CN105825848A - Method, device and terminal for voice recognition - Google Patents
Method, device and terminal for voice recognition Download PDFInfo
- Publication number
- CN105825848A CN105825848A CN201510007739.XA CN201510007739A CN105825848A CN 105825848 A CN105825848 A CN 105825848A CN 201510007739 A CN201510007739 A CN 201510007739A CN 105825848 A CN105825848 A CN 105825848A
- Authority
- CN
- China
- Prior art keywords
- feature parameter
- fisrt feature
- action command
- execution action
- speech recognition
- 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
- Telephone Function (AREA)
Abstract
The invention provides a method, a device and a terminal for voice recognition, which relate to the technical field of communication. the method comprises steps: a first voice signal is received, and a first feature parameter of the first voice signal is acquired; whether a preset execution action instruction corresponding to the first feature parameter exists in a preset voice recognition database is judged; if yes, a preset execution action instruction corresponding to the first feature parameter is sent, and if not, a first execution action instruction corresponding to the first feature parameter is newly added. Thus, in a condition in which the voice is not recognized, correction is carried out, the voice recognition rate is improved qualitatively, and the user experience is improved.
Description
Technical field
The present invention relates to communication technical field, particularly to a kind of audio recognition method, device and terminal.
Background technology
Recent two decades comes, and speech recognition technology obtains marked improvement, starts to move towards market from laboratory.It is contemplated that, in coming 10 years, speech recognition technology will enter the every field such as industry, household electrical appliances, communication, automotive electronics, medical treatment, home services, consumption electronic product.Speech recognition technology is a cross discipline relating to signal processing, pattern recognition, theory of probability and theory of information, sounding hearing mechanism, artificial intelligence etc., its target is to be computer-readable input by the vocabulary Content Transformation in human speech, thus reaches the target of more natural ground man-machine interaction.
In prior art, when carrying out speech recognition, extract speech characteristic value, based on the phonetic feature model library set up, perform the action behavior identified.But, prior art have ignored the non-existent situation in the phonetic feature model library established of the speech characteristic parameter in the voice extracted, if there is no if, then None-identified go out user input voice, the most just cannot perform the action of correspondence, have impact on the experience of user.Simultaneously, because the use colony of mobile terminal is huge, people all over the world are using, and linguistic difference is the biggest, the phonetic feature model library necessarily causing terminal can not completely include the speech characteristic parameter of user, have impact on the practicality of audio recognition method of the prior art.Further, in prior art, phonetic feature model library is more fixing, the action behavior that corresponding voice is able to carry out, unalterable, have impact on the experience of user.
Summary of the invention
Not enough for prior art, it is an object of the invention to provide a kind of audio recognition method, device and terminal, it is intended to the problem solving to use prior art cannot effectively identify all voices.
One aspect of the present invention proposes a kind of audio recognition method, and described method includes:
Receive the first voice signal, obtain the fisrt feature parameter of described first voice signal；
Judge to preset whether speech recognition library exists the default execution action command corresponding with described fisrt feature parameter；And
If existing, then send the default execution action command corresponding with described fisrt feature parameter, if not existing, then the newly-increased first execution action command corresponding with described fisrt feature parameter.
Further, the described newly-increased first execution action command corresponding with described fisrt feature parameter comprises the steps:
Newly-built one second speech recognition library；
Described fisrt feature parameter is saved in described second speech recognition library；And
The first execution action command corresponding with described fisrt feature parameter is set.
Further, the described newly-increased first execution action command corresponding with described fisrt feature parameter comprises the steps:
Described fisrt feature parameter is saved in described default speech recognition library；And
The first execution action command corresponding with described fisrt feature parameter is set.
Further, the first execution action command that described setting is corresponding with described fisrt feature parameter comprises the steps:
Prompting user carries out authentication；
If described user passes through authentication, then terminal arranges the first execution action command corresponding with described fisrt feature parameter according to user instruction.
Further, send the default execution action command corresponding with described fisrt feature parameter described in comprise the steps:
Prompting user confirms the default execution action command corresponding with described fisrt feature parameter；
Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
Second aspect present invention proposes a kind of speech recognition equipment, and described device includes:
Receiver module, for receiving the first voice signal, obtains the fisrt feature parameter of described first voice signal；
Judge module, for judging whether default speech recognition library exists the default execution action command corresponding with described fisrt feature parameter；
Newly-increased module, if for described judge module judged result for existing, then send the default execution action command corresponding with described fisrt feature parameter, if described judge module judged result is not for exist, then the newly-increased first execution action command corresponding with described fisrt feature parameter.
Further, described newly-increased module includes:
Newly-built unit, for newly-built one second speech recognition library；
First storage unit, for being saved in described fisrt feature parameter in described second speech recognition library；
First arranges unit, for arranging the first execution action command corresponding with described fisrt feature parameter.
Further, described newly-increased module includes:
Second storage unit, for being saved in described fisrt feature parameter in described default speech recognition library；
Second arranges unit, for arranging the first execution action command corresponding with described fisrt feature parameter.
Further, if described judge module judged result is for existing, described newly-increased module specifically for: prompting user confirms the default execution action command corresponding with described fisrt feature parameter；Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
Third aspect present invention proposes a kind of terminal, and described terminal includes the speech recognition equipment described in any one of technique scheme.
According to above-mentioned technical scheme, the first voice signal can be received, obtain the fisrt feature parameter of described first voice signal；Judge to preset whether speech recognition library exists the default execution action command corresponding with described fisrt feature parameter；And if exist, then sending the default execution action command corresponding with described fisrt feature parameter, if not existing, then newly-increased corresponding with described fisrt feature parameter first performing action command；Such that it is able in the case of voice is not identified, be modified, make the discrimination of voice get a qualitative improvement, improve Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in describing below is only some embodiments of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of the audio recognition method that first embodiment of the invention provides；
Fig. 2 is the structured flowchart of the speech recognition equipment that second embodiment of the invention provides.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and beneficial effect clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Referring to the flow chart of the audio recognition method that Fig. 1, Fig. 1 provide for first embodiment of the invention, described method is applicable to terminal, and this flow process may comprise steps of:
S102, receive the first voice signal, obtain the fisrt feature parameter of described first voice signal.
In this step, the first voice signal that terminal receives, both can be to come from the voice signal of storage in other terminal or high in the clouds in the phonetic entry of user.
Speech recognition process mainly includes the pretreatment of voice signal, feature extraction, the several part of pattern match.The processes such as pretreatment includes pre-filtering, samples and quantify, windowing, end-point detection, preemphasis.The most important ring of voice signal identification is exactly characteristic parameter extraction.The characteristic parameter extracted must is fulfilled for following requirement: the characteristic parameter that (1) extracts can represent phonetic feature effectively, has good distinction；(2) there is good independence between the parameter of each rank；(3) characteristic parameter wants convenience of calculation, is preferably formed with efficient algorithm, to ensure the real-time implementation of speech recognition.
The extraction of characteristic parameter is the process that an information is significantly compressed, and is also a signal uncoiling process, its objective is to extract in voice the characteristic information that can represent voice, with reduce follow-up carry out speech recognition time required data volume to be processed.Due to the time-varying characteristics of voice, the extraction of phonetic feature must carry out on a bit of voice, namely carry out short-time analysis, and this section is considered as that stable analystal section is referred to as frame, and the skew between frame and frame generally takes the 1/2 or 1/3 of frame length.At present, the basic research of characteristic parameter extraction has been compared abundant, existing terminal has had more ripe solution, therefore, the present invention can use the speech characteristic parameter extracting mode of existing comparative maturity after receiving the first voice signal, obtains the fisrt feature parameter of described first voice signal.Described fisrt feature parameter reflects the feature of the first voice signal, the method obtaining described fisrt feature parameter has multiple, and prior art ensure that described fisrt feature parameter meets the requirement of above-mentioned (1) (3), and the present invention does not repeats them here.
Preferably, after receiving the first voice signal, need first described first voice signal to be processed, eliminate the noise of described first voice signal, so as to more accurately get the fisrt feature parameter of described first voice signal.
S104, judgement preset whether speech recognition library exists the default execution action command corresponding with described fisrt feature parameter.
Described default speech recognition library comprises at least one characteristic parameter and the execution action command corresponding with characteristic parameter each described.Each performs action command and correspond to an execution action, described execution action command is the instruction that instruction terminal performs the execution action corresponding with this execution action command, the action that can perform according to described execution action command includes the everything that terminal can perform, such as: makes a phone call, take pictures, surf the Net, send out microblogging etc..And a characteristic parameter is not limited to corresponding one and performs action command, any one characteristic parameter can perform action command by corresponding one or more.
Described default speech recognition library both can be present in terminal local, it is also possible to is present in high in the clouds.Preferably, described default speech recognition library is positioned at high in the clouds.Described default speech recognition library is positioned at high in the clouds then can save the memory space of terminal, it is also possible to facilitate other terminal to use described default speech recognition library to carry out speech recognition.
When described default speech recognition library is positioned at terminal local, described default speech recognition library both can be user's preset in advance, it is also possible to be that terminal is preset when dispatching from the factory.
After terminal gets described fisrt feature parameter, described default speech recognition library will be traveled through, described fisrt feature parameter is searched, it is judged that whether described default speech recognition library exists the default execution action command corresponding with described fisrt feature parameter in described default speech recognition library.
If S106a exists, then send the default execution action command corresponding with described fisrt feature parameter.
If there is described fisrt feature parameter in described default speech recognition library, terminal then according to the default execution action command that described fisrt feature parameter acquiring to described fisrt feature parameter is corresponding, sends the default execution action command corresponding with described fisrt feature parameter.Preferably, terminal also can perform, according to the default execution action command sent, the execution action that described default execution action command is corresponding.When described fisrt feature parameter is to when should have multiple default execution action command, terminal can point out user to select one to perform action command from the plurality of default execution action command, and the execution action command chosen described in sending；Or the execution action command that terminal selects to perform action command according to the use habit of user automatically from the plurality of default execution action command and chooses described in sending.
Optionally, default speech recognition library is searched the process of described fisrt feature parameter both can be precise search can also be to search for generally, described precise search refers to, only when existing with the described duplicate characteristic parameter of fisrt feature parameter in described default speech recognition library, just will be considered that and there is described fisrt feature parameter in described default speech recognition library；Search for generally referring to if the similarity between a certain characteristic parameter and described fisrt feature parameter has reached predetermined threshold value present in described default speech recognition library, then it is assumed that described default speech recognition library exists described fisrt feature parameter.
Although there is described fisrt feature parameter and the default execution action command corresponding with described fisrt feature parameter in described default speech recognition library, but owing to described default speech recognition library is arranged in advance, default execution action command corresponding to fisrt feature parameter in described default speech recognition library and may not meet the wish that user is current, therefore, it is necessary to prompting user confirms the default execution action command corresponding with described fisrt feature parameter.
Preferably, send the default execution action command corresponding with described fisrt feature parameter described in comprise the steps:
Prompting user confirms the default execution action command corresponding with described fisrt feature parameter；
Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
For described prompting, user can make a choice, terminal now receives the confirmation of user's input, if user confirms described default execution action command, then illustrating that the content in described default speech recognition library meets the wish that user is current, terminal sends the default execution action command corresponding with described fisrt feature parameter without departing from user intention.
Preferably, when user does not confirm described default execution action command, then prompting user setup the 3rd performs action command as the execution action command corresponding with described fisrt feature parameter；
If user disagrees described default execution action command, then illustrate that the content in described default speech recognition library does not meets the current wish of user, need user again the content in described default speech recognition library to be configured, need to point out user setup the 3rd to perform action command as the execution action command corresponding with described fisrt feature parameter.
Optionally, when terminal notifying user setup the 3rd performs action command as the execution action command corresponding with described fisrt feature parameter, and after user receives the prompting of terminal, terminal can provide some execution action commands to select for user, and user selects one to perform action command as the 3rd from some execution action commands that terminal provides.
If S106b does not exists, then the newly-increased first execution action command corresponding with described fisrt feature parameter.
If described default speech recognition library does not exist the default execution action command that fisrt feature parameter is corresponding, i.e. terminal can not find described default execution action command in described default speech recognition library, then terminal by described fisrt feature parameter display to user, and can remind user to increase described fisrt feature parameter and the corresponding with described fisrt feature parameter first execution action command newly.
After user agrees to that arranging described fisrt feature parameter and corresponding with described fisrt feature parameter first performs action command, described fisrt feature parameter can be saved in described second speech recognition library by terminal with newly-built one second speech recognition library；And the first execution action command corresponding with described fisrt feature parameter is set in described second speech recognition library.Concrete, after described fisrt feature parameter is saved in described second speech recognition library by terminal according to the selection of user, both according to the selection of user, a certain execution action command can be set to the first execution action command, it is also possible to automatically a certain execution action command is set to the first execution action command according to user habit.
A certain execution action command is set to after the process that implements of the first execution action command may is that terminal can not find described fisrt feature parameter in described default speech recognition library according to the selection of user by terminal, then terminal can be by described fisrt feature parameter display to user, described fisrt feature parameter is saved in the second speech recognition library, and provide some execution action commands to select for user in described second speech recognition library, user selects one as the first execution action command corresponding with described fisrt feature parameter from some execution action commands that terminal provides, to complete to arrange described fisrt feature parameter and the process of the corresponding with described fisrt feature parameter first execution action command in described second speech recognition library.
A certain execution action command is set to after the process that implements of the first execution action command may is that terminal can not find described fisrt feature parameter in described default speech recognition library according to user habit by terminal automatically, then terminal can be by described fisrt feature parameter display to user, described fisrt feature parameter is saved in the second speech recognition library, after this, terminal programming count all performs the execution number of times of action, and the execution action command performing the most execution action of number of times corresponding is set to the first execution action command, to complete to arrange described fisrt feature parameter and the process of the corresponding with described fisrt feature parameter first execution action command in described second speech recognition library.
Preferably, the described newly-increased first execution action command corresponding with described fisrt feature parameter can also comprise the steps:
Described fisrt feature parameter is saved in described default speech recognition library；And
The first execution action command corresponding with described fisrt feature parameter is set.
After user agrees to that arranging described fisrt feature parameter and corresponding with described fisrt feature parameter first performs action command, described fisrt feature parameter can be directly saved in described default speech recognition library by terminal, and need not newly-built second speech recognition library；And the first execution action command corresponding with described fisrt feature parameter is set in described default speech recognition library.
Preferably, the first execution action command that described setting is corresponding with described fisrt feature parameter comprises the steps: to point out user to carry out authentication；If described user passes through authentication, then terminal arranges the first execution action command corresponding with described fisrt feature parameter according to user instruction.
Content in described default speech recognition library can be updated by technique scheme or newly-built second speech recognition library of meeting, it is therefore desirable to confirm the identity of user, only pass through authentication, the user possessing certain authority can arrange described fisrt feature parameter and the corresponding with described fisrt feature parameter first execution action command, or newly-built second speech recognition library in described default speech recognition library.
If described user is not over authentication, then terminal sends alarm.If user is not over described authentication, then illustrates that the identity of described user is illegal, need to send alarm.
Refer to the block diagram of the speech recognition equipment 100 that Fig. 2, Fig. 2 provide for second embodiment of the invention.
Speech recognition equipment 100 includes: receiver module 20, judge module 40, newly-increased module 60.
Receiver module 20, for receiving the first voice signal, obtains the fisrt feature parameter of described first voice signal.
The first voice signal that receiver module 20 receives, both can be to come from the voice signal of storage in other terminal or high in the clouds in the phonetic entry of user.
Preferably, receiver module 20, after receiving the first voice signal, needs first to process described first voice signal, eliminates the noise of described first voice signal, so as to more accurately get the fisrt feature parameter of described first voice signal.
Judge module 40, for judging whether default speech recognition library exists the default execution action command corresponding with described fisrt feature parameter.
Described default speech recognition library comprises at least one characteristic parameter and the execution action command corresponding with characteristic parameter each described.Each performs action command and correspond to an execution action, described execution action command is the instruction that instruction terminal performs the execution action corresponding with this execution action command, the action that can perform according to described execution action command includes the everything that terminal can perform, such as: makes a phone call, take pictures, surf the Net, send out microblogging etc..And a characteristic parameter is not limited to a corresponding execution action, any one characteristic parameter can perform action command by corresponding one or more.
Described default speech recognition library both can be present in terminal local, it is also possible to is present in high in the clouds.Preferably, described default speech recognition library is positioned at high in the clouds.Described default speech recognition library is positioned at high in the clouds then can save the memory space of terminal, it is also possible to facilitate other terminal to use described default speech recognition library to carry out speech recognition.
When described default speech recognition library is positioned at terminal local, described default speech recognition library both can be user's preset in advance, it is also possible to be that terminal is preset when dispatching from the factory.
After receiver module 20 gets described fisrt feature parameter, judge module 40 will travel through described default speech recognition library, described fisrt feature parameter is searched, it is judged that whether described default speech recognition library exists the default execution action command corresponding with described fisrt feature parameter in described default speech recognition library.
If newly-increased module 60 for existing, then sends the default execution action command corresponding with described fisrt feature parameter for described judge module 40 judged result.
If judge module 40 judges to exist in described default speech recognition library described fisrt feature parameter, newly-increased module 60 then sends the default execution action command corresponding with described fisrt feature parameter.Preferably, newly-increased module 60 also can perform, according to the default execution action command sent, the execution action that described default execution action command is corresponding.
When described fisrt feature parameter to should have multiple preset the first execution action command time, newly-increased module 60 can point out user to select one to perform action command the first execution action command from the plurality of presetting, and the execution action command chosen described in sending；Or the execution action command that newly-increased module 60 performs to select to perform an action command action command from the plurality of first automatically according to the use habit of user and chooses described in sending.
Although there is described fisrt feature parameter and the default execution action command corresponding with described fisrt feature parameter in described default speech recognition library, but owing to described default speech recognition library is arranged in advance, default execution action command corresponding to fisrt feature parameter in described default speech recognition library and may not meet the wish that user is current, therefore, it is necessary to prompting user confirms the default execution action command corresponding with described fisrt feature parameter.
Preferably, if described judge module 40 judged result is for existing, described newly-increased module 60 specifically for: prompting user confirms the default execution action command corresponding with described fisrt feature parameter；Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
For described prompting, user can make a choice, described newly-increased module 60 now receives the confirmation of user's input, if user confirms described default execution action command, then illustrating that the content in described default speech recognition library meets the wish that user is current, described newly-increased module 60 sends the default execution action command corresponding with described fisrt feature parameter without departing from user intention.If user disagrees described default execution action command, then illustrate that the content in described default speech recognition library does not meets the current wish of user, needing user to be again configured the content in described default speech recognition library, the most described newly-increased module 60 points out user setup the 3rd to perform action command as the execution action command corresponding with described fisrt feature parameter.
Preferably, described newly-increased module 60 is additionally operable to, if described judge module 40 judged result is not for exist, then and the newly-increased first execution action command corresponding with described fisrt feature parameter.
If described default speech recognition library does not exist the default execution action command that fisrt feature parameter is corresponding, i.e. judge module 40 can not find described default execution action command in described default speech recognition library, then increasing module 60 newly by described fisrt feature parameter display to user, and can remind user to increase described fisrt feature parameter and the corresponding with described fisrt feature parameter first execution action command newly.
Preferably, described newly-increased module 60 includes: newly-built unit 601, for newly-built one second speech recognition library；
First storage unit 602, for being saved in described fisrt feature parameter in described second speech recognition library；
First arranges unit 603, for arranging the first execution action command corresponding with described fisrt feature parameter in described second speech recognition library.
Preferably, described newly-increased module 60 can also be to include:
Second storage unit 604, for being saved in described fisrt feature parameter in described default speech recognition library；
Second arranges unit 605, for arranging the first execution action command corresponding with described fisrt feature parameter in described default speech recognition library.
Present invention also offers a kind of terminal, described terminal includes the speech recognition equipment 100 that technique scheme provides.
Each embodiment in this specification all uses the mode gone forward one by one to describe, and between each embodiment, identical similar part sees mutually, and what each embodiment stressed is the difference with other embodiments.For apparatus embodiments, owing to it is substantially similar to embodiment of the method, so describing fairly simple, relevant part sees the part of embodiment of the method and illustrates.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, can be by computer program and complete to instruct relevant hardware, described program can be stored in a computer read/write memory medium, this program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-OnlyMemory, ROM) or random store-memory body (RandomAccessMemory, RAM) etc..
The above; being only the detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; the change that can readily occur in or replacement, all should contain within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (10)
1. an audio recognition method, it is characterised in that described method includes:
Receive the first voice signal, obtain the fisrt feature parameter of described first voice signal；
Judge to preset whether speech recognition library exists the default execution action command corresponding with described fisrt feature parameter；And
If existing, then send the default execution action command corresponding with described fisrt feature parameter, if not existing, then the newly-increased first execution action command corresponding with described fisrt feature parameter.
2. audio recognition method as claimed in claim 1, it is characterised in that the described newly-increased first execution action command corresponding with described fisrt feature parameter comprises the steps:
Newly-built one second speech recognition library；
Described fisrt feature parameter is saved in described second speech recognition library；And
The first execution action command corresponding with described fisrt feature parameter is set.
3. audio recognition method as claimed in claim 1, it is characterised in that the described newly-increased first execution action command corresponding with described fisrt feature parameter comprises the steps:
Described fisrt feature parameter is saved in described default speech recognition library；And
The first execution action command corresponding with described fisrt feature parameter is set.
4. as claimed in claim 2 or claim 3 audio recognition method, it is characterised in that described setting first perform action command comprise the steps: corresponding with described fisrt feature parameter
Prompting user carries out authentication；
If described user passes through authentication, then terminal arranges the first execution action command corresponding with described fisrt feature parameter according to user instruction.
5. audio recognition method as claimed in claim 1, it is characterised in that described in send the default execution action command corresponding with described fisrt feature parameter and comprise the steps:
Prompting user confirms the default execution action command corresponding with described fisrt feature parameter；
Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
6. a speech recognition equipment, it is characterised in that described device includes:
Receiver module, for receiving the first voice signal, obtains the fisrt feature parameter of described first voice signal；
Judge module, for judging whether default speech recognition library exists the default execution action command corresponding with described fisrt feature parameter；
Newly-increased module, if for described judge module judged result for existing, then send the default execution action command corresponding with described fisrt feature parameter, if described judge module judged result is not for exist, then the newly-increased first execution action command corresponding with described fisrt feature parameter.
7. speech recognition equipment as claimed in claim 6, it is characterised in that described newly-increased module includes:
Newly-built unit, for newly-built one second speech recognition library；
First storage unit, for being saved in described fisrt feature parameter in described second speech recognition library；
First arranges unit, for arranging the first execution action command corresponding with described fisrt feature parameter.
8. speech recognition equipment as claimed in claim 6, it is characterised in that described newly-increased module includes:
Second storage unit, for being saved in described fisrt feature parameter in described default speech recognition library；
Second arranges unit, for arranging the first execution action command corresponding with described fisrt feature parameter.
9. speech recognition equipment as claimed in claim 6, it is characterised in that if described judge module judged result is for existing, described newly-increased module specifically for: prompting user confirms the default execution action command corresponding with described fisrt feature parameter；Receive the confirmation of user's input, if user confirms described default execution action command, then send the default execution action command corresponding with described fisrt feature parameter.
10. a terminal, described terminal includes the speech recognition equipment described in any one of claim 6-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510007739.XA CN105825848A (en) | 2015-01-08 | 2015-01-08 | Method, device and terminal for voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510007739.XA CN105825848A (en) | 2015-01-08 | 2015-01-08 | Method, device and terminal for voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105825848A true CN105825848A (en) | 2016-08-03 |
Family
ID=56514008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510007739.XA Pending CN105825848A (en) | 2015-01-08 | 2015-01-08 | Method, device and terminal for voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105825848A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107591155A (en) * | 2017-08-29 | 2018-01-16 | 珠海市魅族科技有限公司 | Audio recognition method and device, terminal and computer-readable recording medium |
| CN108039169A (en) * | 2017-12-26 | 2018-05-15 | 海能达通信股份有限公司 | Audio signal processing method, communicating terminal and the computer-readable storage medium that group is exhaled |
| CN108737234A (en) * | 2018-08-13 | 2018-11-02 | 长虹美菱股份有限公司 | A kind of Phonetically door-opening system and method for intelligent refrigerator |
| CN109065056A (en) * | 2018-09-26 | 2018-12-21 | 珠海格力电器股份有限公司 | A kind of method and device of voice control air-conditioning |
| CN110085230A (en) * | 2019-04-30 | 2019-08-02 | 徐州重型机械有限公司 | Control method, apparatus, system and the computer readable storage medium of engineering machinery |
| CN110322876A (en) * | 2018-03-30 | 2019-10-11 | 中华映管股份有限公司 | Voice application system and its method |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
| CN113696178A (en) * | 2021-07-29 | 2021-11-26 | 大箴(杭州)科技有限公司 | Control method and system, medium and equipment for intelligent robot grabbing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923857A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Extensible audio recognition method based on man-machine interaction |
| CN103456296A (en) * | 2012-05-31 | 2013-12-18 | 三星电子株式会社 | Method for providing voice recognition function and electronic device thereof |
| CN103632665A (en) * | 2012-08-29 | 2014-03-12 | 联想(北京)有限公司 | Voice identification method and electronic device |
| CN104183237A (en) * | 2014-09-04 | 2014-12-03 | 百度在线网络技术（北京）有限公司 | Speech processing method and device for portable terminal |
| CN104281609A (en) * | 2013-07-08 | 2015-01-14 | 腾讯科技（深圳）有限公司 | Voice input instruction matching rule configuration method and device |
-
2015
- 2015-01-08 CN CN201510007739.XA patent/CN105825848A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923857A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Extensible audio recognition method based on man-machine interaction |
| CN103456296A (en) * | 2012-05-31 | 2013-12-18 | 三星电子株式会社 | Method for providing voice recognition function and electronic device thereof |
| CN103632665A (en) * | 2012-08-29 | 2014-03-12 | 联想(北京)有限公司 | Voice identification method and electronic device |
| CN104281609A (en) * | 2013-07-08 | 2015-01-14 | 腾讯科技（深圳）有限公司 | Voice input instruction matching rule configuration method and device |
| CN104183237A (en) * | 2014-09-04 | 2014-12-03 | 百度在线网络技术（北京）有限公司 | Speech processing method and device for portable terminal |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107591155A (en) * | 2017-08-29 | 2018-01-16 | 珠海市魅族科技有限公司 | Audio recognition method and device, terminal and computer-readable recording medium |
| CN108039169A (en) * | 2017-12-26 | 2018-05-15 | 海能达通信股份有限公司 | Audio signal processing method, communicating terminal and the computer-readable storage medium that group is exhaled |
| CN110322876A (en) * | 2018-03-30 | 2019-10-11 | 中华映管股份有限公司 | Voice application system and its method |
| CN108737234A (en) * | 2018-08-13 | 2018-11-02 | 长虹美菱股份有限公司 | A kind of Phonetically door-opening system and method for intelligent refrigerator |
| CN109065056A (en) * | 2018-09-26 | 2018-12-21 | 珠海格力电器股份有限公司 | A kind of method and device of voice control air-conditioning |
| CN109065056B (en) * | 2018-09-26 | 2021-05-11 | 珠海格力电器股份有限公司 | Method and device for controlling air conditioner through voice |
| CN110085230A (en) * | 2019-04-30 | 2019-08-02 | 徐州重型机械有限公司 | Control method, apparatus, system and the computer readable storage medium of engineering machinery |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
| CN113696178A (en) * | 2021-07-29 | 2021-11-26 | 大箴(杭州)科技有限公司 | Control method and system, medium and equipment for intelligent robot grabbing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105825848A (en) | Method, device and terminal for voice recognition | |
| CN109326289B (en) | Wake-up-free voice interaction method, device, equipment and storage medium | |
| CN108182937B (en) | Keyword recognition method, device, equipment and storage medium | |
| CN108831469B (en) | Voice command customizing method, device and equipment and computer storage medium | |
| CN107644638B (en) | Audio recognition method, device, terminal and computer readable storage medium | |
| US9583102B2 (en) | Method of controlling interactive system, method of controlling server, server, and interactive device | |
| CN102779509B (en) | Voice processing equipment and voice processing method | |
| CN105654949B (en) | A kind of voice awakening method and device | |
| CN107450390B (en) | intelligent household appliance control device, control method and control system | |
| US20010003173A1 (en) | Method for increasing recognition rate in voice recognition system | |
| CN105070288A (en) | Vehicle-mounted voice instruction recognition method and device | |
| CN102568478A (en) | Video play control method and system based on voice recognition | |
| CN108182944A (en) | Control the method, apparatus and intelligent terminal of intelligent terminal | |
| CN106452997A (en) | Household electrical appliance and control system thereof | |
| CN105702253A (en) | Voice awakening method and device | |
| CN103488384A (en) | Voice assistant application interface display method and device | |
| CN107729433B (en) | Audio processing method and device | |
| CN104409080A (en) | Voice end node detection method and device | |
| CN104282307A (en) | Method, device and terminal for awakening voice control system | |
| CN111081257A (en) | Voice acquisition method, device, equipment and storage medium | |
| CN107544272A (en) | terminal control method, device and storage medium | |
| CN103778915A (en) | Speech recognition method and mobile terminal | |
| CN106531195B (en) | A kind of dialogue collision detection method and device | |
| CN109697989B (en) | Audio data processing method, server and readable storage medium | |
| CN104575509A (en) | Voice enhancement processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160803 |