CN1425980A - Personalized opening computer voice log-in method - Google Patents
Personalized opening computer voice log-in method Download PDFInfo
- Publication number
- CN1425980A CN1425980A CN 03114943 CN03114943A CN1425980A CN 1425980 A CN1425980 A CN 1425980A CN 03114943 CN03114943 CN 03114943 CN 03114943 A CN03114943 A CN 03114943A CN 1425980 A CN1425980 A CN 1425980A
- Authority
- CN
- China
- Prior art keywords
- personalized
- voice
- log
- standard
- comparison standard
- 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 personalized opening computer voice log-in method includes the following steps: starting personalized voice intercourse system; entering the voice matching standard creating state; extracting standard text; reading standard text while the system records synchronously; recording for the second time; starting personalized automatic voice matching standard creating program; waiting for system prompt "voice matching standard created" and back up; inspecting matching effect; judging before continuing or exit. The present invention facilitates voice log-in system design, raises log-in accuracy, reaction speed and matching efficiency and system log-in reaction speed.
Description
Technical field
The present invention relates to a kind of voice input method, relate in particular to a kind of personalized opening computer voice log-in.
Background technology
Computerized speech typing, the most thorny issue are varying of pronouncing of people.The very standard if everybody pronounces, that implements just easier.But people's pronunciation is subjected to all multifactor influences such as environment, dialect, custom, training degree, realize general standardization, the particularly standardization on the computer approval meaning, and that is difficult to accomplish, or even impossible.So attempt to set up that one " public identification comparison standard " realizes fast, to be doomed be hopeless in computerized speech typing accurately.
Summary of the invention
The objective of the invention is to: thoroughly abandon people and in the computerized speech input system, artificially set " identification comparison standard ", force the passive mechanical means that satisfies " machine standard " requirement of user, creatively adopt user's primary sound to make his " identification comparison standard ", (everyone is with regard to the himself with the personalized way of opening different locks with different keys, his pronunciation is " standard "), a most key technical matters---voice are effectively discerned in the settlement computer voice input system, are the practicability of computerized speech input technology, universalness is paved the way.
The present invention realizes by following scheme: may further comprise the steps: the first step: beginning step: open the personalized speech AC system; Second step: enter voice comparison standard and generate state; The 3rd step: extract received text; The 4th step: read aloud received text and carry out synchronization by system; The 5th step: repeating step four, record once more; The 6th step: start personalized speech comparison standard automatically generating program; The 7th step: waiting system prompting: voice comparison standard generates, and backup is also properly preserved; The 8th step: check comparison effect; The 9th step: judge whether to continue; Then repeated for second step as the result for "Yes"; As then carrying out for the tenth step: log off for "No".
The present invention has following characteristics: the design difficulty that 1, has greatly reduced the voice input systems.Because this method has abandoned setting up a subjectivity comparison standard based on masses, and fully based on specific user, quite complicated " a fuzzy comparison " has been become easy " directly comparison ", has greatly simplified system's difficulty.2, typing accuracy and reaction velocity have greatly been improved.Because this method is to generate the comparison standard with the former sound of user, must possess the accurate recognition performance.Open in addition Plasticity Design, along with system constantly is used, system also will be more and more familiar to this user, and recognition capability also will be continually strengthened.Simultaneously, than " subjective criterion comparison " (be system itself set comparison standard), " obfuscation " that need not too complex inevitablely greatly be simplified comparison program and comparison process, thereby greatly improves comparison efficiency, improves the typing reaction velocity of system.3, greatly improve the popularization of system applies.Because this method is to be " standard " with user's self pronunciation, the user is not had must the accurately requirement of (with respect to the standard pronunciation) of pronunciation, obviously can greatly improve the adaptability of system, brings greatly popularizing of voice typing.Even Shi Zi people as long as under others' help, does not set up his comparison standard, can use this system smoothly too.4, can be used as stand-alone product.Because this method is personalized open voice input method, so the comparison standard can be independent of outside the whole input system.That is to say, can make " voice comparison standard generation system " separately, and use as stand-alone product.
Description of drawings
Accompanying drawing is a block diagram of the present invention.
Embodiment
The present invention is described in detail below in conjunction with accompanying drawing.
Personalized opening computer voice log-in of the present invention may further comprise the steps: the first step: the beginning step: open the personalized speech AC system, provide one to have comprehensive representational literal combination by system this moment; Second step: enter voice comparison standard and generate state; The 3rd step: extract received text; The 4th step: read aloud received text and carry out synchronization by system; The 5th step: repeating step four, record once more; The 6th step: start personalized speech comparison standard automatically generating program; The 7th step: waiting system prompting: voice comparison standard generates, and backup is also properly preserved; The 8th step: check comparison effect; The 9th step: judge whether to continue; Then repeated for second step as the result for "Yes"; As then carrying out for the tenth step: log off for "No".
In order to realize better comparing effect, and can satisfy that user's voice change and the needs of language development, this comparison standard is open, and has good plasticity and expansion.Promptly by the such function of software setting: 1. typing new term at any time, foreign word etc., realize the renewal at any time of comparison standard; 2. " mistake " found in each check and correction is stored in the comparison standard, and abundant automatically or correction comparison standard.
System offers the user, and to set up oneself the literal combination (promptly aforementioned " received text ") of comparison standard very important.It must possess comprehensive representativeness.Can arrange multiple choices: 1. common wordss.The common wordss series arrangement or organize writtenly, read aloud for the user; 2. complete vocabulary.Vocabulary commonly used, that be of little use is offered the user as far as possible; 3. common wordss and non-common vocabulary combination.Allow the user read aloud common wordss earlier, read aloud non-common vocabulary again, and common wordss are placed on preferential aligned sequences.4. independent phonetic word (only for Chinese).Each in unison, simple or compound vowel of a Chinese syllable makes up and one of the word select of same tone offers the user.Or the like.
Claims (2)
1, a kind of personalized opening computer voice log-in is characterized in that: may further comprise the steps: the first step: beginning step: open the personalized speech AC system; Second step: enter voice comparison standard and generate state; The 3rd step: extract received text; The 4th step: read aloud received text and carry out synchronization by system; The 5th step: repeating step four, record once more; The 6th step: start personalized speech comparison standard automatically generating program; The 7th step: backup is also properly preserved; The 8th step: check comparison effect; The 9th step: judge whether to continue; Then repeated for second step as the result for "Yes"; As then carrying out for the tenth step: log off for "No".
2, personalized opening computer voice log-in according to claim 1 is characterized in that: typing new term at any time, foreign word etc., realize the renewal at any time of comparison standard; " mistake " found in each check and correction is stored in the comparison standard, and revises the comparison standard automatically.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 03114943 CN1425980A (en) | 2003-01-14 | 2003-01-14 | Personalized opening computer voice log-in method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 03114943 CN1425980A (en) | 2003-01-14 | 2003-01-14 | Personalized opening computer voice log-in method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1425980A true CN1425980A (en) | 2003-06-25 |
Family
ID=4790538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 03114943 Pending CN1425980A (en) | 2003-01-14 | 2003-01-14 | Personalized opening computer voice log-in method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1425980A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102971787A (en) * | 2010-10-29 | 2013-03-13 | 安徽科大讯飞信息科技股份有限公司 | Method and system for endpoint automatic detection of audio record |
| CN103366743A (en) * | 2012-03-30 | 2013-10-23 | 北京千橡网景科技发展有限公司 | Voice-command operation method and device |
| CN106384589A (en) * | 2016-03-07 | 2017-02-08 | 陈勇 | Individual voice input device |
-
2003
- 2003-01-14 CN CN 03114943 patent/CN1425980A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102971787A (en) * | 2010-10-29 | 2013-03-13 | 安徽科大讯飞信息科技股份有限公司 | Method and system for endpoint automatic detection of audio record |
| CN102971787B (en) * | 2010-10-29 | 2014-04-23 | 安徽科大讯飞信息科技股份有限公司 | Method and system for endpoint automatic detection of audio record |
| US9330667B2 (en) | 2010-10-29 | 2016-05-03 | Iflytek Co., Ltd. | Method and system for endpoint automatic detection of audio record |
| CN103366743A (en) * | 2012-03-30 | 2013-10-23 | 北京千橡网景科技发展有限公司 | Voice-command operation method and device |
| CN106384589A (en) * | 2016-03-07 | 2017-02-08 | 陈勇 | Individual voice input device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1267326B1 (en) | Artificial language generation | |
| US6839667B2 (en) | Method of speech recognition by presenting N-best word candidates | |
| US6910012B2 (en) | Method and system for speech recognition using phonetically similar word alternatives | |
| CN101154380B (en) | Method and device for registration and validation of speaker's authentication | |
| KR20170041105A (en) | Apparatus and method for calculating acoustic score in speech recognition, apparatus and method for learning acoustic model | |
| CN107103900A (en) | A kind of across language emotional speech synthesizing method and system | |
| CN103578464A (en) | Language model establishing method, speech recognition method and electronic device | |
| US20030154080A1 (en) | Method and apparatus for modification of audio input to a data processing system | |
| CA2486125A1 (en) | A system and method of using meta-data in speech-processing | |
| EP1349145A3 (en) | System and method for providing information using spoken dialogue interface | |
| CN106057192A (en) | Real-time voice conversion method and apparatus | |
| US20020065653A1 (en) | Method and system for the automatic amendment of speech recognition vocabularies | |
| US20090157408A1 (en) | Speech synthesizing method and apparatus | |
| US20020087317A1 (en) | Computer-implemented dynamic pronunciation method and system | |
| US20020198712A1 (en) | Artificial language generation and evaluation | |
| CN1811912B (en) | Minor sound base phonetic synthesis method | |
| CN102970618A (en) | Video on demand method based on syllable identification | |
| US20060129398A1 (en) | Method and system for obtaining personal aliases through voice recognition | |
| CN108831458A (en) | A kind of offline voice is to order transform method and system | |
| CN1425980A (en) | Personalized opening computer voice log-in method | |
| Comerford et al. | The voice of the computer is heard in the land (and it listens too!)[speech recognition] | |
| Venkatagiri | Speech recognition technology applications in communication disorders | |
| US20030018473A1 (en) | Speech synthesizer and telephone set | |
| Yeh et al. | Speech recognition with word fragment detection using prosody features for spontaneous speech | |
| Sreejith et al. | Automatic prosodic labeling and broad class Phonetic Engine for Malayalam |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |