JP2024087465A - Voice processing device - Google Patents

Abstract

To provide a voice processing device which can appropriately perform processing corresponding to voice uttered by a user.SOLUTION: An outside-vehicle environment detection system includes: a voice analysis unit for detecting a predetermined voice command included in voice data based on voice data; and a control signal generation unit for generating a control signal instructing processing which the voice command indicates based on the voice command detected by the voice analysis unit. The voice command includes: a first portion; a second portion which is arranged after the first portion and contains a verb; and a third portion which is arranged after the second portion and is the same as the first portion.SELECTED DRAWING: Figure 4

Description

This disclosure relates to a voice processing device that performs processing based on voice.

In recent years, voice recognition technology that recognizes voices uttered by a user is often used. For example, Patent Document 1 discloses a voice recognition device that recognizes voices uttered by a user.

JP 2018-045127 A

In a device that performs processing based on the voice uttered by a user, it is desirable to perform processing appropriately according to the voice uttered by the user.

It is desirable to provide a voice processing device that can appropriately process voice uttered by a user.

A voice processing device according to an embodiment of the present disclosure includes a voice analysis unit and a control signal generation unit. The voice analysis unit detects a predetermined voice command included in the voice data based on the voice data. The control signal generation unit generates a control signal that instructs a process indicated by the voice command detected by the voice analysis unit based on the voice command. The voice command includes a first portion, a second portion that is located after the first portion and includes a verb, and a third portion that is located after the second portion and is the same as the first portion.

According to an embodiment of the voice processing device of the present disclosure, it is possible to appropriately perform processing according to the voice uttered by the user.

1 is a configuration diagram illustrating an example of a configuration of a voice processing system according to an embodiment of the present disclosure. FIG. 2 is an explanatory diagram illustrating an example of a voice command. FIG. 11 is an explanatory diagram illustrating another example of a voice command. FIG. 11 is an explanatory diagram illustrating another example of a voice command.

The following describes in detail the embodiments of the present disclosure with reference to the drawings.

<Embodiment>
[Configuration example]
1 shows an example of a configuration of a voice processing system 1 including a voice processing device according to an embodiment. In this example, the voice processing system 1 is applied to a vehicle 10. The vehicle 10 is a vehicle such as an automobile. The vehicle 10 includes a user interface 11, a microphone 12, a processing unit 20, a communication unit 13, a navigation processing unit 14, a headlamp control unit 15, and a door lock control unit 16.

The user interface 11 includes, for example, a display panel, a touch panel, various buttons, etc., and is configured to accept operations by the occupant of the vehicle 10 and present various information to the occupant of the vehicle 10.

The microphone 12 is configured to convert sound waves corresponding to the voice emitted by the occupant of the vehicle 10 into an electrical signal (audio signal).

The processing unit 20 is configured to include, for example, one or more processors and one or more memories. The processing unit 20 has a voice analysis unit 21 and a control signal generation unit 22.

The voice analysis unit 21 is configured to analyze voice based on the voice signal supplied from the microphone 12. Specifically, the voice analysis unit 21 first generates voice data by performing AD (Analog to Digital) conversion at a predetermined sampling rate based on the voice signal supplied from the microphone 12. Then, the voice analysis unit 21 generates spectrum data by performing Fourier transform based on this voice data. Specifically, the voice analysis unit 21 generates a series of spectrum data by sequentially generating spectrum data at a predetermined time interval. The voice analysis unit 21 generates sentence data including sentences indicated by the voice data by extracting characters and words contained in the voice data based on each of the series of spectrum data. Then, the voice analysis unit 21 detects a voice command indicating the content of the process instructed by the occupant of the vehicle 10 based on the sentence data. The voice commands available in the voice processing system 1 are predetermined. In this example, the voice analysis unit 21 detects the voice command based on the text data, but this is not limited to this. Instead, for example, the voice command may be detected based on the voice data, or the voice command may be detected based on the spectrum data. The voice analysis unit 21 then supplies the detection result of the voice command to the control signal generation unit 22.

The control signal generating unit 22 is configured to generate a control signal according to the processing indicated by the voice command based on the detection result of the voice command by the voice analyzing unit 21. The processing unit 20 then supplies this control signal to the communication unit 13, the navigation processing unit 14, the headlamp control unit 15, and the door lock control unit 16.

The communication unit 13 is configured to communicate with external devices by performing wireless communication, such as a wireless LAN (Local Area Network) or Bluetooth (registered trademark). In this example, the communication unit 13 is configured to communicate with a smartphone 100 of an occupant of the vehicle 10.

The navigation processing unit 14 is configured to determine a route (planned driving route) to a destination along which the vehicle 10 should travel, and to provide route information of the planned driving route to the occupant of the vehicle 10, thereby guiding the vehicle 10 along the determined planned driving route. The navigation processing unit 14 acquires the position of the vehicle 10 on the ground using a global navigation satellite system (GNSS) such as a global positioning system (GPS), and determines the planned driving route of the vehicle 10 using a map information database including information on road maps. The navigation processing unit 14 may, for example, store a map information database and determine the planned driving route using the stored map information database, or may, for example, determine the planned driving route by communicating with a network server in which the map information database is stored. The navigation processing unit 14 is configured to, for example, determine a planned driving route to a destination based on information about the destination input by the occupant of the vehicle 10 by operating the user interface 11, and provide route information about the determined planned driving route to the occupant using the user interface 11.

The headlamp control unit 15 is configured to control the on and off operations of the headlamp that emits light ahead of the vehicle 10.

The door lock control unit 16 is configured to control the locking and unlocking of the doors of the vehicle 10 when passengers get in and out of the vehicle.

In this example, the smartphone 100 is a high-function mobile phone owned by a passenger of the vehicle 10. The smartphone 100 stores various data including, for example, phone book data. The smartphone 100 is capable of communicating with the communication unit 13 of the vehicle 10.

In this configuration, in the voice processing system 1, the processing unit 20 detects voice commands based on the voice signal supplied from the microphone 12, thereby grasping the voice instructions of the occupant of the vehicle 1, and generates a control signal. Then, the communication unit 13, navigation processing unit 14, headlamp control unit 15, and door lock control unit 16 perform processing according to the voice instructions of the occupant based on this control signal.

Here, the processing unit 20 corresponds to a specific example of a "voice processing device" in one embodiment of the present disclosure. The voice analysis unit 21 corresponds to a specific example of a "voice analysis unit" in one embodiment of the present disclosure. The control signal generation unit 22 corresponds to a specific example of a "control signal generation unit" in one embodiment of the present disclosure. The vehicle 10 corresponds to a specific example of a "vehicle" in one embodiment of the present disclosure.

[Actions and Functions]
Next, the operation and function of the voice processing system 1 of the present embodiment will be described.

(Overall operation overview)
First, the operation of the voice processing system 1 will be described with reference to FIGS. 1 to 3. The user interface 11 accepts operations by the occupant of the vehicle 10 and presents various information to the occupant of the vehicle 10. The microphone 12 converts sound waves corresponding to the voice uttered by the occupant of the vehicle 10 into an electric signal (voice signal). The voice analysis unit 21 of the processing unit 20 detects a voice command based on the voice signal supplied from the microphone 12. The control signal generation unit 22 generates a control signal corresponding to the process indicated by the voice command based on the detection result of the voice command by the voice analysis unit 21. The communication unit 13 communicates with the smartphone 100 of the occupant of the vehicle 10. The navigation processing unit 14 determines a route (planned driving route) to a destination to which the vehicle 10 should travel, and provides route information of the planned driving route to the occupant of the vehicle 10, thereby guiding the vehicle 10 along the determined planned driving route. The headlamp control unit 15 controls the turning on and off of the headlamp that irradiates light ahead of the vehicle 10. The door lock control unit 16 controls the locking and unlocking of the doors of the vehicle 10 when passengers get in and out of the vehicle.

(Detailed operation)
2 shows an example of a voice command. In this example, the passenger of the vehicle 10 can cause the communication unit 13, the navigation processing unit 14, the headlamp control unit 15, and the door lock control unit 16 to perform processing by uttering a voice including the voice command.

For example, as shown in FIG. 2(A), if the sentence included in the voice data is "Call A", the voice analysis unit 21 detects this voice command instructing to call A, and the control signal generation unit 22 generates a control signal that controls the smartphone 100 to call A. The processing unit 20 supplies this control signal to the communication unit 13. The communication unit 13 transmits this control signal to the smartphone 100. Based on this control signal, the smartphone 100 identifies A's phone number using the phone book data, and performs processing to call A using this phone number.

Also, for example, as shown in FIG. 2(B), if the sentence included in the voice data is "I want to go to City B," the voice analysis unit 21 detects this voice command instructing the provision of a route to City B, and the control signal generation unit 22 generates a control signal for controlling the navigation processing unit 14 to determine a planned driving route to City B based on the information supplied from the voice analysis unit 21. The processing unit 20 supplies this control signal to the navigation processing unit 14. The navigation processing unit 14 determines the planned driving route to City B based on this control signal, and causes the user interface 11 to display the determined planned driving route.

Also, for example, as shown in FIG. 2(C), if the sentence included in the voice data is "Turn off the headlamps," the voice analysis unit 21 detects this voice command instructing to turn off the headlamps, and the control signal generation unit 22 generates a control signal that controls the headlamp control unit 15 to turn off the headlamps. The processing unit 20 supplies this control signal to the headlamp control unit 15. Based on this control signal, the headlamp control unit 15 controls the operation of the headlamps to turn off the headlamps.

For example, as shown in FIG. 2(D), if the sentence included in the voice data is "lock the door," the voice analysis unit 21 detects this voice command instructing to lock the door, and the control signal generation unit 22 generates a control signal that controls the door lock control unit 16 to lock the door. The processing unit 20 supplies this control signal to the door lock control unit 16. The door lock control unit 16 locks the door based on this control signal.

For example, in FIG. 2(A), the number of characters in "Mr. A" may be small. Also, in FIG. 2(B), the number of characters in "City B" may be small. The voice analysis unit 21 may have difficulty recognizing such words with few characters. In addition, since there is a lot of noise in the vehicle 10, such as driving sounds, the voice analysis unit 21 may have difficulty recognizing such words with few characters.

Figure 3 shows a more specific example of a voice command. For example, "mama" is short, having only two characters, and is shorter than, for example, "call me." Also, "mama" is a repetition of the same sound. Therefore, it may be difficult for the voice analysis unit 21 to recognize this "mama" portion. Also, for example, "tsu-shi" is short, having only two characters, and is shorter than "want to go." Therefore, it may be difficult for the voice analysis unit 21 to recognize this "tsu-shi" portion.

Therefore, in order to make it easier to recognize words with such a small number of characters, the voice analysis unit 21 can also analyze voice commands such as those shown below.

Figure 4 shows another example of a voice command. These voice commands include three parts P1 to P3. The sentence consisting of parts P1 and P2 is the same as the sentence in Figure 3. Part P3 is the same as part P1. For example, part P2 includes a verb. And parts P1 and P3 include the object of the verb. This object can be, for example, a common noun, a proper noun, a pronoun, an abbreviation, etc.

For example, as shown in FIG. 4A, if the sentence included in the voice data is "Call Mama, Mama," the voice analysis unit 21 detects that there is a high similarity between part P1 ("Mama") and part P3 ("Mama"). The passenger repeatedly utters the "Mama" part in this way. As a result, the number of phonemes to be analyzed increases, and the voice analysis unit 21 can recognize this "Mama." The control signal generation unit 22 then generates a control signal that controls the smartphone 100 to call Mama. The processing unit 20 supplies this control signal to the communication unit 13. The communication unit 13 transmits this control signal to the smartphone 100. Based on this control signal, the smartphone 100 identifies a telephone number using the telephone directory data, and performs processing to make a call using this telephone number.

For example, as shown in FIG. 4B, if the sentence included in the voice data is "I want to go to Tsu City, Tsu City, Mie Prefecture," the voice analysis unit 21 detects that there is a high similarity between part P1 ("Tsu City") and part P3 ("Tsu City"). The occupant repeatedly utters the part "Tsu City" in this way. As a result, the number of phonemes to be analyzed increases, and the voice analysis unit 21 can recognize "Tsu City." Then, based on the information supplied from the voice analysis unit 21, the control signal generation unit 22 generates a control signal that controls the navigation processing unit 14 to determine a planned driving route to Tsu City, Mie Prefecture. The processing unit 20 supplies this control signal to the navigation processing unit 14. Based on this control signal, the navigation processing unit 14 determines a planned driving route to Tsu City, Mie Prefecture, and displays the determined planned driving route on the user interface 11.

For example, when a short word is spoken by another person, humans may find it difficult to recognize the short word. In this case, if the word is spoken again, humans will find it easier to recognize the short word. Similarly, when the voice analysis unit 21 detects parts P1 and P3 that are highly similar to each other, it can accurately recognize the parts P1 and P3. This allows the voice processing system 1 to improve the recognition accuracy of sentences containing short words and appropriately perform processing according to the voice spoken by the user.

In this way, the voice processing system 1 is provided with a voice analysis unit 21 that detects a predetermined voice command contained in the voice data based on the voice data, and a control signal generation unit 22 that generates a control signal instructing a process indicated by the voice command based on the voice command detected by the voice analysis unit 21. The voice command includes a first part (part P1), a second part (part P2) that is arranged after the first part and includes a verb, and a third part (part P3) that is arranged after the second part and is the same as the first part. This allows the voice analysis unit 21 to accurately recognize parts P1 and P3. As a result, the voice processing system 1 can improve the recognition accuracy of sentences that include short words, for example, and can appropriately perform processing according to the voice uttered by the user.

Furthermore, in the voice processing system 1, the number of characters in the first part (part P1) is made smaller than the number of characters in the second part (part P2). Even in such a case, since there is a part P3 that is the same as part P1, this part with a smaller number of characters is repeated, and therefore this part with a smaller number of characters can be recognized with high accuracy. As a result, the voice processing system 1 can appropriately perform processing according to the voice uttered by the user.

In addition, in the speech processing system 1, the first part includes the object of the verb included in the second part. The object may be, for example, not only a common noun but also a proper noun, pronoun, abbreviation, etc., and may be difficult to recognize. In the speech processing system 1, even in such cases, there is a part P3 that is the same as the part P1, so that even if the object is difficult to recognize, for example, the object is repeated and the object can be recognized with high accuracy. As a result, the speech processing system 1 can appropriately perform processing according to the voice uttered by the user.

In addition, in the voice processing system 1, the processing unit 20 is provided in the vehicle 1. The vehicle 1 then performs processing according to the voice command based on the control signal. This allows the voice processing system 1 to appropriately perform processing according to the voice uttered by the user even in a vehicle where there is a lot of noise, such as driving sounds.

[effect]
As described above, in this embodiment, a voice analysis unit detects a predetermined voice command included in the voice data based on the voice data, and a control signal generation unit generates a control signal instructing a process indicated by the voice command based on the voice command detected by the voice analysis unit. The voice command includes a first part, a second part that is arranged after the first part and includes a verb, and a third part that is arranged after the second part and is the same as the first part. This makes it possible to appropriately perform a process according to the voice uttered by the user.

In this embodiment, the number of characters in the first part is set to be less than the number of characters in the second part, so that processing can be appropriately performed according to the voice uttered by the user.

In this embodiment, the first part includes the object of the verb contained in the second part, so that appropriate processing can be performed according to the voice uttered by the user.

In this embodiment, the processing unit is provided in the vehicle. The vehicle then performs processing in response to the voice command based on the control signal. This allows appropriate processing to be performed in response to the voice uttered by the user.

The present invention has been described above using embodiments, but the present invention is not limited to these embodiments and various modifications are possible.

For example, in the above embodiment, the present technology is applied to a vehicle 10, but the present technology is not limited to this and can be applied to various devices instead. Specifically, the present technology may be applied to, for example, a smartphone or a smart speaker.

In addition, for example, the voice commands shown in Figures 2 to 4 are just examples, and other voice commands may be used.

The effects described in this specification are merely examples, and the effects of the present disclosure are not limited to the effects described in this specification. Therefore, other effects may be obtained with respect to the present disclosure.

Furthermore, the present disclosure may take the following forms:

(1)
a voice analysis unit that detects a predetermined voice command included in the voice data based on the voice data;
a control signal generating unit configured to generate a control signal for instructing a process indicated by the voice command based on the voice command detected by the voice analyzing unit,
The voice command includes a first portion, a second portion located after the first portion and including a verb, and a third portion located after the second portion and identical to the first portion.
(2)
The speech processing device according to (1), wherein the number of characters in the first portion is smaller than the number of characters in the second portion.
(3)
The speech processing device according to (1) or (2), wherein the first portion includes an object of the verb included in the second portion.
(4)
The voice processing device is provided in a vehicle,
The voice processing device according to any one of (1) to (3), wherein the vehicle performs processing according to the voice command based on the control signal.

1... voice processing system, 10... vehicle, 11... user interface, 12... microphone, 13... communication unit, 14... navigation processing unit, 15... headlamp control unit, 16... door lock control unit, 20... processing unit, 21... voice analysis unit, 22... control signal generation unit, 100... smartphone.

Claims (4)

a voice analysis unit that detects a predetermined voice command included in the voice data based on the voice data;
a control signal generating unit configured to generate a control signal for instructing a process indicated by the voice command based on the voice command detected by the voice analyzing unit,
The voice command includes a first portion, a second portion located after the first portion and including a verb, and a third portion located after the second portion and identical to the first portion. The speech processing device of claim 1 , wherein the number of characters in the first portion is less than the number of characters in the second portion. The speech processing device according to claim 1 , wherein the first portion includes an object of the verb included in the second portion. The voice processing device is provided in a vehicle,
The voice processing device according to claim 1 , wherein the vehicle performs processing in accordance with the voice command based on the control signal.

Images