CN111261171A - Method and system for voiceprint verification of customizable text - Google Patents
Method and system for voiceprint verification of customizable text Download PDFInfo
- Publication number
- CN111261171A CN111261171A CN202010055493.4A CN202010055493A CN111261171A CN 111261171 A CN111261171 A CN 111261171A CN 202010055493 A CN202010055493 A CN 202010055493A CN 111261171 A CN111261171 A CN 111261171A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- user
- text
- content
- verification
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000002452 interceptive effect Effects 0.000 claims abstract description 7
- 230000008901 benefit Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 241000207961 Sesamum Species 0.000 description 1
- 235000003434 Sesamum indicum Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
Abstract
The invention discloses a voiceprint verification method of a customizable text, which comprises the following steps: s1, displaying the content of the customized text on the interactive interface to prompt the user to read aloud, wherein the customized text is the user-defined content; s2, comparing and analyzing the collected voiceprint in the reading audio with the voiceprint model in the database; and S3, judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database. The invention not only improves the user experience, but also meets the requirement of the user for personalized customization; in addition, the product diversity is improved, and the product popularization is facilitated.
Description
Technical Field
The invention relates to the technical field of voiceprint recognition, in particular to a voiceprint verification method and a voiceprint verification system for customizable texts.
Background
With the advent of the artificial intelligence era, more and more fields are beginning to use artificial intelligence to assist offices to improve productivity. Voiceprint recognition is an indispensable part of the field of artificial intelligence. The application range of the voiceprint recognition in the bank is very wide, and the voiceprint recognition can be applied to a call center to be used as the identity verification of a user and to build a voiceprint blacklist. In fact, fixed text recognition is a key part in voiceprint recognition. At present, fixed text recognition can only fix a word or a sentence for voice recognition. Similar to the existing awakening words such as "love classmates" in the market, the wrong utterance will cause the verification failure. However, such techniques can result in a user experience that is too boring to provide personalized customization. When the users are identified with fixed text, all users must use keywords set by the service provider. Such as words or sentences like 'love classmates', 'opening the door with sesame', etc. When the voiceprint recognition system receives the user voice, the voiceprint and the content are judged at the same time. The voiceprint recognition system will pass the user if and only if both pass at the same time.
Therefore, the current fixed text recognition technology unintentionally kills the right of user selection, and cannot provide personalized customization requirements for users. Thereby reducing the user experience of using the product.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for verifying the voiceprint of the customizable text aiming at the defects of the prior art, so that the personalized customization requirements of users can be better met, and the use experience of products is further improved.
To achieve the above object, the present invention provides a method for voiceprint verification of customizable text, the method comprising:
s1, displaying the content of the customized text on the interactive interface to prompt the user to read aloud, wherein the customized text is the user-defined content;
s2, comparing and analyzing the collected voiceprint in the reading audio with the voiceprint model in the database;
and S3, judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
Preferably, the user-defined content is a word or a sentence designed by the user according to needs.
Preferably, the voiceprint model establishes a connection with corresponding user-defined content when stored in the database.
Preferably, the voiceprint model is a voiceprint model established for the user by extracting voice voiceprint features of the user.
To achieve the above object, the present invention further provides a system for voiceprint verification of customizable text, the system comprising:
the prompting unit is used for prompting the user to read the customized text by displaying the content of the customized text on the interactive interface, wherein the customized text is the user-defined content;
the comparison unit is used for comparing and analyzing the collected voiceprints in the reading audio with the voiceprint models in the database;
and the verification unit is used for judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
Preferably, the user-defined content is a word or a sentence designed by the user according to needs.
Preferably, the voiceprint model establishes a connection with corresponding user-defined content when stored in the database.
Preferably, the voiceprint model is a voiceprint model established for the user by extracting voice voiceprint features of the user.
According to the scheme, the personalized requirements of the user can be met, and when the user enters the database for the first time, the user can input words or sentences which the user wants to customize on the user interaction interface. After the user inputs, the user recites the content according to the input content. After the voiceprint recognition system receives the user's speech, content recognition is performed. It is determined whether the user recited content is user input content. And if the two are consistent, the voiceprint is put in a storage, and the statement is recorded. During the use stage of the user, the system presents the recorded sentences on the user interaction interface to prompt the user. When the user uses the voiceprint to carry out verification, the voiceprint recognition system can carry out content recognition and voiceprint recognition at the same time, and when the two types of voiceprint recognition and voiceprint recognition pass, the verification is passed. Therefore, the invention has the following advantages:
1. the user experience is improved, and the requirement of the user for personalized customization is met;
2. promote the product diversity, do benefit to the product popularization.
Drawings
Fig. 1 is a flowchart of a method for voiceprint verification of customizable text according to an embodiment of the present invention;
fig. 2 is a block diagram illustrating a structure of a system for voiceprint verification of customizable text according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The present invention will be described in detail with reference to the following examples.
Referring to fig. 1, a flowchart of a method for voiceprint verification of a customizable text is provided according to an embodiment of the present invention. The method comprises the following steps:
s1, displaying the content of the customized text on the interactive interface to prompt the user to read aloud, wherein the customized text is the user-defined content;
s2, comparing and analyzing the collected voiceprint in the reading audio with the voiceprint model in the database;
and S3, judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
Preferably, the user-defined content is a word or a sentence designed by the user according to needs.
Preferably, the voiceprint model establishes a connection with corresponding user-defined content when stored in the database.
Preferably, the voiceprint model is a voiceprint model established for the user by extracting voice voiceprint features of the user.
The scheme solves the problem that the user cannot freely customize the text in the current fixed text recognition. The user personalized experience is ignored in the fixed text recognition as the most critical part for improving the user experience. The reason why the fixed text is required for the voiceprint recognition is that the recognition accuracy is not high in the state of the phrase-voice free text. The fixed text fixes the content of the voice, thereby improving the recognition rate. The improvement of the recognition rate mainly depends on that the content spoken by the user when the user is in storage in the voiceprint modeling is consistent with all the content used for verifying the identity of the user later. Therefore, the voiceprint recognition system does not need to remove semantic information in the audio, and voiceprint feature extraction is directly carried out, so that the recognition accuracy is improved. The scheme maintains the accuracy of phrase voice and voice print recognition and meets the personalized requirements of users.
In addition, the present invention further provides a system for voiceprint verification of customizable text, which is shown in fig. 2 and is a block diagram of a structure of the system for voiceprint verification of customizable text provided in an embodiment of the present invention.
The system comprises:
the prompting unit is used for prompting the user to read the customized text by displaying the content of the customized text on the interactive interface, wherein the customized text is the user-defined content;
the comparison unit is used for comparing and analyzing the collected voiceprints in the reading audio with the voiceprint models in the database;
and the verification unit is used for judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
Preferably, the user-defined content is a word or a sentence designed by the user according to needs.
Preferably, the voiceprint model establishes a connection with corresponding user-defined content when stored in the database.
Preferably, the voiceprint model is a voiceprint model established for the user by extracting voice voiceprint features of the user.
In the stage of the user voiceprint modeling and warehousing, the user sets words or sentences according to the requirement of the user and recites the contents of the words or the sentences. After the voiceprint recognition system receives the user's audio, content recognition is performed first, and the recognized content corresponds to the text entered by the user. If the text is consistent with the recognized content, feature extraction (modeling) is carried out on the section of audio and the section of audio is put in storage, and the text is recorded and is connected with the corresponding voiceprint model.
When the user verifies the voiceprint using the voiceprint recognition system, the voiceprint recognition system will display the text entered when the user modeled the voiceprint on the user interaction interface as a prompt. The user can recite the personalized and customized text at the moment. When the voiceprint recognition system receives the user audio, content recognition and voiceprint recognition are performed simultaneously. When the two pass through at the same time, the voiceprint recognition system can judge that the user is the user himself.
The invention not only retains the advantage that the fixed text improves the recognition accuracy of the voiceprint recognition system, but also meets the requirement that the user customizes own text in a personalized way. The invention can obviously improve the product experience of the user and meet the individual requirements of the user. Meanwhile, the interestingness is generated, and a user can customize interesting sentences according to individual imagination, so that the propaganda effect is played for the popularization of the product on the premise.
The embodiments in the above embodiments can be further combined or replaced, and the embodiments are only used for describing the preferred embodiments of the present invention, and do not limit the concept and scope of the present invention, and various changes and modifications made to the technical solution of the present invention by those skilled in the art without departing from the design idea of the present invention belong to the protection scope of the present invention.
Claims (8)
1. A method for voiceprint verification of customizable text, said method comprising:
s1, displaying the content of the customized text on the interactive interface to prompt the user to read aloud, wherein the customized text is the user-defined content;
s2, comparing and analyzing the collected voiceprint in the reading audio with the voiceprint model in the database;
and S3, judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
2. The method for voiceprint verification of customizable text according to claim 1, wherein the user-defined content is words or sentences designed by a user according to needs.
3. A method for voiceprint verification of customizable text according to any one of claims 1 or 2, characterized in that said voiceprint model is associated with corresponding user-defined content when stored in a database.
4. The method of claim 1, wherein the voiceprint model is a voiceprint model created for the user by extracting voice voiceprint features of the user.
5. A system for voiceprint verification of customizable text, said system comprising:
the prompting unit is used for prompting the user to read the customized text by displaying the content of the customized text on the interactive interface, wherein the customized text is the user-defined content;
the comparison unit is used for comparing and analyzing the collected voiceprints in the reading audio with the voiceprint models in the database;
and the verification unit is used for judging that the verification is passed when the text content is correct and the collected voiceprint is consistent with the voiceprint model in the database.
6. The system of claim 5, wherein the user-defined content is words or sentences designed by the user according to the needs.
7. A system for voiceprint verification of customizable text according to any one of claims 5 or 6, wherein said voiceprint model is associated with corresponding user-defined content when stored in a database.
8. A system for voiceprint verification of customizable text according to claim 5, wherein said voiceprint model is a voiceprint model built for a user by extracting voiceprint features of his voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010055493.4A CN111261171A (en) | 2020-01-17 | 2020-01-17 | Method and system for voiceprint verification of customizable text |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010055493.4A CN111261171A (en) | 2020-01-17 | 2020-01-17 | Method and system for voiceprint verification of customizable text |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111261171A true CN111261171A (en) | 2020-06-09 |
Family
ID=70947134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010055493.4A Pending CN111261171A (en) | 2020-01-17 | 2020-01-17 | Method and system for voiceprint verification of customizable text |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111261171A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646646A (en) * | 2013-11-27 | 2014-03-19 | 联想(北京)有限公司 | Voice control method and electronic device |
| CN103685185A (en) * | 2012-09-14 | 2014-03-26 | 上海掌门科技有限公司 | Mobile equipment voiceprint registration and authentication method and system |
| AU2013315343A1 (en) * | 2012-09-11 | 2015-04-30 | Auraya Pty Ltd | Voice authentication system and method |
| CN105575395A (en) * | 2014-10-14 | 2016-05-11 | 中兴通讯股份有限公司 | Voice wake-up method and apparatus, terminal, and processing method thereof |
| CN108735209A (en) * | 2018-04-28 | 2018-11-02 | 广东美的制冷设备有限公司 | Wake up word binding method, smart machine and storage medium |
-
2020
- 2020-01-17 CN CN202010055493.4A patent/CN111261171A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2013315343A1 (en) * | 2012-09-11 | 2015-04-30 | Auraya Pty Ltd | Voice authentication system and method |
| CN103685185A (en) * | 2012-09-14 | 2014-03-26 | 上海掌门科技有限公司 | Mobile equipment voiceprint registration and authentication method and system |
| CN103646646A (en) * | 2013-11-27 | 2014-03-19 | 联想(北京)有限公司 | Voice control method and electronic device |
| CN105575395A (en) * | 2014-10-14 | 2016-05-11 | 中兴通讯股份有限公司 | Voice wake-up method and apparatus, terminal, and processing method thereof |
| CN108735209A (en) * | 2018-04-28 | 2018-11-02 | 广东美的制冷设备有限公司 | Wake up word binding method, smart machine and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6394709B2 (en) | SPEAKER IDENTIFYING DEVICE AND FEATURE REGISTRATION METHOD FOR REGISTERED SPEECH | |
| Segal | Narrative comprehension and the role of deictic shift theory | |
| EP2109097B1 (en) | A method for personalization of a service | |
| Yankelovich | How do users know what to say? | |
| US9070363B2 (en) | Speech translation with back-channeling cues | |
| US7716050B2 (en) | Multilingual speech recognition | |
| CN110689877A (en) | Voice end point detection method and device | |
| US20070055520A1 (en) | Incorporation of speech engine training into interactive user tutorial | |
| CN110517668B (en) | Chinese and English mixed speech recognition system and method | |
| Karat et al. | Conversational interface technologies | |
| Alghamdi et al. | Saudi accented Arabic voice bank | |
| US20150254238A1 (en) | System and Methods for Maintaining Speech-To-Speech Translation in the Field | |
| CN106910499A (en) | The control method and device of application program | |
| Fellbaum et al. | Principles of electronic speech processing with applications for people with disabilities | |
| Shahin | Studying and enhancing talking condition recognition in stressful and emotional talking environments based on HMMs, CHMM2s and SPHMMs | |
| CN109102807A (en) | Personalized speech database creation system, speech recognition control system and terminal | |
| CN112309406A (en) | Voiceprint registration method, voiceprint registration device and computer-readable storage medium | |
| Deka et al. | Speech corpora of under resourced languages of north-east india | |
| CN111261171A (en) | Method and system for voiceprint verification of customizable text | |
| Minker et al. | Spoken dialogue systems technology and design | |
| Gilbert et al. | Intelligent virtual agents for contact center automation | |
| WO2004034355A2 (en) | System and methods for comparing speech elements | |
| CN109035896A (en) | A kind of Oral Training method and facility for study | |
| CN101304457A (en) | Method and apparatus for implementing automatic spoken language training based on voice telephone | |
| CN108831473A (en) | A kind of audio-frequency processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |
|
| RJ01 | Rejection of invention patent application after publication |