CN103037117A - Method and system of voice recognition and voice access platform - Google Patents
Method and system of voice recognition and voice access platform Download PDFInfo
- Publication number
- CN103037117A CN103037117A CN2011103044652A CN201110304465A CN103037117A CN 103037117 A CN103037117 A CN 103037117A CN 2011103044652 A CN2011103044652 A CN 2011103044652A CN 201110304465 A CN201110304465 A CN 201110304465A CN 103037117 A CN103037117 A CN 103037117A
- Authority
- CN
- China
- Prior art keywords
- user
- provincialism
- access
- mandarin
- code
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a method and a system of voice recognition and a voice access platform, and relates to the technical field of voice recognition. The area a user located in is determined according to the calling number of an incoming call, a mandarin voice recognition characteristic library with dialect characteristics corresponding to the area of the user is called, and therefore voice interaction with the user is achieved. The mandarin voice recognition characteristic library with the dialect characteristics is capable of recognizing the mandarin with the dialect characteristics. The method and the system of voice recognition and the voice access system establish a plurality of voice recognition libraries according to the characteristics of mandarin in different areas, call different libraries for users in different areas by analyzing the calling number of the incoming call, and improve voice recognition rate.
Description
Technical field
The present invention relates to speech recognition technology, relate in particular to a kind of audio recognition method, system and audio access platform.
Background technology
In recent years, speech recognition technology is obtained marked improvement, begins to move towards market from the laboratory.In actual applications, in order to save operator's cost, the audio access platform possesses automatic recognition of speech function, by identification user's speech input information, automatically finishes mutual with the user.
China is populous nation multi-national, multilingual, that in many ways say.According to linguist's statistics, 56 nationalitys of China have the language that kind more than 80 can not be conversed each other.The people of different regions also has the difference of dialect on the basis of language, and dialect quantity is more countless.Mandarin becomes basically universal as the language that exchanges at present, but owing to be subject to the impact of dialect, various places crowd's mandarin has different features, but the crowd of the same area, its word speed that speaks standard Chinese pronunciation, voice, semanteme have similarity.
Promote the use of in that the audio access platform is actual, because user's mandarin of different regions and incomplete standard with area feature, cause phonetic recognization rate not high, automatic recognition of speech function is often given it up.
Summary of the invention
In view of this, the technical problem that the present invention will solve provides a kind of audio recognition method, can improve the discrimination to voice.
A kind of audio recognition method comprises: the calling number according to the access phone is determined user's affiliated area; Call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area user's voice are identified, finish the interactive voice with described user; Wherein, described mandarin pronunciation recognition feature storehouse with provincialism is applicable to identify the mandarin with provincialism.
According to an embodiment of the inventive method, described calling number according to the access phone determines that user's affiliated area comprises: when subscriber phone accesses, if calling number is the PSTN number, according to area code drawn game number definite user region; Wherein, described PSTN number is area code+office number+telephone subscriber's numbering; When calling number for its net mobile subscriber number the time, determine the user region according to Mobile Access Code and HLR identification code number information; Wherein, described mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
An embodiment according to the inventive method, described calling number according to the access phone determines that user's affiliated area comprises: to the apparel CRM inquiry user's corresponding with described calling number identity information, return described user's identity information for the system of real name user, determine the user region according to described identity information.
An embodiment according to the inventive method, the calling number of described analysis access phone, determine that the user region comprises: when described access phone is IP phone, distribute to the regional information of the number of described IP phone according to operator, determine the user region.
According to an embodiment of the inventive method, corresponding relation is set up with the mandarin with provincialism in described mandarin pronunciation recognition feature storehouse with provincialism, and described mandarin with provincialism is sub-divided into districts and cities' rank.
Method of the present invention is determined the residing zone of user by analyzing calling number, calls the speech recognition features storehouse corresponding with the mandarin with this regional provincialism, thereby has improved the discrimination to voice.
The technical problem that the present invention will solve provides a kind of speech recognition system, can improve the discrimination to voice.
A kind of speech recognition system comprises: have the mandarin pronunciation recognition feature storehouse of provincialism, be used for identification and have the mandarin of regional provincialism; Voice access server is used for determining user's affiliated area according to the calling number of access phone; Call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area user's voice are identified, finish the interactive voice with described user.
An embodiment of system according to the invention, if described calling number is the PSTN number, described voice access server is according to area code drawn game number definite user region; If calling number is the mobile subscriber number of its net, described voice access server is determined the user region according to Mobile Access Code and HLR identification code number information; Wherein, described PSTN number is area code+office number+telephone subscriber's numbering; Described mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
An embodiment of system according to the invention, described voice access server is to the apparel CRM inquiry user's corresponding with described calling number identity information, return described user's identity information for the described crm system of system of real name user, described voice access server is determined the user region according to described identity information.
An embodiment of system according to the invention, if described access phone is IP phone, described voice access server is determined the user region according to the regional information that operator distributes to the number of described IP phone.
An embodiment of system according to the invention, corresponding relation is set up with the mandarin with provincialism in described mandarin pronunciation recognition feature storehouse with provincialism, and described mandarin with provincialism is sub-divided into districts and cities' rank.
Voice access server in the system of the present invention is determined the residing zone of user by analyzing calling number, calls the speech recognition features storehouse corresponding with the mandarin with this regional provincialism, has improved the discrimination to voice.
The technical problem that the present invention will solve provides a kind of audio access platform, can improve the discrimination to voice.
A kind of audio access platform comprises: determine the unit, user area, be used for determining user's affiliated area according to the calling number of access phone; Call the speech recognition features library unit, be used for calling the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area; Wherein, described mandarin pronunciation recognition feature storehouse with provincialism is applicable to identify the mandarin with described regional provincialism.
Platform embodiment according to the present invention, further comprise: inquiring user identity unit, be used for according to the identity information of calling number to the apparel CRM inquiring user, return described user's identity information for the described crm system of system of real name user; The user region is determined according to described identity information in unit, described definite user area.
Platform embodiment according to the present invention, if described calling number is the PSTN number, unit, described definite user area is according to area code drawn game number definite user region; If calling number is the mobile subscriber number of its net, the user region is determined according to Mobile Access Code and HLR identification code number information in unit, described definite user area; Wherein, described PSTN number is area code+office number+telephone subscriber's numbering; Described mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
Platform embodiment according to the present invention, if described access phone is IP phone, the user region is determined according to the regional information that operator distributes to the number of described IP phone in unit, described definite user area.
Audio access platform of the present invention is determined the residing zone of user by analyzing calling number, calls the speech recognition features storehouse corresponding with the mandarin with this regional provincialism, has improved the discrimination to voice.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, the below will do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the flow chart according to an embodiment of audio recognition method of the present invention;
Fig. 2 is the flow chart according to another embodiment of audio recognition method of the present invention;
Fig. 3 is the schematic diagram according to an embodiment of speech recognition system of the present invention;
Fig. 4 is the schematic diagram according to an embodiment of audio access platform of the present invention;
Fig. 5 is the schematic diagram according to another embodiment of audio access platform of the present invention.
Embodiment
With reference to the accompanying drawings the present invention is described more fully, exemplary embodiment of the present invention wherein is described.Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
In order to improve phonetic recognization rate, adopt at present more method to have two kinds, a kind of is voice recognition mode for the specific user, a kind of is the voice recognition mode of not distinguishing the user;
RM for the specific user: the user is at first in the enterprising lang sound training of speech recognition platform and study, set up specific user's speech recognition library, after the user logins with specific user name, sound identification module calls the specific speech recognition library of this user, can effectively improve phonetic recognization rate;
Do not distinguish user's voice recognition mode: system sets up speech recognition library according to standard mandarin, and any user can call sound identification module, identifies according to standard mandarin, and this mode phonetic recognization rate is lower;
The present invention need not set up the phonetic feature storehouse for each user, and according to the feature of zones of different mandarin, sets up a plurality of speech recognition library, the user of zones of different calls different storehouses, effectively reduce the kind of speech recognition library, reduced the process of user speech study, improved phonetic recognization rate;
When phone accesses, analyze the calling number of access phone and determine the user region, call the speech recognition features storehouse corresponding with the mandarin with regional provincialism, finish the interactive voice with the user, Effective Raise to the discrimination of voice.The mobile subscriber number of its net of indication of the present invention refers to not be Home Network mobile subscriber's number, but the mobile subscriber number of other carrier network.
Below in conjunction with each figure and embodiment technical scheme of the present invention is carried out many-sided description.
Fig. 1 is the flow chart according to an embodiment of audio recognition method of the present invention.As shown in Figure 1:
Step 102: according to the calling number of access phone, determine the user region;
Step 103: call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area, finish the interactive voice with the user.The mandarin with regional provincialism can be identified in the speech recognition features storehouse.
Determine the user region by the calling number of analyzing the access phone, call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area, finish the interactive voice with the user, improved the discrimination to voice.
According to one embodiment of present invention, when the subscriber phone access is arranged, if calling number is the PSTN number, according to area code drawn game number definite user region; Wherein, the PSTN number is area code+office number+telephone subscriber's numbering; If calling number is mobile subscriber number, determine the user region according to Mobile Access Code and HLR identification code number information; Wherein, mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
According to one embodiment of present invention, identity information to manageming contacts CRM (Customer Relationship Management) the system queries user corresponding with calling number, return user's identity information for the system of real name user, determine the user region according to identity information.
According to one embodiment of present invention, if caller is IP phone, according to the regional information that operator distributes to the number of IP phone, determine the user region.IP phone is if the telephone number that operator provides, and has during number assignment by the district to distribute, and the characteristics in the time of can be according to number assignment are determined user's geographical position and identity information.
According to one embodiment of present invention, the mandarin that has a provincialism is sub-divided into districts and cities' rank.To the zone of dialect complexity, be sub-divided into the following zone of districts and cities, comprise city, county or district.
Fig. 2 is the flow chart according to another embodiment of audio recognition method of the present invention.As shown in Figure 2:
Step 202: subscriber phone access.
Step 203: the type of judging calling number.
Step 204: judge that calling number is PSTN user's number.
Step 205: according to area code drawn game number definite user region of PSTN number; The PSTN number is area code+office number+telephone subscriber's numbering.
Step 206: judge that calling number is the mobile subscriber's of its net number.Wherein for the mobile subscriber number of its net, there be not the customer information corresponding with its net mobile number in the apparel CRM.Step 207: determine the user region according to Mobile Access Code and HLR identification code number information.Mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
Step 208: the number of judging caller is the Home Network mobile subscriber.
Step 209: to the apparel CRM inquiry user's corresponding with calling number identity information.
Step 210: judge whether crm system has returned user's identity information.
Step 211: for the identity information that the system of real name user returns the user, determine the user region according to identity information.User's identity information can comprise information such as name, nationality, native place, birthplace and identity card of user etc.Can by the zone at definite user places such as native place or birthplace information, also can determine by the information of ID card No. the zone at user place.
Step 212: if do not return user's identity information, then judge the type of calling number.If the number of caller is mobile subscriber's number, execution in step 207 is determined the user region.
Step 213: call corresponding speech recognition library according to customer position information, call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area.
Step 214: enter the subsequent operation flow process.
According to one embodiment of present invention, a Guangdong Telecom cdma user dials in the audio access platform of Guangdong Telecom, and when Guangdong Telecom cdma user was linked into voice platform, platform is the calling number of analysis user at first, and discovery is the Home Network Subscriber Number; The audio access platform returns user's ID card No. information by the identity information of calling number to the crm system inquiring user for the system of real name user.To returning user identity card information, the audio access platform is determined user's positional information according to ID card information.Return other informations for non-system of real name user, analyze the CDMA number, CC+MAC+H0 H1 H2 H3+ABCD, CC wherein: be national code, China uses 86, MAC: be Mobile Access Code, be 133,153,189 etc., H0H1H2H 3:HLR identification code is distributed unitedly by China Telecom.The audio access platform is by MAC+H0 H1 H2 H3 number information, determine that the user is certain districts and cities of Guangdong Telecom subordinate, the audio access platform calls the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area according to customer position information.Speech recognition is carried out in phonetic entry according to the user, and audio access platform boot user enters follow-up flow process.
By analyzing the calling number of access phone, determine the user region according to the type of different calling numbers, call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area, finish the interactive voice with the user, improved the discrimination to voice.
Fig. 3 is the schematic diagram according to an embodiment of speech recognition system of the present invention.Shown in Figure 3: speech recognition system comprises that speech recognition features storehouse 31 is for having the mandarin pronunciation recognition feature storehouse of provincialism.31 identifications of speech recognition features storehouse have the mandarin of regional provincialism; The calling number that voice access server 32 is analyzed by tandem exchange's 34 accesses is determined the user region; Call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area, finish the interactive voice with the user.
According to one embodiment of present invention, voice access server 32 is analyzed calling number, if calling number is the PSTN number, according to area code drawn game number definite user region; If calling number is mobile subscriber number, determine the user region according to Mobile Access Code and HLR identification code number information;
Wherein, the PSTN number is area code+office number+telephone subscriber's numbering; Mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
According to one embodiment of present invention, voice access server 32 is according to the identity information of calling number to apparel CRM 33 inquiring users, return user's identity information for system of real name user crm system 33, voice access server is determined the user region according to identity information.
According to one embodiment of present invention, if calling number is IP phone, the audio access platform is determined the user region according to the regional information that operator distributes to the number of IP phone.
According to one embodiment of present invention, corresponding relation is set up with the mandarin with provincialism in the mandarin pronunciation recognition feature storehouse 31 with provincialism, and the mandarin with provincialism is sub-divided into districts and cities' rank.To the zone of dialect complexity, be sub-divided into the following zone of districts and cities, comprise city, county or district.
Voice access server 32 in the system of the present invention is determined the residing zone of user by analyzing calling number, call the mandarin pronunciation recognition feature storehouse 31 with provincialism corresponding with the mandarin with this regional provincialism, improved the discrimination to voice.
Fig. 4 is the schematic diagram according to an embodiment of audio access platform of the present invention.As shown in Figure 4:
Audio access platform 41 comprises to be determined unit, user area 411 and calls speech recognition features library unit 412.Determine the calling number of unit, user area 411 analysis access phones, determine the user region; Call speech recognition features library unit 412 and call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with the mandarin with regional provincialism; The mandarin with regional provincialism can be identified in mandarin pronunciation recognition feature storehouse with provincialism.
According to one embodiment of present invention, determine unit, user area 411 analysis calling numbers, if calling number is the PSTN number, according to area code drawn game number definite user region; If calling number is determined the user region for the mobile subscriber number of its net according to Mobile Access Code and HLR identification code number information;
Wherein, the PSTN number is area code+office number+telephone subscriber's numbering; The mobile subscriber number of its net is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
According to one embodiment of present invention, if calling number is IP phone, determine that unit, user area 411 according to the regional information that operator distributes to the number of IP phone, determines the user region.
Fig. 5 is the schematic diagram according to another embodiment of audio access platform of the present invention.As shown in Figure 5:
Audio access platform 51 comprises definite unit, user area 511, calls speech recognition features library unit 512 and inquiring user identity unit 513.Determine the calling number of unit, user area 511 analysis access phones, determine that the user is this network users; Inquiring user identity unit 513 returns user's identity information according to the identity information of calling number to the apparel CRM inquiring user for system of real name user crm system; Determine the identity information of unit, user area 511 analysis user, determine the user region; Call speech recognition features library unit 512 and call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with the mandarin with regional provincialism.
According to one embodiment of present invention, determine unit, user area 511 analysis calling numbers, if calling number is the Home Network mobile subscriber number, so, inquiring user identity unit 513 is connected to crm system removes inquiring user according to leading role's number identity information, if crm system has returned subscriber identity information, determine 511 definite user regions, unit, user area; If crm system does not return subscriber identity information, determine that unit, user area 511 determines the user region according to Mobile Access Code and HLR identification code number information;
Wherein, the Home Network mobile subscriber number is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
The present invention determines the residing zone of user by analyzing calling number, this regional user says that general can be non-type, have an accent, have regional feature, speak Mandarin such as Shanghai people, the Cantonese speaks Mandarin, call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with the mandarin with this regional provincialism, improved the discrimination to voice.
Description of the invention provides for example with for the purpose of describing, and is not exhaustively or limit the invention to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Selecting and describing embodiment is for better explanation principle of the present invention and practical application, thereby and makes those of ordinary skill in the art can understand the various embodiment with various modifications that the present invention's design is suitable for special-purpose.
Claims (14)
1. an audio recognition method is characterized in that, comprising:
Calling number according to the access phone is determined user's affiliated area;
Call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area user's voice are identified, finish the interactive voice with described user;
Wherein, described mandarin pronunciation recognition feature storehouse with provincialism is applicable to identify the mandarin with provincialism.
2. the method for claim 1 is characterized in that:
Described calling number according to the access phone determines that user's affiliated area comprises:
When subscriber phone accesses, if calling number is the PSTN number, according to area code drawn game number definite user region;
Wherein, described PSTN number is area code+office number+telephone subscriber's numbering;
When calling number for its net mobile subscriber number the time, determine the user region according to Mobile Access Code and HLR identification code number information;
Wherein, the mobile subscriber number of described its net is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
3. the method for claim 1 is characterized in that:
Described calling number according to the access phone determines that user's affiliated area comprises:
To the apparel CRM inquiry user's corresponding with described calling number identity information, for the identity information that the system of real name user returns described user, determine the user region according to described identity information.
4. the method for claim 1 is characterized in that:
Described calling number according to the access phone determines that user's affiliated area comprises:
When described access phone is IP phone, according to the regional information that operator distributes to the number of described IP phone, determine the user region.
5. such as each described method of claim 1 to 4, it is characterized in that:
Corresponding relation is set up with the mandarin with provincialism in described mandarin pronunciation recognition feature storehouse with provincialism, and described mandarin with provincialism is sub-divided into districts and cities' rank.
6. a speech recognition system is characterized in that, comprising:
Mandarin pronunciation recognition feature storehouse with provincialism is used for identification and has the mandarin of regional provincialism;
Voice access server is used for determining user's affiliated area according to the calling number of access phone; Call the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area user's voice are identified, finish the interactive voice with described user.
7. method as claimed in claim 6 is characterized in that:
If described calling number is the PSTN number, described voice access server is according to area code drawn game number definite user region; If calling number is the mobile subscriber number of its net, described voice access server is determined the user region according to Mobile Access Code and HLR identification code number information;
Wherein, described PSTN number is area code+office number+telephone subscriber's numbering; The mobile subscriber number of described its net is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
8. system as claimed in claim 6 is characterized in that:
Described voice access server is to the apparel CRM inquiry user's corresponding with described calling number identity information, return described user's identity information for the described crm system of system of real name user, described voice access server is determined the user region according to described identity information.
9. system as claimed in claim 6 is characterized in that:
If described access phone is IP phone, described voice access server is determined the user region according to the regional information that operator distributes to the number of described IP phone.
10. such as each described system of claim 6 to 9, it is characterized in that:
Corresponding relation is set up with the mandarin with provincialism in described mandarin pronunciation recognition feature storehouse with provincialism, and described mandarin with provincialism is sub-divided into districts and cities' rank.
11. an audio access platform is characterized in that, comprising:
Determine the unit, user area, be used for determining user's affiliated area according to the calling number of access phone;
Call the speech recognition features library unit, be used for calling the mandarin pronunciation recognition feature storehouse with provincialism corresponding with user's affiliated area;
Wherein, described mandarin pronunciation recognition feature storehouse with provincialism is applicable to identify the mandarin with provincialism.
12. audio access platform as claimed in claim 11 is characterized in that, further comprises:
Inquiring user identity unit is used for according to the identity information of calling number to the apparel CRM inquiring user, returns described user's identity information for the described crm system of system of real name user;
The user region is determined according to described identity information in unit, described definite user area.
13. audio access platform as claimed in claim 11 is characterized in that:
If described calling number is the PSTN number, unit, described definite user area is according to area code drawn game number definite user region; If calling number is the mobile subscriber number of its net, the user region is determined according to Mobile Access Code and HLR identification code number information in unit, described definite user area;
Wherein, described PSTN number is area code+office number+telephone subscriber's numbering; The mobile subscriber number of described its net is national code+Mobile Access Code+HLR identification code+telephone subscriber's numbering.
14. audio access platform as claimed in claim 11 is characterized in that:
If described access phone is IP phone, the user region is determined according to the regional information that operator distributes to the number of described IP phone in unit, described definite user area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110304465.2A CN103037117B (en) | 2011-09-29 | 2011-09-29 | Audio recognition method, system and audio access platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110304465.2A CN103037117B (en) | 2011-09-29 | 2011-09-29 | Audio recognition method, system and audio access platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103037117A true CN103037117A (en) | 2013-04-10 |
| CN103037117B CN103037117B (en) | 2016-08-03 |
Family
ID=48023577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110304465.2A Active CN103037117B (en) | 2011-09-29 | 2011-09-29 | Audio recognition method, system and audio access platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103037117B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105931643A (en) * | 2016-06-30 | 2016-09-07 | 北京海尔广科数字技术有限公司 | Speech recognition method and apparatus |
| CN105931642A (en) * | 2016-05-31 | 2016-09-07 | 北京灵隆科技有限公司 | Speech recognition method, apparatus and system |
| CN107274885A (en) * | 2017-05-31 | 2017-10-20 | 广东欧珀移动通信有限公司 | Audio recognition method and Related product |
| CN107566912A (en) * | 2016-06-30 | 2018-01-09 | 上海博泰悦臻网络技术服务有限公司 | A kind of program broadcasting method, server, listening device and onboard system |
| CN107665710A (en) * | 2016-07-27 | 2018-02-06 | 上海博泰悦臻网络技术服务有限公司 | Mobile terminal sound data processing method and device |
| CN108288466A (en) * | 2016-12-30 | 2018-07-17 | 中国移动通信集团浙江有限公司 | A kind of method and device improving speech recognition accuracy |
| CN110047467A (en) * | 2019-05-08 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Audio recognition method, device, storage medium and controlling terminal |
| CN110534116A (en) * | 2019-08-29 | 2019-12-03 | 北京安云世纪科技有限公司 | Speech recognition modeling setting method and device applied to smart machine |
| CN112995421A (en) * | 2021-04-20 | 2021-06-18 | 国网浙江省电力有限公司金华供电公司 | Virtual seat system for electric power regulation and control |
| CN113709315A (en) * | 2021-08-31 | 2021-11-26 | 芸豆数字科技有限公司 | Method, device, electronic equipment and medium for identifying matching customer service to which language belongs |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000187496A (en) * | 1998-11-30 | 2000-07-04 | Lucent Technol Inc | Automatic voice/speaker recognition on digital radio channel |
| CN101329868A (en) * | 2008-07-31 | 2008-12-24 | 林超 | Speech recognition optimizing system aiming at locale language use preference and method thereof |
| CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
-
2011
- 2011-09-29 CN CN201110304465.2A patent/CN103037117B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000187496A (en) * | 1998-11-30 | 2000-07-04 | Lucent Technol Inc | Automatic voice/speaker recognition on digital radio channel |
| CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
| CN101329868A (en) * | 2008-07-31 | 2008-12-24 | 林超 | Speech recognition optimizing system aiming at locale language use preference and method thereof |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105931642A (en) * | 2016-05-31 | 2016-09-07 | 北京灵隆科技有限公司 | Speech recognition method, apparatus and system |
| CN107566912B (en) * | 2016-06-30 | 2020-08-04 | 上海博泰悦臻网络技术服务有限公司 | Program playing method, server, listening device and vehicle-mounted system |
| CN105931643A (en) * | 2016-06-30 | 2016-09-07 | 北京海尔广科数字技术有限公司 | Speech recognition method and apparatus |
| CN107566912A (en) * | 2016-06-30 | 2018-01-09 | 上海博泰悦臻网络技术服务有限公司 | A kind of program broadcasting method, server, listening device and onboard system |
| CN107665710B (en) * | 2016-07-27 | 2021-02-09 | 上海博泰悦臻网络技术服务有限公司 | Mobile terminal voice data processing method and device |
| CN107665710A (en) * | 2016-07-27 | 2018-02-06 | 上海博泰悦臻网络技术服务有限公司 | Mobile terminal sound data processing method and device |
| CN108288466A (en) * | 2016-12-30 | 2018-07-17 | 中国移动通信集团浙江有限公司 | A kind of method and device improving speech recognition accuracy |
| CN108288466B (en) * | 2016-12-30 | 2020-10-16 | 中国移动通信集团浙江有限公司 | Method and device for improving accuracy of voice recognition |
| WO2018219105A1 (en) * | 2017-05-31 | 2018-12-06 | Oppo广东移动通信有限公司 | Speech recognition and related products |
| CN107274885B (en) * | 2017-05-31 | 2020-05-26 | Oppo广东移动通信有限公司 | Speech recognition method and related product |
| CN107274885A (en) * | 2017-05-31 | 2017-10-20 | 广东欧珀移动通信有限公司 | Audio recognition method and Related product |
| CN110047467A (en) * | 2019-05-08 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Audio recognition method, device, storage medium and controlling terminal |
| CN110047467B (en) * | 2019-05-08 | 2021-09-03 | 广州小鹏汽车科技有限公司 | Voice recognition method, device, storage medium and control terminal |
| CN110534116A (en) * | 2019-08-29 | 2019-12-03 | 北京安云世纪科技有限公司 | Speech recognition modeling setting method and device applied to smart machine |
| CN112995421A (en) * | 2021-04-20 | 2021-06-18 | 国网浙江省电力有限公司金华供电公司 | Virtual seat system for electric power regulation and control |
| CN113709315A (en) * | 2021-08-31 | 2021-11-26 | 芸豆数字科技有限公司 | Method, device, electronic equipment and medium for identifying matching customer service to which language belongs |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103037117B (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103037117B (en) | Audio recognition method, system and audio access platform | |
| US7657005B2 (en) | System and method for identifying telephone callers | |
| EP3550827A1 (en) | Method and device for controlling camera shooting, smart device, and storage medium | |
| US20060246891A1 (en) | Voice mail with phone number recognition system | |
| CN104468959A (en) | Method, device and mobile terminal displaying image in communication process of mobile terminal | |
| CN102722539A (en) | Query method and device based on voice recognition | |
| CN102298929A (en) | Call center subscriber recognition method based on voice recognition | |
| CN102055855A (en) | Instant speech translation system based on multiple communication platforms | |
| CN102917143A (en) | Method and device for call of special numbers | |
| KR101127011B1 (en) | The Operation Method of Prefix and/or Surfix for the Identification of a user of Calling party Terminal | |
| CN105827877A (en) | IVR (Interactive Voice Response) platform based service processing method and IVR platform | |
| CN103249034A (en) | Method and device for acquiring contact information | |
| CN106791125A (en) | The generation method of mobile terminal and its message registration | |
| EP3157236A1 (en) | Method and device for quickly accessing ivr menu | |
| CN104202458A (en) | Method and intelligent terminal for automatically storing contact information | |
| CN105007365B (en) | A kind of extension number dialing method and device | |
| CN111343328B (en) | Voice print recognition-based call management method and system and mobile terminal | |
| KR100383054B1 (en) | Voice identification telephone number guidance and auto-connecting method and system therefor | |
| US20130315385A1 (en) | Speech recognition based query method and apparatus | |
| CN106874312B (en) | User interface acquisition method and device | |
| CN110708418B (en) | Method and device for identifying attributes of calling party | |
| CN108462802B (en) | Key operation prompting method and terminal equipment | |
| CN110310627A (en) | It is a kind of for detecting the method and system of live user | |
| EA200601130A1 (en) | METHOD OF IMPLEMENTATION OF ACCESS TO SERVICES IN TELECOMMUNICATION NETWORKS | |
| KR100399607B1 (en) | Method for servicing a translation of language by using a telephone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |