CN110867186A - Personal voice database and non-standard voice translation system, method and terminal - Google Patents
Personal voice database and non-standard voice translation system, method and terminal Download PDFInfo
- Publication number
- CN110867186A CN110867186A CN201810980707.1A CN201810980707A CN110867186A CN 110867186 A CN110867186 A CN 110867186A CN 201810980707 A CN201810980707 A CN 201810980707A CN 110867186 A CN110867186 A CN 110867186A
- Authority
- CN
- China
- Prior art keywords
- voice
- standard
- personal
- database
- matching
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention belongs to the technical field of communication, and particularly relates to a personal voice database and non-standard voice translation system, a method and a terminal; the non-standard voice translation system comprises a personal voice database, a conversion module and a standard voice database, wherein the conversion module is used for mutually converting voice information in the personal voice database and the standard voice database, so that people with language disorder can also use the voice function of the electronic equipment, and people who stutter, have unclear pronunciation and can only speak dialects can also input voice; by identifying the voice of the user, correcting the voice and converting the voice of the user, such as the click, the unclear party and the dialect, and then sending the voice, the user can hear standard and smooth voice sentences; moreover, the voice can be converted into characters to be sent out, if the voice is sent by the opposite side, the characters can be displayed by directly converting the voice, so that communication is promoted, and the patients with language disorder can enjoy convenience brought by science and technology.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a personal voice database and non-standard voice translation system, a method and a terminal.
Background
Currently, with the continuous development of speech recognition technology, speech assistants are applied to various electronic devices, and functions such as speech recognition, speech input, and speech conversion are convenient for people's life, but in the prior art, most of languages generally adopted by a speech system are mandarin, english, cantonese, and chinese, and there is no dialect, which is a problem for people with language disorder, for example: people who pronounce inaccurately, stutter, only understand the dialect have brought very big inconvenience, can appear the condition of misidentification even for language barrier personage can't carry out the speech interaction, can't enjoy the facility that scientific and technological progress brought.
Disclosure of Invention
In order to solve the problems that voice interaction cannot be carried out due to inaccurate pronunciation, stuttering, only dialect understanding and the like of the voice-disabled person, the invention provides a personal voice database and non-standard voice translation system, a method and a terminal.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: a personal voice database creation and update method,
s1: creating a personal voice database;
s2: collecting personal voice, and matching the collected voice with characters;
s3: successfully matching the voice and the characters, outputting voice information, and storing the voice information into a personal voice database;
s4: and returning to the step 2 to perform update learning in the use of the personal voice database.
Further, the voice in step S2 includes one or more of tone, pronunciation, and syntax of the person.
Further, in step S2, after the personal voice is collected, the voice is corrected and then the character matching is performed.
Further, the matching of the characters and the voice in the step S3 is unsuccessful, and the step S2 is returned to for voice collection again.
A personal voice database comprises a voice acquisition module, a character matching module, a judgment module and a data storage module;
the voice acquisition module is used for acquiring personal voice information;
the character matching module is used for matching the collected voice information with characters;
the judging module is used for judging whether the matching of the voice and the characters is successful;
and the data storage module is used for storing the output voice information.
The system further comprises a cloud end, and the data storage module is arranged on the cloud end and used for storing and updating the voice information.
A non-standard speech translation system comprises the personal speech database, a conversion module and a standard speech database, wherein the conversion module is used for mutually converting speech information in the personal speech database and the standard speech database.
Further, the standard voice database is arranged at the cloud end.
Further, the conversion module comprises a language conversion unit, and the language conversion unit is used for mutually converting the voice information of different languages.
Furthermore, the conversion module also comprises a text conversion unit, and the text conversion unit is used for converting the voice into text.
A translation method of non-standard voice uses the above translation system of non-standard voice,
s1: inputting a personal voice;
s2: matching the input personal voice with the voice in the personal voice database, and outputting voice information;
s3: substituting the voice information into a standard voice database for conversion to obtain standard voice information;
s4: and outputting the converted corresponding standard voice information.
Further, in step S3, the personal voice is first converted into a text, and the text is brought into the standard voice database, and a voice matching the text is found to obtain a standard voice.
A personalized translation method of standard voice uses the above non-standard voice translation system,
s1: inputting standard voice;
s2: matching the standard voice with the voice information in the standard voice database, and outputting the voice information;
s3: substituting the voice information into a personal voice database for conversion to obtain personal voice information;
s4: and outputting the converted corresponding personal voice information.
Further, in step S3, the personal voice is first converted into words, and the words are brought into the personal voice database, so as to find out the voice matching with the words, and obtain the personal voice.
The sound correction software comprises the non-standard voice sound correction translation system.
A terminal comprises one or more of a mobile phone, a Pad and a PC, and the mobile terminal is provided with the sound correction software.
The invention provides a non-standard speech translation system, which comprises a personal speech database, a conversion module and a standard speech database, wherein the conversion module is used for mutually converting speech information in the personal speech database and the standard speech database, so that people with language disorder can also use the speech function of electronic equipment, and can input speech like people who stutter, have unclear pronunciation and can only speak dialects; by identifying the voice of the user, correcting the voice and converting the voice of the user, such as the click, the unclear party and the dialect, and then sending the voice, the user can hear standard and smooth voice sentences; moreover, the voice can be converted into characters to be sent out, if the voice is sent by the opposite side, the characters can be displayed by directly converting the voice, so that communication is promoted, and the patients with language disorder can enjoy convenience brought by science and technology.
Drawings
FIG. 1 is a schematic diagram of a personal voice database;
FIG. 2 is a flow chart of a method for creating updates to a personal voice database;
FIG. 3 is a schematic structural diagram of a system for correcting and translating non-standard speech;
FIG. 4 is a flow chart of a method for correcting and translating non-standard speech;
FIG. 5 is a flow chart of a method for personalized translation of standard speech.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments.
As shown in fig. 1, a personal voice database 1 includes a voice acquisition module 11, a text matching module 12, a judgment module 13, a data storage module 14, and a cloud 4, where the data storage module 14 is disposed on the cloud 4;
the voice acquisition module 11 is used for acquiring personal voice information; the character matching module 12 is used for matching the collected voice information with characters; the judging module 13 is used for judging whether the matching between the voice and the characters is successful; the data storage module 14 is used for storing the output voice information; the cloud 15 is used for storing and updating voice information.
As shown in fig. 2, a personal voice database creation update method,
s1: creating a personal voice database;
s2: collecting personal voice, correcting voice according to the collected voice, and then performing character matching, wherein the voice comprises personal tone, pronunciation and syntax;
s3: successfully matching the voice and the characters, outputting voice information, and storing the voice information into a personal voice database;
when the matching of the characters and the voice is unsuccessful, returning to the step 2 for carrying out voice collection again;
s4: and returning to the step 2 to perform update learning in the use of the personal voice database.
For example, a stuttered person with unclear pronunciation needs to collect the voice of the individual before using the voice function, then corrects the voice, performs character matching on the voice, and creates a personal voice database, the first time is to collect the tone, the basic pronunciation and the syntax of the individual, then the system automatically learns in the continuous using process of the person with language disorder, then updates the personal voice database and synchronizes with the cloud end, and the more the user, the more the system can accurately express the sentence semantics of the person with language disorder, so that the personal voice database can be used anytime and anywhere, the cloud end is connected in real time, and convenience is brought to the person with language disorder.
As shown in fig. 3, a system for correcting and translating non-standard speech includes the personal speech database 1, a conversion module 2 and a standard speech database 3, where the conversion module 2 is configured to convert speech information in the personal speech database 1 and the standard speech database 2 to each other; the standard voice database 3 is disposed in the cloud 4.
The conversion module comprises a language conversion unit and a character conversion unit, wherein the language conversion unit is used for mutually converting voice information of different languages; the character conversion unit is used for converting the voice into characters.
As shown in fig. 4, a method for sound correction and translation of non-standard speech, using the above-mentioned system for sound correction and translation of non-standard speech,
s1: inputting a personal voice;
s2: matching the input personal voice with the voice in the personal voice database, and outputting voice information;
s3: substituting the voice information into a standard voice database for conversion to obtain standard voice information;
firstly, personal voice is converted into characters, the characters are brought into a standard voice database, voice matched with the characters is found, and standard voice is obtained;
s4: and outputting the converted corresponding standard voice information, including text output or voice output.
As shown in fig. 5, a personalized translation method for standard speech, using the above-mentioned non-standard speech sound correction translation system,
s1: inputting standard voice;
s2: matching the standard voice with the voice information in the standard voice database, and outputting the voice information;
s3: substituting the voice information into a personal voice database for conversion to obtain personal voice information;
firstly, personal voice is converted into characters, the characters are brought into a personal voice database, voice matched with the characters is found, and personal voice is obtained;
s4: and outputting the converted corresponding personal voice information, including text output or voice output.
The speech conversion aspect is mainly to match the personal speech database with the standard speech database, for example, a dialect person needs to match his personal speech database with the general standard speech database of the public, when needing to communicate with a person who does not know the dialect, the personal language needs to be translated into a language which can be heard by the opposite party, and then the translated speech is sent out, and the tone and tone of the speech are completely simulated for a language-handicapped patient, so that the speech is not obtrusive. Or directly converting dialects into characters which can be understood by the other party and sending the characters. Similarly, the other party should communicate with the language-handicapped patient, and the speech received by the language-handicapped patient should be a speech that can be understood by himself or a text that can be understood by himself.
The sound correction software is provided with the sound correction translation system of the non-standard voice, can be installed on a mobile phone, a Pad, a PC and the like, and can be applied to daily communication of a voice-handicapped patient, course education of students with language handicapped patients, communication of service personnel of a nursing home service center and the old, and the like by using the sound correction translation method of the non-standard voice.
The above description is only a preferred embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing on the protection scope of the present invention.
Claims (16)
1. A method for creating and updating a personal voice database, comprising:
s1: creating a personal voice database;
s2: collecting personal voice, and matching the collected voice with characters;
s3: successfully matching the voice and the characters, outputting voice information, and storing the voice information into a personal voice database;
s4: and returning to the step 2 to perform update learning in the use of the personal voice database.
2. The personal voice database creation update method of claim 1, wherein: the voice in step S2 includes one or more of tone, pronunciation, and syntax of the person.
3. The personal voice database creation update method of claim 1, wherein: and step S2, after the personal voice is collected, the voice is corrected and then the character matching is carried out.
4. The personal voice database creation update method of claim 1, wherein: and the matching of the characters and the voice in the step S3 is unsuccessful, and the step 2 is returned to for voice collection again.
5. A personal voice database, characterized by: the system comprises a voice acquisition module, a character matching module, a judgment module and a data storage module;
the voice acquisition module is used for acquiring personal voice information;
the character matching module is used for matching the collected voice information with characters;
the judging module is used for judging whether the matching of the voice and the characters is successful;
and the data storage module is used for storing the output voice information.
6. The personal voice database of claim 5, wherein: the voice information updating system further comprises a cloud end, and the data storage module is arranged on the cloud end and used for storing and updating voice information.
7. A non-standard speech translation system comprising the personal speech database of any of claims 5-6, wherein: the system also comprises a conversion module and a standard voice database, wherein the conversion module is used for mutually converting the voice information in the personal voice database and the standard voice database.
8. The non-standard speech translation system of claim 7, wherein: the standard voice database is arranged at the cloud end.
9. The non-standard speech translation system of claim 7, wherein: the conversion module comprises a language conversion unit, and the language conversion unit is used for mutually converting different voice information.
10. The non-standard speech translation system of claim 7, wherein: the conversion module also comprises a text conversion unit, and the text conversion unit is used for converting the voice into text.
11. A method for translating non-standard speech, characterized by: using the non-standard speech translation system of any of claims 7-10,
s1: inputting a personal voice;
s2: matching the input personal voice with the voice in the personal voice database, and outputting voice information;
s3: substituting the voice information into a standard voice database for conversion to obtain standard voice information;
s4: and outputting the converted corresponding standard voice information.
12. The method of translating non-standard speech according to claim 11, wherein: in the step S3, the personal voice is first converted into words, and the words are brought into the standard voice database, so as to find out the voice matching with the words, and obtain the standard voice.
13. A personalized translation method for standard voice is characterized in that: using the non-standard speech translation system of any of claims 7-10,
s1: inputting standard voice;
s2: matching the standard voice with the voice information in the standard voice database, and outputting the voice information;
s3: substituting the voice information into a personal voice database for conversion to obtain personal voice information;
s4: and outputting the converted corresponding personal voice information.
14. The method for personalized translation of standard speech according to claim 13, characterized in that: in step S3, the standard voice is first converted into text, and the text is brought into the personal voice database to find out the voice matching with the text, and obtain the personal voice.
15. A tone correction software, comprising: the sound correction software comprises a sound correction translation system of the non-standard speech as claimed in any one of claims 7-10.
16. A terminal comprises one or more of a mobile phone, a Pad and a PC, and is characterized in that: the mobile terminal is provided with the sound correction software of claim 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810980707.1A CN110867186A (en) | 2018-08-27 | 2018-08-27 | Personal voice database and non-standard voice translation system, method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810980707.1A CN110867186A (en) | 2018-08-27 | 2018-08-27 | Personal voice database and non-standard voice translation system, method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110867186A true CN110867186A (en) | 2020-03-06 |
Family
ID=69651100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810980707.1A Pending CN110867186A (en) | 2018-08-27 | 2018-08-27 | Personal voice database and non-standard voice translation system, method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110867186A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101295296A (en) * | 2007-04-28 | 2008-10-29 | 舒东 | Simultaneous translator |
| CN102831195A (en) * | 2012-08-03 | 2012-12-19 | 河南省佰腾电子科技有限公司 | Individualized voice collection and semantics determination system and method |
| US20160118050A1 (en) * | 2014-10-24 | 2016-04-28 | Sestek Ses Ve Iletisim Bilgisayar Teknolojileri Sanayi Ticaret Anonim Sirketi | Non-standard speech detection system and method |
| CN106328142A (en) * | 2015-06-15 | 2017-01-11 | 中兴通讯股份有限公司 | Speech translation method and speech translation device for language barrier |
| CN106897275A (en) * | 2017-04-17 | 2017-06-27 | 山东荣安电子科技有限公司 | A kind of dialect real-time translation system |
-
2018
- 2018-08-27 CN CN201810980707.1A patent/CN110867186A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101295296A (en) * | 2007-04-28 | 2008-10-29 | 舒东 | Simultaneous translator |
| CN102831195A (en) * | 2012-08-03 | 2012-12-19 | 河南省佰腾电子科技有限公司 | Individualized voice collection and semantics determination system and method |
| US20160118050A1 (en) * | 2014-10-24 | 2016-04-28 | Sestek Ses Ve Iletisim Bilgisayar Teknolojileri Sanayi Ticaret Anonim Sirketi | Non-standard speech detection system and method |
| CN106328142A (en) * | 2015-06-15 | 2017-01-11 | 中兴通讯股份有限公司 | Speech translation method and speech translation device for language barrier |
| CN106897275A (en) * | 2017-04-17 | 2017-06-27 | 山东荣安电子科技有限公司 | A kind of dialect real-time translation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3323519B2 (en) | Text-to-speech converter | |
| US20100217591A1 (en) | Vowel recognition system and method in speech to text applictions | |
| CN102572372A (en) | Extraction method and device for conference summary | |
| US20090144048A1 (en) | Method and device for instant translation | |
| CN108766441A (en) | A kind of sound control method and device based on offline Application on Voiceprint Recognition and speech recognition | |
| CN102831195B (en) | Personalized speech gathers and semantic certainty annuity and method thereof | |
| Popovici et al. | Professional challenges in computer-assisted speech therapy | |
| CN101287229A (en) | Natural language processing technique and device applying to query by short message service of mobile phone | |
| CN112256827A (en) | Sign language translation method and device, computer equipment and storage medium | |
| CN104361787A (en) | System and method for converting signals | |
| Ramadani et al. | A new technology on translating Indonesian spoken language into Indonesian sign language system. | |
| CN107274886B (en) | Voice recognition method and device | |
| Anuja et al. | Design and development of a frame based MT system for English-to-ISL | |
| CN110867186A (en) | Personal voice database and non-standard voice translation system, method and terminal | |
| CN106897275A (en) | A kind of dialect real-time translation system | |
| JP2018087945A (en) | Language recognition system, language recognition method, and language recognition program | |
| Zhao | Speech-recognition technology in health care and special-needs assistance [Life Sciences] | |
| CN101287228A (en) | Phoneticizing error correcting technique and device applying to query by short message service of mobile phone | |
| KR19990037776A (en) | Auto translation and interpretation apparatus using awareness of speech | |
| CN111009234B (en) | Voice conversion method, device and equipment | |
| KR100747689B1 (en) | Voice-Recognition Word Conversion System | |
| CN109064789A (en) | A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor | |
| CN113257231A (en) | Language sound correcting system method and device | |
| CN112270930A (en) | Method for voice recognition conversion | |
| Phuphatana et al. | Thai Minspeak® system for long-distance facilitating communications involving people with communication disabilities |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |