CN102404278A - Song requesting system based on voiceprint recognition and application method thereof - Google Patents
Song requesting system based on voiceprint recognition and application method thereof Download PDFInfo
- Publication number
- CN102404278A CN102404278A CN2010102734656A CN201010273465A CN102404278A CN 102404278 A CN102404278 A CN 102404278A CN 2010102734656 A CN2010102734656 A CN 2010102734656A CN 201010273465 A CN201010273465 A CN 201010273465A CN 102404278 A CN102404278 A CN 102404278A
- Authority
- CN
- China
- Prior art keywords
- user
- song
- sound
- voice signal
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a song requesting system based on voiceprint recognition, which comprises: the system comprises a song database, a recording module, a voice signal processing module, a voiceprint feature extraction module and a voiceprint feature comparison module. The invention also discloses an application method of the song requesting system, which comprises the following steps: recording the voice of a user; preprocessing the recorded voice signal; extracting voiceprint characteristics of a user contained in the voice signal and establishing a user voiceprint model; and performing similarity matching on the voiceprint model of the user and the voiceprint models of the songs in the database, and returning a matched song list. The song requesting system and the application method thereof can improve the experience of singing of the user. When the user requests songs, the song requesting system can automatically retrieve songs suitable for the user to sing according to the voiceprint characteristics of the user and provide the songs for the user to select, so that the singing effect of the user is guaranteed.
Description
Technical field
The present invention relates to a kind of order programme, especially a kind of order programme based on the Application on Voiceprint Recognition technology.The invention still further relates to a kind of application process of this order programme.
Background technology
Along with people's is to the pursuit of quality of the life, and people's free life becomes more and more abundanter, and singing is very popular a kind of entertainment way; People usually can stay at home or the singing-hall in program request oneself like or present popular song; But because everyone is in the difference of aspects such as vocal cords structure, tune, some song not convenience point singer is sung; And present order programme can only provide common list of songs; Can not select to be fit to the song that this user sings according to user's sound characteristic, if the song of user's program request is not suitable for oneself, the effect of performance will be poor; Not only do not reach the purpose of amusement, oneself and audience are felt disappointed.
Summary of the invention
The technical problem that the present invention will solve provides a kind of order programme based on Application on Voiceprint Recognition, and it can improve the experience that the user sings.
For solving the problems of the technologies described above, the order programme based on Application on Voiceprint Recognition of the present invention comprises:
Song database stores song and corresponding song sound-groove model thereof, and this song sound-groove model is set up through the vocal print characteristic of extracting song;
Recording module is used to record user's voice;
Voice signal processing module is connected with recording module, and the voice signal that is used for recording module is recorded to carries out preliminary treatment;
The vocal print characteristic extracting module is connected with voice signal processing module, is used for the analyzing speech signal, and from voice signal, extracts the vocal print characteristic, sets up sound-groove model;
Vocal print characteristic comparing module; Be connected with the vocal print characteristic extracting module; The user's sound-groove model that is used for that the vocal print characteristic extracting module is set up carries out similitude with song database song sound-groove model and matees, and returns the tabulation of the song that sound-groove model can be complementary with user's sound-groove model.
Another technical problem that the present invention will solve provides a kind of application process of above-mentioned order programme.
For solving the problems of the technologies described above, the application process of order programme of the present invention comprises the following steps:
(1) the prompting user sends one section voice;
(2) user's voice is recorded;
(3) voice signal of recording is carried out preliminary treatment;
(4) voice signal that obtains in the analytical procedure (3) extracts the user's who comprises in this voice signal vocal print characteristic, and sets up user's sound-groove model;
(5) sound-groove model with song in the user's who obtains in the step (4) sound-groove model and the song database carries out the similitude coupling; Calculate both similarities; And according to the distribution of similarity numerical value; Choose suitable numerical value as threshold value, the quantity of the song that the sound-groove model that retrieves with control can be complementary with user's sound-groove model;
The tabulation of the song that (6) step (5) is retrieved offers user's program request.
Order programme of the present invention and application process thereof can retrieve the song that is fit to this user's performance according to user's vocal print characteristic, offer user's program request, thereby can improve user's singing effect, make the user obtain good singing and experience.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is done further detailed explanation:
Fig. 1 is the module diagram of order programme of the present invention;
Fig. 2 is the application process flow chart of order programme of the present invention.
Embodiment
Understand for technology contents of the present invention, characteristics and effect being had more specifically, combine illustrated execution mode at present, details are as follows:
Vocal print is the sound wave spectrum that carries verbal information that the electricity consumption acoustic instrument shows.Because it is complex physical physical process between human body speech center and the vocal organs that people's language produces; Organ---tongue, tooth, larynx, lung, nasal cavity that health uses when speech; Everyone is widely different aspect size and form; Therefore, any two people's vocal print collection of illustrative plates can be not identical, thereby utilize the characteristic of vocal print collection of illustrative plates can discern the pairing speaker of this vocal print automatically.
At present, the Application on Voiceprint Recognition technology has been a very mature technique, is widely used in fields such as criminal investigation.And along with the technological development of Application on Voiceprint Recognition, the accuracy of Application on Voiceprint Recognition is also increasingly high, and the present invention is exactly by means of the Application on Voiceprint Recognition technology, makes order programme intelligent more, can retrieve to be fit to the song that the user sings, confession user program request.
Order programme based on Application on Voiceprint Recognition of the present invention; At first to collect song; Analyze the audio signal of every first song; Utilize the Application on Voiceprint Recognition technology from audio signal, to extract the vocal print characteristic (actual is this singing songs person's vocal print characteristic) of this song, set up the sound-groove model of song, then with song one by one corresponding stored in a song database.In addition, as shown in Figure 1, order programme of the present invention also includes following modules:
Voice signal processing module 2 is connected with recording module 1, and the voice signal that is used for recording module 1 is recorded to carries out preliminary treatment, for example quantizes, processing such as preemphasis, windowing, filtering;
Vocal print characteristic extracting module 3 is connected with voice signal processing module 2, is used for the analyzing speech signal, and from voice signal, extracts the vocal print characteristic, sets up sound-groove model;
Vocal print characteristic comparing module 4; Be connected with vocal print characteristic extracting module 3; The user's sound-groove model that is used for vocal print characteristic extracting module 3 is set up carries out similitude with the song sound-groove model of song database and matees, and returns the tabulation of the song that sound-groove model can be complementary with user's sound-groove model.
When the user gets into above-mentioned order programme, when preparing to request a song, this order programme is realized it selects song to the user function according to the following step:
(1) the prompting user sends one section voice, and these voice can be one section word or one section song;
(2) when the user sends voice, recording module 1 is recorded user's voice get off;
(3) voice signal of recording in 2 pairs of steps of voice signal processing module (2) carries out preliminary treatment, for example, carries out filtering, removes the noise in this voice signal, or quantize, processing such as preemphasis, windowing;
(4) 3 pairs of voice signals of handling through step (3) of vocal print characteristic extracting module are analyzed, and utilize the Application on Voiceprint Recognition technology to extract the user's who is comprised in this voice signal vocal print characteristic, and set up user's sound-groove model;
(5) vocal print characteristic comparing module 4 is carried out the similitude coupling with user's sound-groove model that obtains in the step (4) and the song sound-groove model in the song database; Promptly calculate both similarities; Then according to the distribution of similarity numerical value; Choose suitable similarity numerical value as threshold value (the adjustment doors limit value can be controlled the number of songs that retrieves); Retrieve the song sound-groove model that is complementary with user's sound-groove model in the song database, and return the tabulation of the pairing song of these song sound-groove models;
(6) list of songs that searches is offered user's program request.
Similitude coupling in the above-mentioned steps (5) can adopt vector quantization model, stochastic model or neural network model.Hidden Markov model (Hidden Markov Model; HMM) be a kind of stochastic model based on transition probability and transmission probability; It regards sound as the random process of being made up of observable symbol sebolic addressing (being the output of sonification system status switch); Since regular when not required, computing time and the memory space of judging identification can be practiced thrift, therefore be widely used in field of speech recognition.Preferred embodiment of the present invention has also selected hidden Markov model to carry out the similitude calculation of Matching; And the number through the sound-groove model that retrieves of adjustment maximum probability (being threshold value) the control song similar with user's sound-groove model; Promptly when the number of songs that retrieves is too much; Heighten most probable value, improve the similitude requirement, make the song that retrieves be more suitable for the user and sing; Otherwise, when the number of songs that retrieves seldom the time, turn down most probable value, to reduce the similitude requirement, retrieve more song and supply the user to select.
After using order programme of the present invention; The song that the user just can select to be fit to own sound condition is sung, can blindly not request tune popular again or oneself like but and be not suitable for own song of singing, like this; Not only can improve the effect that the user sings; Reach the purpose of amusement, and can also make the singer obtain audience's approval, make the user obtain good singing and experience.
Claims (6)
1. the order programme based on Application on Voiceprint Recognition is characterized in that, comprising:
Song database stores song and corresponding song sound-groove model thereof, and this song sound-groove model is set up through the vocal print characteristic of extracting song;
Recording module is used to record user's voice;
Voice signal processing module is connected with recording module, and the voice signal that is used for recording module is recorded to carries out preliminary treatment;
The vocal print characteristic extracting module is connected with voice signal processing module, is used for the analyzing speech signal, and from voice signal, extracts the vocal print characteristic, sets up sound-groove model;
Vocal print characteristic comparing module; Be connected with the vocal print characteristic extracting module; The user's sound-groove model that is used for that the vocal print characteristic extracting module is set up carries out similitude with song database song sound-groove model and matees, and returns the tabulation of the song that sound-groove model can be complementary with user's sound-groove model.
2. order programme as claimed in claim 1 is characterized in that: said recording module is at least one microphone.
3. the application process of the described order programme of claim 1 is characterized in that, comprises the following steps:
(1) the prompting user sends one section voice;
(2) user's voice is recorded;
(3) voice signal of recording is carried out preliminary treatment;
(4) voice signal that obtains in the analytical procedure (3) extracts the user's who comprises in this voice signal vocal print characteristic, and sets up user's sound-groove model;
(5) sound-groove model with song in the user's who obtains in the step (4) sound-groove model and the song database carries out the similitude coupling; Calculate both similarities; And according to the distribution of similarity numerical value; Choose suitable numerical value as threshold value, the quantity of the song that the sound-groove model that retrieves with control can be complementary with user's sound-groove model;
The tabulation of the song that (6) step (5) is retrieved offers user's program request.
4. the application process of order programme as claimed in claim 3 is characterized in that: in the said step (3), the preliminary treatment of voice signal is comprised filtering, remove the noise in the voice signal.
5. method for ordering song as claimed in claim 3 is characterized in that: in the said step (5), adopt vector quantization model, stochastic model or neural network model to carry out the similitude coupling and calculate.
6. method for ordering song as claimed in claim 5 is characterized in that: said stochastic model is a hidden Markov model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102734656A CN102404278A (en) | 2010-09-08 | 2010-09-08 | Song requesting system based on voiceprint recognition and application method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102734656A CN102404278A (en) | 2010-09-08 | 2010-09-08 | Song requesting system based on voiceprint recognition and application method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102404278A true CN102404278A (en) | 2012-04-04 |
Family
ID=45886074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010102734656A Pending CN102404278A (en) | 2010-09-08 | 2010-09-08 | Song requesting system based on voiceprint recognition and application method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102404278A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103035247A (en) * | 2012-12-05 | 2013-04-10 | 北京三星通信技术研究有限公司 | Method and device of operation on audio/video file based on voiceprint information |
| CN103631802A (en) * | 2012-08-24 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Song information searching method, device and corresponding server |
| CN103793641A (en) * | 2014-02-27 | 2014-05-14 | 联想(北京)有限公司 | Information processing method and device, and electronic device |
| CN104268279A (en) * | 2014-10-16 | 2015-01-07 | 魔方天空科技（北京）有限公司 | Query method and device of corpus data |
| CN105677799A (en) * | 2015-12-31 | 2016-06-15 | 宇龙计算机通信科技(深圳)有限公司 | Picture retrieval method and system |
| WO2017028704A1 (en) * | 2015-08-18 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Method and device for providing accompaniment music |
| CN106548792A (en) * | 2015-09-17 | 2017-03-29 | 阿里巴巴集团控股有限公司 | Intelligent sound box device, mobile terminal and music processing method |
| WO2018094952A1 (en) * | 2016-11-22 | 2018-05-31 | 百度在线网络技术（北京）有限公司 | Content recommendation method and apparatus |
| CN108182946A (en) * | 2017-12-25 | 2018-06-19 | 广州势必可赢网络科技有限公司 | Vocal music mode selection method and device based on voiceprint recognition |
| CN109712635A (en) * | 2018-12-28 | 2019-05-03 | 深圳创维－Rgb电子有限公司 | A kind of voice data processing method, intelligent terminal and storage medium |
| CN110867189A (en) * | 2018-08-28 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Login method and device |
| CN111199729A (en) * | 2018-11-19 | 2020-05-26 | 阿里巴巴集团控股有限公司 | Voiceprint recognition method and device |
| CN112489607A (en) * | 2019-08-22 | 2021-03-12 | 北京峰趣互联网信息服务有限公司 | Method and device for recording songs, electronic equipment and readable storage medium |
| WO2021127975A1 (en) * | 2019-12-24 | 2021-07-01 | 广州国音智能科技有限公司 | Voiceprint detection method, apparatus and device for sound acquisition object |
| CN113366567A (en) * | 2021-05-08 | 2021-09-07 | 腾讯音乐娱乐科技（深圳）有限公司 | Voiceprint identification method, singer authentication method, electronic equipment and storage medium |
| TWI745338B (en) * | 2017-01-19 | 2021-11-11 | 香港商阿里巴巴集團服務有限公司 | Method and device for providing accompaniment music |
| US11514885B2 (en) | 2016-11-21 | 2022-11-29 | Microsoft Technology Licensing, Llc | Automatic dubbing method and apparatus |
-
2010
- 2010-09-08 CN CN2010102734656A patent/CN102404278A/en active Pending
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103631802A (en) * | 2012-08-24 | 2014-03-12 | 腾讯科技（深圳）有限公司 | Song information searching method, device and corresponding server |
| CN103631802B (en) * | 2012-08-24 | 2015-05-20 | 腾讯科技（深圳）有限公司 | Song information searching method, device and corresponding server |
| US9704485B2 (en) | 2012-08-24 | 2017-07-11 | Tencent Technology (Shenzhen) Company Limited | Multimedia information retrieval method and electronic device |
| CN103035247B (en) * | 2012-12-05 | 2017-07-07 | 北京三星通信技术研究有限公司 | Based on the method and device that voiceprint is operated to audio/video file |
| CN103035247A (en) * | 2012-12-05 | 2013-04-10 | 北京三星通信技术研究有限公司 | Method and device of operation on audio/video file based on voiceprint information |
| CN107274916A (en) * | 2012-12-05 | 2017-10-20 | 北京三星通信技术研究有限公司 | The method and device operated based on voiceprint to audio/video file |
| CN103793641A (en) * | 2014-02-27 | 2014-05-14 | 联想(北京)有限公司 | Information processing method and device, and electronic device |
| CN103793641B (en) * | 2014-02-27 | 2021-07-16 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
| CN104268279B (en) * | 2014-10-16 | 2018-04-20 | 魔方天空科技（北京）有限公司 | The querying method and device of corpus data |
| CN104268279A (en) * | 2014-10-16 | 2015-01-07 | 魔方天空科技（北京）有限公司 | Query method and device of corpus data |
| CN106469557A (en) * | 2015-08-18 | 2017-03-01 | 阿里巴巴集团控股有限公司 | The offer method and apparatus of accompaniment music |
| WO2017028704A1 (en) * | 2015-08-18 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Method and device for providing accompaniment music |
| CN106469557B (en) * | 2015-08-18 | 2020-02-18 | 阿里巴巴集团控股有限公司 | Method and device for providing accompaniment music |
| CN106548792A (en) * | 2015-09-17 | 2017-03-29 | 阿里巴巴集团控股有限公司 | Intelligent sound box device, mobile terminal and music processing method |
| CN105677799A (en) * | 2015-12-31 | 2016-06-15 | 宇龙计算机通信科技(深圳)有限公司 | Picture retrieval method and system |
| US11514885B2 (en) | 2016-11-21 | 2022-11-29 | Microsoft Technology Licensing, Llc | Automatic dubbing method and apparatus |
| WO2018094952A1 (en) * | 2016-11-22 | 2018-05-31 | 百度在线网络技术（北京）有限公司 | Content recommendation method and apparatus |
| TWI745338B (en) * | 2017-01-19 | 2021-11-11 | 香港商阿里巴巴集團服務有限公司 | Method and device for providing accompaniment music |
| CN108182946A (en) * | 2017-12-25 | 2018-06-19 | 广州势必可赢网络科技有限公司 | Vocal music mode selection method and device based on voiceprint recognition |
| CN108182946B (en) * | 2017-12-25 | 2021-04-13 | 广州势必可赢网络科技有限公司 | A method and device for selecting vocal music mode based on voiceprint recognition |
| CN110867189A (en) * | 2018-08-28 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Login method and device |
| CN111199729A (en) * | 2018-11-19 | 2020-05-26 | 阿里巴巴集团控股有限公司 | Voiceprint recognition method and device |
| CN111199729B (en) * | 2018-11-19 | 2023-09-26 | 阿里巴巴集团控股有限公司 | Voiceprint recognition method and voiceprint recognition device |
| CN109712635B (en) * | 2018-12-28 | 2020-10-09 | 深圳创维－Rgb电子有限公司 | Sound data processing method, intelligent terminal and storage medium |
| CN109712635A (en) * | 2018-12-28 | 2019-05-03 | 深圳创维－Rgb电子有限公司 | A kind of voice data processing method, intelligent terminal and storage medium |
| CN112489607A (en) * | 2019-08-22 | 2021-03-12 | 北京峰趣互联网信息服务有限公司 | Method and device for recording songs, electronic equipment and readable storage medium |
| WO2021127975A1 (en) * | 2019-12-24 | 2021-07-01 | 广州国音智能科技有限公司 | Voiceprint detection method, apparatus and device for sound acquisition object |
| CN113366567A (en) * | 2021-05-08 | 2021-09-07 | 腾讯音乐娱乐科技（深圳）有限公司 | Voiceprint identification method, singer authentication method, electronic equipment and storage medium |
| CN113366567B (en) * | 2021-05-08 | 2024-06-04 | 腾讯音乐娱乐科技（深圳）有限公司 | Voiceprint recognition method, singer authentication method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102404278A (en) | Song requesting system based on voiceprint recognition and application method thereof | |
| CN108320733B (en) | Voice data processing method and device, storage medium and electronic equipment | |
| US11475897B2 (en) | Method and apparatus for response using voice matching user category | |
| CN102723078B (en) | Emotion speech recognition method based on natural language comprehension | |
| CN105334743B (en) | A kind of intelligent home furnishing control method and its system based on emotion recognition | |
| CN103680497B (en) | Speech recognition system and method based on video | |
| CN108874895B (en) | Interactive information pushing method and device, computer equipment and storage medium | |
| CN108538293B (en) | Voice awakening method and device and intelligent device | |
| CN107623614A (en) | Method and apparatus for pushed information | |
| CN112562681B (en) | Speech recognition method and apparatus, and storage medium | |
| WO2020155490A1 (en) | Method and apparatus for managing music based on speech analysis, and computer device | |
| CN109074806A (en) | Distributed audio output is controlled to realize voice output | |
| CN106228988A (en) | A kind of habits information matching process based on voiceprint and device | |
| CN104036774A (en) | Method and system for recognizing Tibetan dialects | |
| CN107767879A (en) | Audio conversion method and device based on tone color | |
| CN101794576A (en) | Dirty word detection aid and using method thereof | |
| CN107293300A (en) | Audio recognition method and device, computer installation and readable storage medium storing program for executing | |
| CN109346057A (en) | A kind of speech processing system of intelligence toy for children | |
| JP6915637B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN112420063A (en) | A kind of speech enhancement method and apparatus | |
| CN115171731A (en) | Emotion category determination method, device and equipment and readable storage medium | |
| CN114999472A (en) | An air conditioner control method, device and an air conditioner | |
| CN114817514A (en) | Method and device for determining reply audio, storage medium and electronic device | |
| CN114283820A (en) | Interaction method, electronic device and storage medium for multi-role voice | |
| CN114664303A (en) | Continuous voice instruction rapid recognition control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120404 |