CN108597484A - A kind of multi-mode singing system - Google Patents

Abstract

The invention discloses a multi-mode singing system, which includes a human-computer interaction module, a singing mode switching module, a singing auxiliary module, a song updating module and a central processing unit; the singing mode includes a stand-alone singing mode, a PK singing mode, and a score singing mode and training singing mode. The invention has simple operation and diversified singing modes, which can meet the singing needs of different users; realizes the on-demand automatic update of the music library data, so that users can freely choose songs; multiple accounts can communicate online, PK, and have strong entertainment; The recording and sharing of the singing video can be carried out as required; the original sound audio data can be automatically played through the earphone module during the singing process, so that the singer's guidance can be realized without interrupting the singing or switching the accompaniment/original sound mode.

Description

A multi-mode singing system

technical field

The invention relates to the field of software applications, in particular to a multi-mode singing system.

Background technique

Existing singing software kind is less, generally has the following defects:

1. The singing mode is single, unable to meet various singing needs;

2. The data in the music library is limited, and it is easy to happen that there is no song that the user wants to sing;

3. During the singing process, the original sound audio data can only be obtained by interrupting the singing or switching the accompaniment/original sound mode;

Contents of the invention

In order to solve the above problems, the present invention provides a multi-mode singing system, which is easy to operate, has diversified singing modes, and at the same time realizes automatic update of music library data on demand.

In order to achieve the above object, the technical scheme that the present invention takes is:

A multi-mode singing system, including a human-computer interaction module, which is used to complete user registration, input of control commands and data demand commands, and is used for the access of microphone equipment and earphone modules;

The singing mode switching module is used to switch the singing mode, the singing scene and the song to be sung according to the control command input by the human-computer interaction module; the singing mode includes a stand-alone singing mode, a PK singing mode, a scoring singing mode and a training singing mode;

The singing auxiliary module is used to start the earphone module according to the evaluation result of the user's singing situation, so as to realize the playback of the corresponding singing original audio data;

The song update module is used to obtain related song data through the data upload module and data download module; a data review module is built in to review the uploaded/downloaded song data. If it does not meet the requirements, a dialog box will pop up remind the user in the form of and delete the corresponding data;

The central processing unit is used to coordinate the above modules to work.

Preferably, the PK singing mode is provided with a

The online communication module is used for communication, PK and sharing between accounts; the initiator can establish a temporary group according to the needs, and the number of people in the group is 5-10; all communication data is sent to The central processing unit performs real-time storage. Once sensitive words are found, the central processing unit issues a control command to close the module and remind in the form of a pop-up dialog box; it is also used to make voice/video calls with the specified account according to the selection. Before making a call, you need to send a call request to the corresponding account, and the module can only be activated after the account returns a confirmation message;

Preferably, the training singing mode is provided with

The audio frequency collection module is used to carry out the collection of the practitioner's voice audio data through the pickup, and sends the collected data to the pronunciation standard evaluation module;

The mouth shape image acquisition module is used to collect the user's mouth shape data through the camera, and send the collected data to the pronunciation standard evaluation module;

The characteristic signal collection module is used to collect the characteristic signal of the speaker through the sensor group according to the preset frequency, and send the collected characteristic signal to the pronunciation standard evaluation module, the characteristic signal includes subglottic pressure, glottic airflow and sound level ;

Respiratory frequency collection module, carries out the collection of practitioner's respiration frequency by respiratory frequency sensor, and sends the collected data to pronunciation standard assessment module;

The pitch extraction module is used to extract the pitch from the audio frame of the audio data after the denoising process;

The beat extraction module is used to obtain the pitch of the audio frame from the pitch extraction module, accumulate and analyze the pitch changes of the audio frame, and extract the beat information of the melody segment after judging the melody segment contained therein;

Pronunciation standard evaluation module, used for evaluating the pronunciation standard according to the received audio data, mouth shape image data, characteristic model data, respiratory rate data, pitch data and beat data, and performing evaluation results in the form of a table It shows that each row in the table includes at least the evaluation subject, full score, current score, points for improvement and improvement plan.

Preferably, the data review module is used to review the received data for viruses, types, and sensitive words through a preset algorithm, and all three items must meet to pass the review.

Preferably, it also includes a singing data recording module, which is used to record the audio data of the user's singing through the microphone and the sound pickup module according to the needs of the user.

Preferably, a data sharing module is also included, which is used to share the recorded audio data according to the needs of the users after the user identification is completed, wherein each user can only obtain their own audio data.

Preferably, the data sharing module shares the audio data through the mail automatic editing and sending module. After the user completes the identity verification, he selects the audio data to be shared, and the system pops up a dialog box requiring the user to input the associated mailbox information. After the mailbox information is confirmed to be input, the mail The automatic editing and sending module is started, and the selected audio data is sent to the input mailbox in the mode of uploading attachments.

Preferably, the human-computer interaction module is composed of a high-performance server and its touch screen.

Preferably, it also includes an audio data appreciating module, and realizes appreciating the selected audio data through the earphone module.

Preferably, the sensor group includes an oral air pressure sensor, an oral air flow sensor and a small microphone.

The present invention has the following beneficial effects:

The operation is simple and the singing modes are diversified, which can meet the singing needs of different users; the music library data can be automatically updated on demand, so that users can freely choose songs; multiple accounts can communicate online, PK, which is highly entertaining; It is necessary to share the recording of the singing video; during the singing process, the original sound audio data can be automatically played through the earphone module, so that the singer can be guided without interrupting the singing or switching the accompaniment/original sound mode.

Description of drawings

FIG. 1 is a system block diagram of a multi-mode singing system according to an embodiment of the present invention.

Detailed ways

In order to make the objects and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

As shown in Figure 1, the embodiment of the present invention provides a multi-mode singing system, including a human-computer interaction module for completing user registration, input of control commands and data demand commands, and for connecting microphone equipment and earphone modules enter;

The singing mode switching module is used to switch the singing mode, the singing scene and the song to be sung according to the control command input by the human-computer interaction module; the singing mode includes a stand-alone singing mode, a PK singing mode, a scoring singing mode and a training singing mode;

The singing auxiliary module is used to start the earphone module according to the evaluation result of the user's singing situation, so as to realize the playback of the corresponding singing original audio data;

The song update module is used to obtain related song data through the data upload module and data download module; a data review module is built in to review the uploaded/downloaded song data. If it does not meet the requirements, a dialog box will pop up remind the user in the form of and delete the corresponding data;

The central processing unit is used to coordinate the above modules to work.

The PK singing mode is provided with a

The online communication module is used for communication, PK and sharing between accounts; the initiator can establish a temporary group according to the needs, and the number of people in the group is 5-10; all communication data is sent to The central processing unit performs real-time storage. Once sensitive words are found, the central processing unit issues a control command to close the module and remind in the form of a pop-up dialog box; it is also used to make voice/video calls with the specified account according to the selection. Before making a call, you need to send a call request to the corresponding account, and the module can only be activated after the account returns a confirmation message;

The training singing mode is provided with

The audio frequency collection module is used to carry out the collection of the practitioner's voice audio data through the pickup, and sends the collected data to the pronunciation standard evaluation module;

The mouth shape image acquisition module is used to collect the user's mouth shape data through the camera, and send the collected data to the pronunciation standard evaluation module;

The characteristic signal collection module is used to collect the characteristic signal of the speaker through the sensor group according to the preset frequency, and send the collected characteristic signal to the pronunciation standard evaluation module, the characteristic signal includes subglottic pressure, glottic airflow and sound level ; installed in the microphone;

Respiratory frequency acquisition module, which collects the respiratory rate of the practitioner through the respiratory frequency sensor, and sends the collected data to the pronunciation standard evaluation module; it is installed in the microphone;

The pitch extraction module is used to extract the pitch from the audio frame of the audio data after the denoising process;

The beat extraction module is used to obtain the pitch of the audio frame from the pitch extraction module, accumulate and analyze the pitch changes of the audio frame, and extract the beat information of the melody segment after judging the melody segment contained therein;

Pronunciation standard evaluation module, used for evaluating the pronunciation standard according to the received audio data, mouth shape image data, characteristic model data, respiratory rate data, pitch data and beat data, and performing evaluation results in the form of a table It shows that each row in the table includes at least the evaluation subject, full score, current score, points for improvement and improvement plan.

The data review module is used to review the received data for viruses, types, and sensitive words through a preset algorithm, and all three items must meet to pass the review.

It also includes a singing data recording module, which is used to record the user's singing audio data through the microphone and the sound pickup module according to the needs of the user.

It also includes a data sharing module, which is used to share the recorded audio data after the user identity identification is completed according to the needs of the users, wherein each user can only obtain their own audio data.

The data sharing module shares the audio data through the automatic mail editing and sending module. After the user completes the identity verification, he selects the audio data to be shared, and the system pops up a dialog box requiring the user to input the associated mailbox information. After the mailbox information is confirmed and input, the mail is automatically edited and sent The module starts and sends the selected audio data to the input mailbox in the mode of attachment upload.

The human-computer interaction module is composed of a high-performance server and its touch screen.

It also includes an audio data appreciating module, which realizes appreciating the selected audio data through the earphone module.

The sensor group includes an oral air pressure sensor, an oral air flow sensor and a small radio.

The above is only a preferred embodiment of the present invention, it should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications should also be It is regarded as the protection scope of the present invention.

Claims (10)

1. a kind of multi-mode singing system, which is characterized in that including

The input of human-computer interaction module, the registration for completing user, control command and demand data order, and it is used for Mike The access of wind devices and handset module；

Mode switch module is sung, the control command for being inputted according to human-computer interaction module carries out performance pattern, sings scene And the switching to be given song recitals；The performance pattern include single machine sing pattern, PK sing pattern, scoring performance pattern and Training performance pattern；

Supplementary module is sung, the assessment result for singing situation according to user carries out the startup of handset module, realizes corresponding Sing the broadcasting of former sound audio data；

Song update module, the acquisition for carrying out associated song data by data uploading module and data download module；It is interior If a data-auditing module is audited for the song data to upload/download, if against regulation, to pop up dialogue The form of frame reminds user, and deletes corresponding data；

Central processing unit works for coordinating above-mentioned module.

2. a kind of multi-mode singing system as described in claim 1, which is characterized in that the PK, which is sung, is equipped with one in pattern

Online AC module is used for the mutual exchange of each account, PK and shares；It can be interim by mobilizing people to carry out as needed The foundation of group, personnel are 5-10 people in group；The data of all exchanges using script record pattern be sent to central processing unit into Row storage in real time, once finding sensitive wording, central processing unit sends out control command, closes the module, and to pop up dialog box Pattern reminded；It is additionally operable to carry out voice/video call with specified account according to selection, needs first to send out before being conversed It send call request to corresponding account, the enabling of the module can be carried out after the account returns to confirmation message.

3. a kind of multi-mode singing system as described in claim 1, which is characterized in that be equipped in the training performance pattern

Audio collection module, for the acquisition by sound pick-up progress practitioner's sounding audio-frequency data, and by collected data It is sent to pronunciation standard evaluation module；

Mouth shape image acquisition module, the acquisition for carrying out user's mouth shape data by camera, and collected data are sent out It is sent to pronunciation standard evaluation module；

Characteristic signal acquisition module, the characteristic signal for acquiring sounder by sensor group according to predeterminated frequency, and will adopt The characteristic signal collected is sent to pronunciation standard evaluation module, and the characteristic signal includes pressure subglottic, glottal air flow and sound level；

Respiratory rate acquisition module, the acquisition of the respiratory rate of practitioner is carried out by respiratory frequen, and will be collected Data be sent to pronunciation standard evaluation module；

Pitch extraction module, for extracting pitch from the audio frame of the audio data after denoising；

Beat extraction module, the pitch for obtaining audio frame from pitch extraction module, the change in pitch of cumulative analysis audio frame Situation judges the beat information that the melody section is extracted after melody section wherein included；

Pronunciation standard evaluation module, the audio data received for basis, mouth shape image data, feature model data, breathing Frequency data, pitch data and beat data carry out the assessment for pronunciation standard, and carry out assessment result in table form Display, include at least assessment theme per a line in the table, full marks, this score, need improvement and improvement project.

4. a kind of multi-mode singing system as described in claim 1, which is characterized in that the data-auditing module, for leading to The examination that preset algorithm carries out the data received virus, type, sensibility vocabulary is crossed, three is needed and meets and could pass through entirely Audit.

5. a kind of multi-mode singing system as described in claim 1, which is characterized in that further include that a singing data records mould Block, for being needed through microphone according to user and being the recording that pickup module carries out that user sings audio data.

6. a kind of multi-mode singing system as described in claim 1, which is characterized in that further include a data sharing module, use It is needed after completing user identity identification according to user by carrying out the shared of recorded audio data, wherein Mei Geyong Family can only obtain respective audio data.

7. a kind of multi-mode singing system as claimed in claim 5, which is characterized in that the data sharing module passes through mail Automatically editor's sending module carries out the shared of audio data, and user selects to need audio data to be sharing after completing authentication, System pop-up dialog box needs user to input relevant mailbox information, and after mailbox message confirmation input, mail edits sending module automatically Start, selected audio data is sent to inputted mailbox with the pattern that attachment uploads.

8. a kind of multi-mode singing system as described in claim 1, which is characterized in that the human-computer interaction module is by high-performance Server and its touch display screen composition.

9. a kind of multi-mode singing system as described in claim 1, which is characterized in that further include that an audio data appreciates mould Block realizes the appreciation of selected audio data by handset module.

10. a kind of multi-mode singing system as claimed in claim 3, which is characterized in that the sensor group includes oral cavity gas Pressure sensor, oral airflow sensor and small-sized radio reception device.