CN109801619A - A kind of across language voice identification method for transformation of intelligence - Google Patents
A kind of across language voice identification method for transformation of intelligence Download PDFInfo
- Publication number
- CN109801619A CN109801619A CN201910112299.2A CN201910112299A CN109801619A CN 109801619 A CN109801619 A CN 109801619A CN 201910112299 A CN201910112299 A CN 201910112299A CN 109801619 A CN109801619 A CN 109801619A
- Authority
- CN
- China
- Prior art keywords
- voice
- speech recognition
- module
- speech
- identification
- 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
Landscapes
- Machine Translation (AREA)
Abstract
The invention discloses a kind of across the language voice identification method for transformation of intelligence, and across the language voice identification method for transformation of the intelligence is the following steps are included: S1: voice is collected, S2: speech recognition, S3: voice conversion, S4: speech recognition judgement.The present invention is ingenious in design, it can be realized and identification conversion is carried out to voice, and method of the invention is convenient to voice progress denoising, to guarantee the sound quality of voice, the people of different zones are facilitated to carry out communication exchange, it is convenient that voice to be identified is collected by voice collection module, to guarantee to provide precondition for voice conversion；Pass through speech recognition module one and speech recognition module two, speech recognition module one is facilitated first to carry out identification judgement to voice, then the judgement after converting to voice is carried out by speech recognition module two again belong to that voice family of languages, it is convenient that Classification of Speech is stored, also facilitate other equipment to access speech database.
Description
Technical field
The present invention relates to voice transformation technology field more particularly to a kind of across the language voice identification method for transformation of intelligence.
Background technique
Voice refers to that the mankind are issued by vocal organs, with definite meaning, purpose is for carrying out social friendship
The sound on border.In the shape of language, sound, adopted three essential attributes, voice is the first attribute, and the language of the mankind is with language first
The form of sound is formed, and has letterless language in the world, but not without the language of voice, voice plays conclusive branch in language
Support effect.
Voice, i.e. the substance shell of language, are the external forms of language, are the most directly symbols of the thinking activities of recorder
Number system.It is the sound with certain social effect of the vocal organs sending of people.The physical basis of voice mainly have pitch,
Loudness of a sound, the duration of a sound, tone color, this is also four elements for constituting voice.
Existing speech category is not relatively more, and the exchange between people is then that communication exchange is carried out by voice, but not
It is then to need voice to carry out to be converted into the mutually known voice of people with region people, to guarantee that people carry out communication exchange,
When the people of different zones exchange, need to convert language, but present voice method for transformation, it cannot be to language
The family of languages belonging to sound differentiated, therefore is inconvenient to store or inconvenient other equipment access speech database, existing
Voice method for transformation, cannot identify and voice is pre-processed, therefore just will affect the sound quality of voice, so influence user
Voice is understood, in consideration of it, the present invention provides a kind of across language voice identification method for transformation of intelligence.
Summary of the invention
The purpose of the present invention is to solve cannot differentiate in the prior art to the family of languages belonging to voice, therefore not side
Just storage or inconvenient other equipment access speech database, and existing voice method for transformation cannot be identified to voice
A kind of intelligence for being pre-processed, therefore just will affect the sound quality of voice, and then influenced the disadvantages of user understands voice, and propose
Across the language voice identification method for transformation of energyization.
To achieve the goals above, present invention employs following technical solutions:
A kind of across language voice identification method for transformation of intelligence, across the language voice identification method for transformation of the intelligence includes following step
It is rapid:
S1: voice is collected: the voice data of conversion to be identified is obtained by voice collection module；
S2: the voice data of collection first speech recognition: is carried out identification comparison by speech recognition module one；
S3: after the voice data identification comparison in S2, conversion classification voice conversion: is carried out to voice by voice conversion module；
S4: speech recognition judgement: the voice after converting in S3 carries out identification judgement by speech recognition module two, and speech recognition is looked for
Data are then stored in speech database after to the corresponding voice family of languages, otherwise voice then enter in S3 converted again with
And identification.
Preferably, the voice collection module includes speech preprocessing module, and speech preprocessing module is used for voice
Denoising.
It preferably, include Speech comparison module, voice pair in the speech recognition module one and speech recognition module two
Than module for carrying out identification judgement to voice data or the voice family of languages.
Preferably, the speech database is used to store the data of classification, wherein speech recognition module one and speech recognition
Module two is compared with the voice data in speech database respectively, and speech recognition module one is for comparing identification voice data
Data in library, speech recognition module two is for carrying out identification judgement to the voice family of languages.
Across the language voice identification method for transformation of a kind of intelligence proposed by the present invention, beneficial effect are: present invention design
It is ingenious, it can be realized and identification conversion is carried out to voice, and method of the invention is convenient to voice progress denoising, to guarantee language
The sound quality of sound facilitates the people of different zones to carry out communication exchange, by voice collection module, it is convenient to voice to be identified into
Row is collected, to guarantee to provide precondition for voice conversion.
By speech recognition module one and speech recognition module two, speech recognition module one is facilitated first to identify to voice
Then judgement is carried out the judgement after converting to voice by speech recognition module two again and belongs to that voice family of languages, convenient to language
Sound classified storage also facilitates other equipment to access speech database.
Voice collection module first collects voice to be identified, and voice carries out at denoising voice by speech preprocessing module
Reason, the voice after denoising compares judgement by the data in speech recognition module one and speech database, if voice number
There is no corresponding voice data according to the data in library, then voice enters voice conversion module and converted, and otherwise voice is then
It being stored in speech database, the voice after conversion is compared identification by speech recognition module two by voice conversion module,
If the voice data after conversion meets the family of languages of voice data library standard, data are stored in speech database, otherwise language
Sound then passes through voice conversion module and is converted again.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
Referring to Fig.1, across the language voice identification method for transformation of a kind of intelligence, across the language voice identification conversion side of the intelligence
Method the following steps are included:
S1: voice is collected: the voice data of conversion to be identified is obtained by voice collection module, voice collection module includes voice
Preprocessing module, speech preprocessing module is for the denoising to voice；
S2: the voice data of collection first speech recognition: is carried out identification comparison by speech recognition module one；
S3: after the voice data identification comparison in S2, conversion classification voice conversion: is carried out to voice by voice conversion module；
S4: speech recognition judgement: the voice after converting in S3 carries out identification judgement by speech recognition module two, and speech recognition is looked for
Data are then stored in speech database after to the corresponding voice family of languages, otherwise voice then enter in S3 converted again with
And identification.
In speech recognition module one and speech recognition module two include Speech comparison module, Speech comparison module for pair
Voice data or the voice family of languages carry out identification judgement, and speech database is used to store the data of classification, wherein speech recognition mould
Block one and speech recognition module two are compared with the voice data in speech database respectively, speech recognition module one for pair
Than the data in identification speech database, speech recognition module two is known for carrying out identification judgement to the voice family of languages by voice
Other module one and speech recognition module two, facilitate speech recognition module one first to carry out identification judgement to voice, then pass through language again
Sound identification module two carries out the judgement after converting to voice and belongs to that voice family of languages, convenient to store to Classification of Speech, also facilitates
Other equipment access speech database.
The present invention is ingenious in design, can be realized and carries out identification conversion to voice, and method of the invention it is convenient to voice into
Row denoising facilitates the people of different zones to carry out communication exchange to guarantee the sound quality of voice, by voice collection module,
It is convenient that voice to be identified is collected, to guarantee to provide precondition for voice conversion.
Working principle: voice collection module first collects voice to be identified, and voice is by speech preprocessing module to voice
Denoising is carried out, the voice after denoising compares judgement by the data in speech recognition module one and speech database,
If the data in speech database do not have corresponding voice data, voice enters voice conversion module and is converted,
Otherwise voice is then stored in speech database, and voice conversion module carries out the voice after conversion by speech recognition module two
Comparison identification, if the voice data after conversion meets the family of languages of voice data library standard, data are stored in speech database
Interior, otherwise voice then passes through voice conversion module and is converted again.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (4)
1. a kind of across language voice identification method for transformation of intelligence, which is characterized in that across the language voice identification conversion of the intelligence
Method the following steps are included:
S1: voice is collected: the voice data of conversion to be identified is obtained by voice collection module；
S2: the voice data of collection first speech recognition: is carried out identification comparison by speech recognition module one；
S3: after the voice data identification comparison in S2, conversion classification voice conversion: is carried out to voice by voice conversion module；
S4: speech recognition judgement: the voice after converting in S3 carries out identification judgement by speech recognition module two, and speech recognition is looked for
Data are then stored in speech database after to the corresponding voice family of languages, otherwise voice then enter in S3 converted again with
And identification.
2. across the language voice identification method for transformation of a kind of intelligence according to claim 1, it is characterised in that: the voice
Collection module includes speech preprocessing module, and speech preprocessing module is for the denoising to voice.
3. across the language voice identification method for transformation of a kind of intelligence according to claim 1, it is characterised in that: the voice
Include Speech comparison module in identification module one and speech recognition module two, Speech comparison module be used for voice data or
The voice family of languages carries out identification judgement.
4. across the language voice identification method for transformation of a kind of intelligence according to claim 1, it is characterised in that: the voice
Database is used to store the data of classification, and wherein speech recognition module one and speech recognition module two are respectively and in speech database
Voice data compare, speech recognition module one be used for compare identify speech database in data, speech recognition module
Two for carrying out identification judgement to the voice family of languages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112299.2A CN109801619A (en) | 2019-02-13 | 2019-02-13 | A kind of across language voice identification method for transformation of intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112299.2A CN109801619A (en) | 2019-02-13 | 2019-02-13 | A kind of across language voice identification method for transformation of intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109801619A true CN109801619A (en) | 2019-05-24 |
Family
ID=66562187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910112299.2A Pending CN109801619A (en) | 2019-02-13 | 2019-02-13 | A kind of across language voice identification method for transformation of intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109801619A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| US8374865B1 (en) * | 2012-04-26 | 2013-02-12 | Google Inc. | Sampling training data for an automatic speech recognition system based on a benchmark classification distribution |
| US20160343368A1 (en) * | 2013-01-17 | 2016-11-24 | Speech Morphing Systems, Inc. | Method and apparatus to model and transfer the prosody of tags across languages |
| CN106409285A (en) * | 2016-11-16 | 2017-02-15 | 杭州联络互动信息科技股份有限公司 | Method and apparatus for intelligent terminal device to identify language type according to voice data |
| CN107808659A (en) * | 2017-12-02 | 2018-03-16 | 宫文峰 | Intelligent sound signal type recognition system device |
| CN107945805A (en) * | 2017-12-19 | 2018-04-20 | 程海波 | A kind of intelligent across language voice identification method for transformation |
| CN108648747A (en) * | 2018-03-21 | 2018-10-12 | 清华大学 | Language recognition system |
| CN109065020A (en) * | 2018-07-28 | 2018-12-21 | 重庆柚瓣家科技有限公司 | The identification storehouse matching method and system of multilingual classification |
-
2019
- 2019-02-13 CN CN201910112299.2A patent/CN109801619A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| US8374865B1 (en) * | 2012-04-26 | 2013-02-12 | Google Inc. | Sampling training data for an automatic speech recognition system based on a benchmark classification distribution |
| US20160343368A1 (en) * | 2013-01-17 | 2016-11-24 | Speech Morphing Systems, Inc. | Method and apparatus to model and transfer the prosody of tags across languages |
| CN106409285A (en) * | 2016-11-16 | 2017-02-15 | 杭州联络互动信息科技股份有限公司 | Method and apparatus for intelligent terminal device to identify language type according to voice data |
| CN107808659A (en) * | 2017-12-02 | 2018-03-16 | 宫文峰 | Intelligent sound signal type recognition system device |
| CN107945805A (en) * | 2017-12-19 | 2018-04-20 | 程海波 | A kind of intelligent across language voice identification method for transformation |
| CN108648747A (en) * | 2018-03-21 | 2018-10-12 | 清华大学 | Language recognition system |
| CN109065020A (en) * | 2018-07-28 | 2018-12-21 | 重庆柚瓣家科技有限公司 | The identification storehouse matching method and system of multilingual classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108877801A (en) | More wheel dialog semantics based on multi-modal Emotion identification system understand subsystem | |
| CN108899050A (en) | Speech signal analysis subsystem based on multi-modal Emotion identification system | |
| CN108805087A (en) | Semantic temporal fusion association based on multi-modal Emotion identification system judges subsystem | |
| CN106357942A (en) | Intelligent response method and system based on context dialogue semantic recognition | |
| CN110459204A (en) | Audio recognition method, device, storage medium and electronic equipment | |
| CN107818785A (en) | A kind of method and terminal device that information is extracted from multimedia file | |
| CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
| CN106294774A (en) | User individual data processing method based on dialogue service and device | |
| CN105427855A (en) | Voice broadcast system and voice broadcast method of intelligent software | |
| CN109344240A (en) | A kind of data processing method, server and electronic equipment | |
| CN106653019A (en) | Man-machine conversation control method and system based on user registration information | |
| CN106709804A (en) | Interactive wealth planning consulting robot system | |
| CN111723239A (en) | Multi-mode-based video annotation method | |
| CN110347811A (en) | A kind of professional knowledge question and answer robot system based on artificial intelligence | |
| CN105845143A (en) | Speaker confirmation method and speaker confirmation system based on support vector machine | |
| CN105957517A (en) | Voice data structured conversion method and system based on open source API | |
| CN113569924B (en) | Emotion identification classification method based on support vector machine multi-core cooperation | |
| CN110378190A (en) | Video content detection system and detection method based on topic identification | |
| CN114169364A (en) | Electroencephalogram emotion recognition method based on space-time diagram model | |
| Zhang et al. | Research on spectrum sensing system based on composite neural network | |
| CN109243458A (en) | A kind of speech recognition system for intelligent robot | |
| CN109801619A (en) | A kind of across language voice identification method for transformation of intelligence | |
| CN115861670A (en) | Training method of feature extraction model and data processing method and device | |
| CN108717851A (en) | A kind of audio recognition method and device | |
| CN115145402A (en) | Intelligent toy system with network interaction function and control method |
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: 20190524 |