CN104021146A - Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files - Google Patents
Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files Download PDFInfo
- Publication number
- CN104021146A CN104021146A CN201410207282.2A CN201410207282A CN104021146A CN 104021146 A CN104021146 A CN 104021146A CN 201410207282 A CN201410207282 A CN 201410207282A CN 104021146 A CN104021146 A CN 104021146A
- Authority
- CN
- China
- Prior art keywords
- configuration file
- speaker
- user
- microsoft
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/065—Adaptation
- G10L15/07—Adaptation to the speaker
Abstract
An automatic switching method for Microsoft voice recognition configuration files includes the steps that a corresponding table of the configuration files and identity information of all users using the same computer for voice recognition is set up; one user makes a sound to a microphone, and the computer can recognize the identity according to the timbre of the sound of the speaker and output the identity information of the user; the corresponding configuration file is queried from the corresponding table file according to the identity information of the user; the configuration file of the user is automatically switched to. The invention further provides an automatic switching system for the Microsoft voice recognition configuration files.
Description
Technical field
The present invention relates to the automatic switchover of computer speech identification configuration file, in particular to automatic switching method and the system thereof of a kind of Microsoft speech recognition configuration file.
Background technology
At present, the speech recognition engine of main flow has Microsoft, University of Science and Technology news to fly with Google etc. in the industry, wherein the identification engine of Microsoft is that the tranining database of installing based on this locality of windows platform carries out work, this learning sample collection that has just determined it unlike University of Science and Technology news fly, the database of the speech recognition engine that is deployed in high in the clouds of Google is so huge.In general, the engine of Microsoft needs user to carry out pronounciation training to form and leave the local configuration file that is applicable to this user in.When being provided with after the acquiescence support of the configuration file of training through user, the engine precision of identifying speech of Microsoft can reach gratifying degree.
But in the time having some users to use same computer to do speech recognition, just need between different configuration files, switch, current such switching must rely on manual operation completely and carry out.For example, because the action that configuration file switches is more loaded down with trivial details: in win8 system, first user wants the speaker icon in right mouse button point-> to select sound pick-up outfit-> in the window ejecting, to continue to choose with right mouse button microphone icon-> to choose " configured voice identification " menu-> in the control panel ejecting, to choose upper left " advanced speech option "-> in the voice attributes window ejecting, to choose configuration file-> corresponding to user to exit by determining, has 7 steps altogether and realize the switching of configuration file.If open microphone and arrange the switching of configuration file by control panel in win8 system, need 10 steps.The user that these operations are unfamiliar with windows system for general clerical workforce who writes document by oral account etc. is a white elephant, the present invention proposes a kind of single stepping method of the configuration file that automatically switches.
Summary of the invention
The present invention will solve prior art and rely on manually operated shortcoming, and automatic switching method and the system thereof of a kind of Microsoft speech recognition configuration file is provided.
An automatic switching method for configuration file, is characterized in that, comprising:
Step 1, system initialisation phase create use same user's identity information and the correspondence table of configuration file that computer carries out speech recognition;
Step 2, before everyone uses speech recognition, user opens microphone and facing to microphone sounding, computer is identified speaker's voice identity, and exports this user's identity information;
Step 3, then system, from corresponding list file, inquires configuration filename corresponding to this user according to this user's identity information;
Step 4, system are switched to this user's configuration file according to configuration file star default configuration file obtained in the previous step, then start to enter the work of speech recognition.
Further, the identification of computer to speaker in step 2, its concrete mode is: open microphone and carry out according to the signature analysis of input audio frequency.In step 3, there is the corresponding table of speaker ' s identity configuration file with the configuration file of speech recognition configuration listed files string representation of the same name one to one.
An automatic switchover system for Microsoft's speech recognition configuration file, comprises microphone location module, Speaker Identification module, the corresponding table of speaker ' s identity configuration file, Microsoft's speech recognition engine the profile list, the SAPI of Microsoft storehouse Helper function and automatic switching module;
Microphone location module is to open the acoustic signal of microphone collection user environment, exports to Speaker Identification module;
Speaker Identification module is analyzed speaker's sound tone color, the speaker's who exports to automatic switching module identity information according to the voice signal gathering;
Automatic switching module, for the configuration that amendment default configuration file is this user automatically, does not need through loaded down with trivial details manual operation;
The corresponding table of speaker ' s identity configuration file is for providing inquiry to automatic switching module, so that automatic switching module obtains the corresponding configuration filename of this speaker;
Micro-the profile list of Microsoft's speech recognition engine is the filename that Microsoft's speech recognition engine is deployed in each local user voice training characteristic, and this list travels through used in the time that handover module arranges default configuration file;
The SAPI of Microsoft storehouse Helper function for handover module provide about amendment default configuration file interface API.
Advantage of the present invention is: can on the basis of Microsoft's speech recognition engine, realize the different configuration file that automatically switches, without manual operation.
Brief description of the drawings
Fig. 1 is the logical schematic that realizes of embodiment of the present invention configuration file automatic switching method, and in figure, in speech recognition configuration listed files, the configuration file k of overstriking represents it is active user's default configuration file.
Fig. 2 is the systemic-function operation logic sequence chart of the embodiment of the present invention.
Fig. 3 is the system component figure of the embodiment of the present invention, in figure
what represent is " depending on ".
Embodiment
With reference to accompanying drawing:
An automatic switching method for configuration file, is characterized in that, comprising:
Step 1, system initialisation phase create use same user's identity information and the correspondence table of configuration file that computer carries out speech recognition;
Step 2, before everyone uses speech recognition, user opens microphone and facing to microphone sounding, computer is identified speaker's voice identity, and exports this user's identity information;
Step 3, then system, from corresponding list file, inquires configuration filename corresponding to this user according to this user's identity information;
Step 4, system are switched to this user's configuration file according to configuration file star default configuration file obtained in the previous step, then start to enter the work of speech recognition.
The identification of computer to speaker in step 2, its concrete mode is: open microphone and carry out according to the signature analysis of input audio frequency.In step 3, there is the corresponding table of speaker ' s identity configuration file with the configuration file of speech recognition configuration listed files string representation of the same name one to one.
Please refer to Fig. 1 below, this figure is the logical schematic that realizes of configuration file automatic switching method, specifically describes as follows:
Create all users' the identity information and the corresponding list file of configuration file that use same computer; In the time that microphone has phonetic entry, computer is identified speaker's voice identity, and exports this speaker's identity information; From corresponding list file, speaker's identity information inquires its corresponding configuration file, and the configuration file that automatically switches again.
Multiple element representations in figure in speech recognition configuration listed files have been trained multiple configuration files at present in speech recognition system, and the configuration file of acquiescence only has one; While pointing to speech recognition configuration listed files when automatically switching, represent to check whether default configuration file is exactly current user's configuration, if not automatically revise the configuration that default configuration file is active user, in figure, exactly the configuration file of user k is made as to default configuration file.
Please refer to Fig. 2 below, this figure is systemic-function operation logic sequence chart, and concrete flow process is as follows:
Create all users' that use same computer to carry out speech recognition identity information and the corresponding list file of configuration file.
1) user is facing to microphone sounding;
2) speaker's sounding tone color is identified, and exported this speaker's identity information;
3) remove to mate this speaker's configuration filename according to the speaker ' s identity information of output after identification;
4) the coupling configuration file that automatically switches after configuration filename;
5) user continues to speak facing to microphone;
6) continue to carry out speech recognition.
Correspondingly, the automatic switchover system of a kind of Microsoft of the present invention speech recognition configuration file, comprises microphone location module, Speaker Identification module, the corresponding table of speaker ' s identity configuration file, Microsoft's speech recognition engine the profile list, the SAPI of Microsoft storehouse Helper function and automatic switching module;
Microphone location module is to open the acoustic signal of microphone collection user environment, exports to Speaker Identification module;
Speaker Identification module is analyzed speaker's sound tone color according to the voice signal gathering, to automatic switching module output speaker's identity information;
Automatic switching module, for the configuration that amendment default configuration file is this user automatically, does not need through loaded down with trivial details manual operation;
The corresponding table of speaker ' s identity configuration file is for providing inquiry to automatic switching module, so that automatic switching module obtains the corresponding configuration filename of this speaker;
The profile list of Microsoft's speech recognition engine is the filename that Microsoft's speech recognition engine is deployed in each local user voice training characteristic, and this list travels through used while default configuration file being set for handover module;
The SAPI of Microsoft storehouse Helper function for handover module provide about amendment default configuration file interface API.
Speaker Identification module is to set up personnel's tamber characteristic storehouse according to the spectrum signature such as speech pitch, resonance peak, realizes Speaker Identification, and accurately searches speaker's configuration file.
Speaker ' s identity identification (Speaker Recognition) although precision performance error affect the accuracy that the identification of speaker ' s identity is exported, but the reduction that wrong configuration file is set can cause precision of identifying speech causing thus, this is because mistake appears in Speaker Identification, the tamber characteristic that means this two people is more similar, so their configuration file is also seemingly closer, thereby cause them can not cause mutually the reduction of precision of identifying speech with the other side's configuration file.
Automatic switching module is for the configuration that amendment default configuration file is active user automatically, does not need through loaded down with trivial details manual operation.
What automatically switch realizes logic according to Speaker Identification module output " user " information, inquire " configuration file " name corresponding to " user " from corresponding list file, the interface function of the Helper part in the SAPI storehouse that use Microsoft provides is realized the change of default configuration file, thereby realizes the switching between different configuration files.The method of calling that the SAPI interface of default configuration file is wherein set is
// enumerate all configuration files in the profile list
Please refer to Fig. 3 below, this figure is system component figure, and particular content comprises:
System will realize automatic switchover configuration file need to depend on user, the corresponding table of configuration filename, the SAPI of Microsoft storehouse Helper interface function and third party's Speaker Identification engine.
User, the corresponding table of configuration filename are to search corresponding configuration file according to subscriber identity information;
The SAPI of Microsoft storehouse Helper interface function is change for realizing default configuration file;
Third party's Speaker Identification engine depends on microphone location, and this is with voice tone color identification speaker ' s identity because of third party's Speaker Identification engine, need to have the input of microphone location just can carry out identification.
Claims (4)
1. the automatic switching method of Microsoft's speech recognition configuration file, is characterized in that, comprising:
Step 1, system initialisation phase create use same user's identity information and the correspondence table of configuration file that computer carries out speech recognition;
Step 2, before everyone uses speech recognition, user opens microphone and facing to microphone sounding, computer is identified speaker's voice identity, and exports this user's identity information;
Step 3, then system, from corresponding list file, inquires configuration filename corresponding to this user according to this user's identity information;
Step 4, system are switched to this user's configuration file according to configuration file star default configuration file obtained in the previous step, then start to enter the work of speech recognition.
2. method according to claim 1, is characterized in that: the identification of computer to speaker in step 2, its concrete mode is: open microphone and carry out according to the signature analysis of input audio frequency.
3. method according to claim 1, is characterized in that: in step 3, have the corresponding table of speaker ' s identity configuration file with the configuration file of speech recognition configuration listed files string representation of the same name one to one.
4. right to use requires a system for the method described in 1, it is characterized in that: comprise microphone location module, Speaker Identification module, the corresponding table of speaker ' s identity configuration file, Microsoft's speech recognition engine the profile list, the SAPI of Microsoft storehouse Helper function and automatic switching module;
Microphone location module is to open the acoustic signal of microphone collection user environment, exports to Speaker Identification module;
Speaker Identification module is analyzed speaker's sound tone color, the speaker's who exports to automatic switching module identity information according to the voice signal gathering;
Automatic switching module, for the configuration that amendment default configuration file is this user automatically, does not need through loaded down with trivial details manual operation;
The corresponding table of speaker ' s identity configuration file is for providing inquiry to automatic switching module, so that automatic switching module obtains the corresponding configuration filename of this speaker;
The profile list of Microsoft's speech recognition engine is the filename that Microsoft's speech recognition engine is deployed in each local user voice training characteristic, and this list travels through used while default configuration file being set for handover module;
The SAPI of Microsoft storehouse Helper function for handover module provide about amendment default configuration file interface API.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410207282.2A CN104021146A (en) | 2014-05-15 | 2014-05-15 | Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410207282.2A CN104021146A (en) | 2014-05-15 | 2014-05-15 | Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104021146A true CN104021146A (en) | 2014-09-03 |
Family
ID=51437901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410207282.2A Pending CN104021146A (en) | 2014-05-15 | 2014-05-15 | Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104021146A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104867494A (en) * | 2015-05-07 | 2015-08-26 | 广东欧珀移动通信有限公司 | Naming and classification method and system of sound recording files |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819758A (en) * | 2009-12-22 | 2010-09-01 | 中兴通讯股份有限公司 | System of controlling screen display by voice and implementation method |
| CN103607609A (en) * | 2013-11-27 | 2014-02-26 | Tcl集团股份有限公司 | Voice switching method and device for TV set channels |
-
2014
- 2014-05-15 CN CN201410207282.2A patent/CN104021146A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819758A (en) * | 2009-12-22 | 2010-09-01 | 中兴通讯股份有限公司 | System of controlling screen display by voice and implementation method |
| CN103607609A (en) * | 2013-11-27 | 2014-02-26 | Tcl集团股份有限公司 | Voice switching method and device for TV set channels |
Non-Patent Citations (1)
| Title |
|---|
| 郭宁宁: "《多媒体实用技术》", 30 September 2006 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104867494A (en) * | 2015-05-07 | 2015-08-26 | 广东欧珀移动通信有限公司 | Naming and classification method and system of sound recording files |
| CN104867494B (en) * | 2015-05-07 | 2017-10-24 | 广东欧珀移动通信有限公司 | The name sorting technique and system of a kind of recording file |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10079014B2 (en) | Name recognition system | |
| US8700397B2 (en) | Speech recognition of character sequences | |
| US10811005B2 (en) | Adapting voice input processing based on voice input characteristics | |
| CN101484934B (en) | Method and device for the natural-language recognition of a vocal expression | |
| US20160328205A1 (en) | Method and Apparatus for Voice Operation of Mobile Applications Having Unnamed View Elements | |
| KR101330328B1 (en) | Method of recognizing voice and system for the same | |
| US8374862B2 (en) | Method, software and device for uniquely identifying a desired contact in a contacts database based on a single utterance | |
| WO2021135604A1 (en) | Voice control method and apparatus, server, terminal device, and storage medium | |
| EP2680165B1 (en) | System and method to perform textual queries on voice communications | |
| KR102141116B1 (en) | Interface device and method supporting speech dialogue survice | |
| WO2016002251A1 (en) | Information processing system, and vehicle-mounted device | |
| WO2019082017A1 (en) | Creating modular conversations using implicit routing | |
| JP2015510176A (en) | Input processing method and apparatus | |
| CN105426357A (en) | Fast voice selection method | |
| WO2006126649A1 (en) | Audio edition device, audio edition method, and audio edition program | |
| CN103106061A (en) | Voice input method and device | |
| CN106504748A (en) | A kind of sound control method and device | |
| CN108509412A (en) | A kind of data processing method, device, electronic equipment and storage medium | |
| WO2019051805A1 (en) | Data processing device and method for performing speech-based human machine interaction | |
| CN103426429A (en) | Voice control method and voice control device | |
| US9747891B1 (en) | Name pronunciation recommendation | |
| US20210065708A1 (en) | Information processing apparatus, information processing system, information processing method, and program | |
| EP3843090B1 (en) | Method and apparatus for outputting analysis abnormality information in spoken language understanding | |
| CN109120774A (en) | Terminal applies voice control method and system | |
| CN104021146A (en) | Automatic switching method for Microsoft voice recognition configuration files and system of Microsoft voice recognition configuration files |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140903 |