respectively matching acquired signal parameters corresponding to a plurality of sub-acquisition results with test signal parameters of an audio test signal, respectively matching acquired playing parameters corresponding to a plurality of sub-acquisition results with test playing parameters of the audio test signal, and determining that a loudspeaker and/or a plurality of sound pickups corresponding to any one acquisition result are abnormal when any one acquired signal parameter or any one acquired playing parameter fails to match.

Conversely, when the acquired signal parameters and the acquired playing parameters corresponding to the sub-acquired results are successfully matched, it is determined that no abnormality exists in the loudspeaker and the sound pickup corresponding to any one of the acquired results.

The specific matching process of each acquisition result is the same as that of the second case, so the description of the second case will not be repeated here.

Optionally, when the judging device determines that the abnormal detection result is that the speaker and/or the pickup is abnormal according to any one of the collection results, the abnormal detection result may be reported before the analysis and judgment operation is performed on the next collection result, so that the related staff can manually overhaul the speaker and the pickup 1-pickup S corresponding to any one of the collection results. In this case, since the pickup 1 and the pickup S are inspected, there is no abnormality, and it is ensured that when the analysis and judgment operation is performed on the subsequent collected result, the abnormality detection can be completed by judging whether or not there is an abnormality in the speaker corresponding to the collected result, thereby reducing the calculation amount of the judgment device and improving the judgment efficiency.

Fig. 6 shows only a case where the pickup 1-pickup S is inspected before the analysis and judgment of the acquisition result corresponding to the speaker T, and if the pickup 1-pickup S is not inspected before the analysis and judgment of the acquisition result corresponding to the speaker T, the pickup 1-pickup S is processed so as to analyze and judge the acquisition result corresponding to the speaker 1.

Based on the above four conditions, the configuration scene of the single speaker Shan Sheyin, the multi-speaker single pickup, the single speaker multi-pickup and the multi-speaker multi-pickup can be covered, so that the self-checking requirement of most voice equipment can be met, and compared with the self-checking scheme in the related art, the self-checking method has wider coverage.

Based on the same concept of the above method, referring to fig. 7, an abnormality detection apparatus 700 for a voice device according to an embodiment of the present application is provided, where the apparatus 700 is capable of performing each step in the above method, and in order to avoid repetition, details are not described herein. The apparatus 700 comprises an acquisition unit 701 and a processing unit 702. In one scenario:

an acquisition unit 701 for acquiring an audio test signal;

The processing unit 702 is configured to control the at least one speaker to sequentially play the audio test signal, and control each pickup of the at least one pickup to acquire an acquisition result corresponding to each speaker when each speaker plays the audio test signal, where the acquisition result includes at least one sub-acquisition result, the at least one sub-acquisition result corresponds to the at least one pickup one by one, any two speakers of the at least one speaker do not play the audio test signal at the same time, and determine an anomaly detection result of the at least one speaker and the at least one pickup based on the acquisition result corresponding to each speaker.

In a possible implementation manner, the acquiring unit 701 is specifically configured to acquire an audio test signal, select a plurality of target audio signals from a plurality of pre-stored audio signals according to a frequency range supported by the at least one speaker, and combine the plurality of target audio signals according to a random arrangement manner to generate the audio test signal.

In a possible implementation manner, the processing unit 702 combines the multi-entry audio signals according to a random arrangement manner to generate the audio test signal, and is specifically configured to randomly select a group from a plurality of pre-stored candidate play parameters as a test play parameter, adjust respective gains of the multi-entry audio signals according to the test play parameter, and combine the adjusted multi-entry audio signals according to a random arrangement manner to generate the audio test signal.

In a possible implementation manner, when the voice device includes a speaker and a pickup, the processing unit 702 determines an abnormality detection result of the at least one speaker and the at least one pickup based on the collection result corresponding to each of the at least one speaker, and is specifically configured to determine that the speaker and/or the pickup are abnormal when the collection result indicates that the audio test signal is not collected, analyze the collected audio test signal included in the collection result to obtain a collection signal parameter and a collection play parameter when the collection signal parameter and the collection play parameter are both successfully matched, match the collection signal parameter and the test play parameter of the audio test signal, and determine that the speaker and/or the pickup are not abnormal when the collection signal parameter and the collection play parameter are both successfully matched.

In a possible implementation manner, when the voice device includes one speaker and a plurality of pickups, the processing unit 702 determines, based on the collection results corresponding to each of the at least one speaker and the at least one pickups, an anomaly detection result of each of the at least one speaker and the at least one pickups, and is specifically configured to determine that the speaker and/or the plurality of pickups are abnormal when any one sub-collection result included in the collection results characterizes that the audio test signal is not collected, analyze, when the sub-collection results included in the collection results all characterize the audio test signal, the collected audio test signal corresponding to each of the plurality of sub-collection results to obtain a collection signal parameter and a collection play parameter corresponding to each of the sub-collection results, match the collection signal parameters corresponding to each of the plurality of sub-collection results with a test signal parameter of the audio test signal, match the collection play parameters corresponding to each of the plurality of sub-collection results with a test signal of the audio test signal, and determine that the speaker and the plurality of pickups are not successfully matched when any one or any one sub-collection signal parameter fails or the plurality of sub-collection results are not matched with each other.

In a possible implementation manner, the processing unit 702 is configured to determine that the speaker or the plurality of microphones are abnormal when any one sub-acquisition result included in the acquisition result indicates that the audio test signal is not acquired, and is specifically configured to determine that the speaker or the plurality of microphones are abnormal when some sub-acquisition results included in the acquisition result indicate that the audio test signal is not acquired, and determine that the speaker or the plurality of microphones are abnormal when all sub-acquisition results included in the acquisition result indicate that the audio test signal is not acquired.

In a possible implementation manner, when the voice device includes a plurality of speakers and a sound pickup, the processing unit 702 determines, based on the collection results corresponding to each of the at least one speaker, an abnormality detection result of the at least one speaker and the at least one sound pickup, and specifically is used for matching a test signal parameter of the collection signal with a test play parameter of the audio test signal, for any one of the collection results corresponding to each of the plurality of speakers, determining that an abnormality exists in the speaker and/or the sound pickup corresponding to any one of the collection results when the any one of the collection results characterizes the audio test signal is not collected, analyzing the collected audio test signal included in any one of the collection results when the any one of the collection results characterizes the audio test signal is collected, obtaining a collection signal parameter and a collection play parameter, matching the collection signal parameter with a test signal parameter of the audio test signal, and determining that an abnormality exists in any one of the collection results corresponding to any one of the speakers and/or the sound pickup when the collection signal parameter fails or the audio test signal is not matched.

In a possible implementation manner, when the voice device comprises a plurality of speakers and a plurality of pickups, the processing unit 702 determines, based on the acquired results corresponding to the at least one speaker and the at least one pickups, an abnormal detection result of the at least one speaker and the at least one pickups, and is specifically configured to, for any one of the acquired results corresponding to the plurality of speakers, determine that the speaker and/or the plurality of pickups corresponding to the any one of the acquired results are abnormal when the any one of the acquired results is characterized by not acquiring the audio test signal, respectively analyze the acquired audio test signal corresponding to each of the plurality of sub-acquired results when the plurality of sub-acquired results are characterized by acquiring the audio test signal, respectively obtain an acquired signal parameter and an acquired play parameter corresponding to each of the sub-acquired results, respectively match the acquired signal parameter corresponding to each of the plurality of sub-acquired results with the test signal parameter of the audio test signal, respectively match the sub-acquired signal parameter corresponding to each of the plurality of sub-acquired results with the audio test signal, and match the audio test signal corresponding to each of the plurality of sub-acquired results when the plurality of sub-acquired results are matched with the audio test signal corresponding to each of the plurality of sub-acquired results and/or the plurality of pickups and the audio test signal corresponding to each of the plurality of sub-acquired parameters fails, and determining that the loudspeaker corresponding to any one acquisition result and the plurality of sound pick-up devices are not abnormal.

In a possible implementation manner, after determining the abnormality detection result of the at least one speaker and the at least one sound pickup, the processing unit 702 is further configured to report the abnormality detection result when the abnormality detection result characterizes that the at least one speaker or the at least one sound pickup is abnormal.

Based on the same concept of the above method, referring to fig. 8, a schematic structural diagram of an electronic device according to an embodiment of the present application is provided, where the electronic device includes at least one processor 802, and a memory 801 connected or coupled to the at least one processor 802, and further, the electronic device may further include a communication interface 803. The electronic device may interact with other devices via communication interface 803.

By way of example, the communication interface 803 may be a transceiver, a circuit, a bus, a module, a pin, or other type of communication interface. When the electronic device is a chip-type device or circuit, the communication interface 803 in the electronic device may also be an input/output circuit, and may input information (or called receiving information) and output information (or called transmitting information), and the processor may be an integrated processor or a microprocessor or an integrated circuit or a logic circuit, and the processor may determine the output information according to the input information.

The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units, or modules, which may be in electrical, mechanical, or other forms for information interaction between the devices, units, or modules. The processor 802 may cooperate with the memory 801 and the communication interface 803. The specific connection medium between the processor 802, the memory 801, and the communication interface 803 is not limited in the present application.

Optionally, referring to fig. 8, the processor 802, the memory 801 and the communication interface 803 are connected to each other through a bus. The bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.

In an embodiment of the present application, the memory 801 is used as a non-volatile computer readable storage medium for storing non-volatile software programs, non-volatile computer executable programs, and modules. The Memory 801 may include at least one type of storage medium, and may include, for example, flash Memory, hard disk, multimedia card, card Memory, random access Memory (Random Access Memory, RAM), static random access Memory (Static Random Access Memory, SRAM), programmable Read-Only Memory (Programmable Read Only Memory, PROM), read-Only Memory (ROM), charged erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM), magnetic Memory, magnetic disk, optical disk, and the like. Memory 801 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto. The memory 801 in the embodiments of the present application may also be circuitry or any other device capable of implementing a storage function for storing instructions, computer programs, and/or data.

In an embodiment of the present application, the processor 802 may be a general-purpose processor, such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, and may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the abnormality detection method for voice equipment disclosed in connection with the embodiment of the application can be directly embodied as the execution completion of a hardware processor or the execution completion of the combination execution of hardware and software modules in the processor.

By programming the processor 802, the code corresponding to the abnormality detection method for a voice device described in the foregoing embodiment may be cured into the chip, so that the chip can execute the steps of the foregoing abnormality detection method for a voice device during operation, and how to program the processor 802 is a technology known to those skilled in the art will not be repeated here.

In one or more embodiments, the memory 801 stores instructions executable by the at least one processor 802, and the at least one processor 802 may implement steps of any of the methods described above by invoking instructions or computer programs stored in the memory 801.

Embodiments of the present application also provide a computer-readable storage medium having stored thereon computer instructions which, when run on a computer, cause the computer to perform the steps of any of the methods described above.

Based on the same inventive concept, embodiments of the present application also provide a computer program product comprising computer program code which, when run on a computer, causes the computer to perform the anomaly detection method for a speech device as any one of the preceding discussion. Since the principle of the solution of the problem of the computer program product is similar to that of the abnormality detection method for the voice device, the implementation of the computer program product may refer to the implementation of the method, and the repetition is omitted.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of implementing the various method embodiments described above may be implemented by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs the steps comprising the method embodiments described above, and the storage medium described above includes various media capable of storing program code, such as ROM, RAM, magnetic or optical disk.

While specific embodiments of the application have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and the scope of the application is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the application, but such changes and modifications fall within the scope of the application. While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (10)

1. A method for detecting anomalies of a voice device, wherein the voice device comprises at least one speaker and at least one microphone, and the method comprises: Get audio test signal; Controlling the at least one speaker to play the audio test signal in sequence, and when each speaker plays, controlling each of the at least one pickup to collect the currently played audio test signal respectively, and obtaining a collection result corresponding to each speaker; wherein the collection result includes at least one sub-collection result, and the at least one sub-collection result corresponds to the at least one pickup one by one; any two of the at least one speaker do not play the audio test signal at the same time; Based on the collection results corresponding to each of the at least one speaker, abnormality detection results of the at least one speaker and the at least one pickup are determined. 2. The method according to claim 1, characterized in that the obtaining of the audio test signal comprises: Selecting a plurality of target audio signals from a plurality of pre-stored audio signals according to a frequency range supported by the at least one speaker; The multiple target audio signals are combined in a random arrangement to generate the audio test signal. 3. The method according to claim 2, characterized in that the step of combining the plurality of target audio signals in a random arrangement to generate the audio test signal comprises: Randomly select one set of pre-stored candidate playback parameters as a test playback parameter; The gains of the plurality of target audio signals are adjusted according to the test playback parameters, and the adjusted plurality of target audio signals are combined in a random arrangement to generate the audio test signal. 4. The method according to any one of claims 1 to 3, characterized in that when the voice device includes a speaker and a microphone, determining the abnormality detection result of the at least one speaker and the at least one microphone based on the collection result corresponding to each of the at least one speaker comprises: When the collection result indicates that the audio test signal is not collected, determining that an abnormality exists in the speaker and/or the pickup; When the acquisition result indicates that the audio test signal is acquired, the acquired audio test signal included in the acquisition result is analyzed to obtain acquisition signal parameters and acquisition playback parameters; Matching the acquisition signal parameters with the test signal parameters of the audio test signal, and matching the acquisition playback parameters with the test playback parameters of the audio test signal, and determining that the speaker and/or the pickup has an abnormality when the acquisition signal parameters or the acquisition playback parameters fail to match; When the acquisition signal parameters and the acquisition playback parameters are matched successfully, it is determined that there is no abnormality in the speaker and the pickup. 5. The method according to any one of claims 1 to 3, characterized in that when the voice device includes a speaker and a plurality of pickups, determining the abnormality detection result of the at least one speaker and the at least one pickup based on the collection results corresponding to each of the at least one speakers comprises: When any one of the sub-collection results included in the collection result indicates that the audio test signal is not collected, determining that an abnormality exists in the speaker and/or the plurality of pickups; When the multiple sub-acquisition results included in the acquisition result all represent that the audio test signal is acquired, respectively analyzing the acquired audio test signals included in each of the multiple sub-acquisition results to obtain acquisition signal parameters and acquisition playback parameters corresponding to each sub-acquisition result; Matching the acquisition signal parameters corresponding to each of the plurality of sub-acquisition results with the test signal parameters of the audio test signal, matching the acquisition playback parameters corresponding to each of the plurality of sub-acquisition results with the test playback parameters of the audio test signal, and determining that the speaker and/or the plurality of pickups are abnormal when any acquisition signal parameter or any acquisition playback parameter fails to match; When the acquisition signal parameters and the acquisition playback parameters corresponding to the plurality of sub-acquisition results are matched successfully, it is determined that there is no abnormality in the speaker and the plurality of pickups. 6. The method according to claim 5, characterized in that when any one of the sub-collection results included in the collection result indicates that the audio test signal is not collected, determining that the speaker or the plurality of pickups are abnormal comprises: When some of the sub-collection results included in the collection result indicate that the audio test signal is not collected, determining that some of the plurality of pickups are abnormal; When the plurality of sub-collection results included in the collection result all indicate that the audio test signal is not collected, it is determined that an abnormality exists in the speaker or the plurality of pickups. 7. The method according to any one of claims 1 to 3, characterized in that when the voice device includes a plurality of speakers and a microphone, determining the abnormality detection result of the at least one speaker and the at least one microphone based on the collection result corresponding to each of the at least one speakers comprises: For any one of the collection results corresponding to each of the multiple speakers, perform the following operations: When any one of the collection results indicates that the audio test signal is not collected, determining that the speaker and/or the pickup corresponding to the any one of the collection results is abnormal; When any one of the acquisition results indicates that the audio test signal is acquired, analyzing the acquired audio test signal included in any one of the acquisition results to obtain acquisition signal parameters and acquisition playback parameters; Matching the acquisition signal parameters with the test signal parameters of the audio test signal, and matching the acquisition playback parameters with the test playback parameters of the audio test signal, and when the acquisition signal parameters or the acquisition playback parameters fail to match, determining that the speaker and/or the pickup corresponding to any one of the acquisition results is abnormal; When the acquisition signal parameters and the acquisition playback parameters are matched successfully, it is determined that there is no abnormality in the loudspeaker and the pickup corresponding to any one of the acquisition results. 8. The method according to any one of claims 1 to 3, characterized in that when the voice device includes multiple speakers and multiple microphones, determining the abnormality detection result of the at least one speaker and the at least one microphone based on the collection result corresponding to each of the at least one speakers comprises: For any one of the collection results corresponding to each of the multiple speakers, perform the following operations: When any one of the sub-collection results included in any one of the collection results indicates that the audio test signal is not collected, determining that the speaker and/or the plurality of pickups corresponding to the any one of the collection results are abnormal; When the multiple sub-acquisition results included in any one of the acquisition results all represent that the audio test signal is acquired, respectively analyzing the acquired audio test signals included in each of the multiple sub-acquisition results to obtain acquisition signal parameters and acquisition playback parameters corresponding to each sub-acquisition result; Matching the acquisition signal parameters corresponding to each of the plurality of sub-acquisition results with the test signal parameters of the audio test signal, respectively, matching the acquisition playback parameters corresponding to each of the plurality of sub-acquisition results with the test playback parameters of the audio test signal, and determining that the speaker and/or the plurality of pickups corresponding to any one of the acquisition results are abnormal when any one of the acquisition signal parameters or any one of the acquisition playback parameters fails to match; When the acquisition signal parameters and the acquisition playback parameters corresponding to the multiple sub-acquisition results are matched successfully, it is determined that there is no abnormality in the loudspeaker and the multiple pickups corresponding to any one of the acquisition results. 9. An abnormality detection device for a voice device, characterized in that the voice device includes at least one speaker and at least one pickup, and the device includes: An acquisition unit, used for acquiring an audio test signal; A processing unit is used to control the at least one speaker to play the audio test signal in sequence, and when each speaker plays, control each of the at least one pickup to collect the audio test signal currently being played, and obtain a collection result corresponding to each speaker; wherein the collection result includes at least one sub-collection result, and the at least one sub-collection result corresponds one-to-one with the at least one pickup; any two speakers of the at least one speaker do not play the audio test signal at the same time; based on the collection results corresponding to each of the at least one speakers, determine the abnormality detection results of the at least one speaker and the at least one pickup. 10. An electronic device, comprising: Memory, for storing computer instructions; A processor is connected to the memory, and is used to execute computer instructions in the memory, and implement the method according to any one of claims 1 to 8 when executing the computer instructions.