CN104751843A - Voice service switching method and voice service switching system - Google Patents
Voice service switching method and voice service switching system Download PDFInfo
- Publication number
- CN104751843A CN104751843A CN201310728145.9A CN201310728145A CN104751843A CN 104751843 A CN104751843 A CN 104751843A CN 201310728145 A CN201310728145 A CN 201310728145A CN 104751843 A CN104751843 A CN 104751843A
- Authority
- CN
- China
- Prior art keywords
- service
- voice
- recording
- voice service
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5108—Secretarial services
Abstract
The invention discloses a voice service switching method and a voice service switching system. The workload of a call center can be reduced under the premise of ensuring the service experience. The technical scheme is as follows: voice input of a user is recognized by local voice service first; and as voice service fails usually due to accent or inaccurate demand description, voice service is automatically switched to a remote manual agent after an error is reported, and the real service demand of the user is labeled after the service of the manual agent so as to improve a voice recognition engine. Compared with voice service of a traditional vehicle-mounted system, the problem of low recognition rate or recognition error caused by simple dependence on an automatic voice recognition engine is solved, and the problem of high cost caused by high call volume generated due to simple dependence on manual service is also solved.
Description
Technical field
The present invention relates to a kind of voice service technology of onboard system, particularly relate to the method for work switched between local voice service and remote handle are served.
Background technology
Development along with automobile industry makes automobile more and more become a part for life, the tourism on and off duty, festivals or holidays of people and looking for relative are called on a friend in process all to be needed to spend the most of the time on automobile, but driver manipulates multimedia equipment and the operation such as listens song, listens to the radio programme or carry out that destination navigation is arranged can bring hidden danger to traffic safety when driving, and in automobile, non-human pilot carries out operating the problem that there is operating position inconvenience.Therefore the intelligent sound application be identified in vehicle multimedia navigation system seems more and more urgent.
Existing speech synthesis Information Service adopts system this locality to identify or two kinds of methods of service of artificial speech access, and the language of saying is converted into word by speech recognition.Various speech recognition application utilizes word to perform data input, thus Control Component executable operations.
Local voice identification often there will be user speech identification error based on some reason (environment is noisy, mandarin is nonstandard), thus constantly circulation prompting user re-enters voice.Speech recognition mainly contains following problem: voice messaging amount is large, speech pattern is not only different to different speakers, is also different, such as to same speaker, the voice messaging of a speaker when arbitrarily speaking and conscientiously speak is different, and the tongue of a people is along with time variations.The ambiguity of voice: speaker is when talking, and different words may sound it being similar.The characteristics of speech sounds of single letter or word, word affects by contextual, so that changes stress, tone, volume and the rate of articulation etc.Neighbourhood noise and interference have a strong impact on speech recognition, cause discrimination low.
When adopting artificial speech access way, user accesses manual position after dialing service number, and manual position is the information that user inquired about and obtained its needs, adopts artificial speech to report mode and informs user, and the information content be sent in the terminal of user.
And operator attendance calls out the relative local service feedback speed of often flow process slowly, and require also very high for the workload of attending a banquet online.
Summary of the invention
The object of the invention is to solve the problem, provide a kind of voice service changing method and system, under the prerequisite can experienced at Deterministic service, reduce the workload of call center.
Technical scheme of the present invention is: present invention is disclosed a kind of voice service changing method, comprising:
The voice operating instruction of system acceptance outside also starts recording;
System carries out automatic speech recognition, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre;
After call center receives recording, artificial cognition carried out to this recording and do corresponding process.
According to an embodiment of voice service changing method of the present invention, the process of call center after carrying out artificial cognition to recording comprises:
If operator attendance identification is recorded successfully, then recording marked and issue corresponding operational order;
If operator attendance identification recording failure, then connecting subscribers participating, line provides service.
According to an embodiment of voice service changing method of the present invention, method also comprises:
The recording through mark that system issues according to operator attendance improves speech recognition.
According to an embodiment of voice service changing method of the present invention, outside voice operating instruction comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
According to an embodiment of voice service changing method of the present invention, the automatic speech recognition of system is the voice recognition processing of the automated voice identification engine based on this locality.
Present invention further teaches a kind of voice service switched system, comprising:
Recording device, receives outside voice operating instruction and starts recording;
Automatic speech recognition device, carries out automatic speech recognition to recording, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre;
Call center's treating apparatus, carries out artificial cognition to this recording after call center receives recording and does corresponding process.
According to an embodiment of voice service switched system of the present invention, call center's treating apparatus comprises:
Artificial speech identification module, if operator attendance identification is recorded successfully, then marks recording and issues corresponding operational order;
Artificial line service module, if operator attendance identification recording failure, then connecting subscribers participating, line provides service.
According to an embodiment of voice service switched system of the present invention, system also comprises:
Speech recognition modifying device, improves speech recognition according to the recording through mark that operator attendance issues.
According to an embodiment of voice service switched system of the present invention, outside voice operating instruction comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
According to an embodiment of voice service switched system of the present invention, automatic speech recognition device is the voice recognition processing of the automated voice identification engine based on this locality.
The present invention contrasts prior art following beneficial effect: the solution of the present invention is first by the phonetic entry of local voice service identification user, but often due to accent or cannot accurate description demand cause voice service failure, after reporting an error, automatically voice service is switched to long-range manual position, and after seat completes, mark the real demand for services of user, to improve speech recognition engine.Compared to the voice service of traditional onboard system, both solve the problem depending on merely the low or identification error of discrimination that automated voice identification engine causes, solve again the excessive problem causing high cost of call volume depending on merely manual service and produce.
Accompanying drawing explanation
Fig. 1 shows the process flow diagram of the first embodiment of voice service changing method of the present invention.
Fig. 2 shows the process flow diagram of the second embodiment of voice service changing method of the present invention.
Fig. 3 shows the schematic diagram of the first embodiment of voice service switched system of the present invention.
Fig. 4 shows the schematic diagram of the second embodiment of voice service switched system of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention will be further described.
first embodiment of voice service changing method
Fig. 1 shows the first embodiment of voice service changing method of the present invention.Refer to Fig. 1, details are as follows for each step of the voice service changing method of the present embodiment.
Step S10: the voice operating instruction of system acceptance outside also starts recording.
The voice operating of outside here comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
Step S11: system carries out automatic speech recognition, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre.
The automatic speech recognition that system is carried out is the voice recognition processing of the automated voice identification engine based on this locality.
Step S12: after call center receives recording, artificial cognition carried out to this recording and do corresponding process.
The heart is in the process of recording in a call, if operator attendance identification is recorded successfully, then marks recording and issues corresponding operational order; If operator attendance identification recording failure, then connecting subscribers participating, line provides service.
second embodiment of voice service changing method
Fig. 2 shows the second embodiment of voice service changing method of the present invention.Refer to Fig. 2, details are as follows for each step of the voice service changing method of the present embodiment.
Step S20: the voice operating instruction of system acceptance outside also starts recording.
The voice operating of outside here comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
Step S21: system carries out automatic speech recognition, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre.
The automatic speech recognition that system is carried out is the voice recognition processing of the automated voice identification engine based on this locality.
Step S22: after call center receives recording, artificial cognition carried out to this recording and do corresponding process.
The heart is in the process of recording in a call, if operator attendance identification is recorded successfully, then marks recording and issues corresponding operational order; If operator attendance identification recording failure, then connecting subscribers participating, line provides service.
Step S23: the recording through mark that system issues according to operator attendance improves speech recognition.
According to the result of operator attendance identification, normally automated voice identification engine is adjusted, namely help the improvement of speech recognition engine conversely.
first embodiment of voice service switched system
Fig. 3 shows the principle of the first embodiment of voice service switched system of the present invention.Refer to Fig. 3, the voice service switched system of the present embodiment comprises: recording device 10, automatic speech recognition device 11, call center's treating apparatus 12.
Recording device 10 receives outside voice operating instruction and starts recording.The voice operating of outside here comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
Automatic speech recognition device 11 carries out automatic speech recognition to recording, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre.The automatic speech recognition that automatic speech recognition device 11 carries out is the voice recognition processing of the automated voice identification engine based on this locality.
Call center's treating apparatus 12 carries out artificial cognition to this recording after the heart receives recording in a call and does corresponding process.Call center's treating apparatus 12 comprises again artificial speech identification module 120 and artificial line service module 122.In artificial speech identification module 120, if operator attendance identification is recorded successfully, then recording marked and issue corresponding operational order.In artificial line service module 122, if operator attendance identification recording failure, then connecting subscribers participating, line provides service.
second embodiment of voice service switched system
Fig. 4 shows the principle of the second embodiment of voice service switched system of the present invention.Refer to Fig. 4, the voice service switched system of the present embodiment comprises: recording device 20, automatic speech recognition device 21, call center's treating apparatus 22, speech recognition modifying device 23.
Recording device 20 receives outside voice operating instruction and starts recording.The voice operating of outside here comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
Automatic speech recognition device 21 carries out automatic speech recognition to recording, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre.The automatic speech recognition that automatic speech recognition device 21 carries out is the voice recognition processing of the automated voice identification engine based on this locality.
Call center's treating apparatus 22 carries out artificial cognition to this recording after the heart receives recording in a call and does corresponding process.Call center's treating apparatus 22 comprises again artificial speech identification module 220 and artificial line service module 222.In artificial speech identification module 220, if operator attendance identification is recorded successfully, then recording marked and issue corresponding operational order.In artificial line service module 222, if operator attendance identification recording failure, then connecting subscribers participating, line provides service.
The recording through mark that speech recognition modifying device 23 issues according to operator attendance improves speech recognition, according to the result of operator attendance identification, normally adjusts to automated voice identification engine, namely helps the improvement of speech recognition engine conversely.
Above-described embodiment is available to those of ordinary skill in the art to realize and uses of the present invention; those of ordinary skill in the art can be without departing from the present invention in the case of the inventive idea; various modifications or change are made to above-described embodiment; thus protection scope of the present invention not limit by above-described embodiment, and should be the maximum magnitude meeting the inventive features that claims are mentioned.
Claims (10)
1. a voice service changing method, comprising:
The voice operating instruction of system acceptance outside also starts recording;
System carries out automatic speech recognition, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre;
After call center receives recording, artificial cognition carried out to this recording and do corresponding process.
2. voice service changing method according to claim 1, is characterized in that, the process of call center after carrying out artificial cognition to recording comprises:
If operator attendance identification is recorded successfully, then recording marked and issue corresponding operational order;
If operator attendance identification recording failure, then connecting subscribers participating, line provides service.
3. voice service changing method according to claim 2, it is characterized in that, method also comprises:
The recording through mark that system issues according to operator attendance improves speech recognition.
4. voice service changing method according to claim 1, is characterized in that, outside voice operating instruction comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
5. voice service changing method according to claim 1, is characterized in that, the automatic speech recognition of system is the voice recognition processing of the automated voice identification engine based on this locality.
6. a voice service switched system, comprising:
Recording device, receives outside voice operating instruction and starts recording;
Automatic speech recognition device, carries out automatic speech recognition to recording, if identify successfully, the operational order according to identifying carries out system process, if recognition failures, call center service starts manual service, and recording is sent to service centre;
Call center's treating apparatus, carries out artificial cognition to this recording after call center receives recording and does corresponding process.
7. voice service switched system according to claim 6, is characterized in that, call center's treating apparatus comprises:
Artificial speech identification module, if operator attendance identification is recorded successfully, then marks recording and issues corresponding operational order;
Artificial line service module, if operator attendance identification recording failure, then connecting subscribers participating, line provides service.
8. voice service switched system according to claim 7, it is characterized in that, system also comprises:
Speech recognition modifying device, improves speech recognition according to the recording through mark that operator attendance issues.
9. voice service switched system according to claim 6, is characterized in that, outside voice operating instruction comprises listening to the music on onboard system, listen to the radio programme or guidance operation on onboard system.
10. voice service switched system according to claim 6, is characterized in that, automatic speech recognition device is the voice recognition processing of the automated voice identification engine based on this locality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310728145.9A CN104751843A (en) | 2013-12-25 | 2013-12-25 | Voice service switching method and voice service switching system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310728145.9A CN104751843A (en) | 2013-12-25 | 2013-12-25 | Voice service switching method and voice service switching system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104751843A true CN104751843A (en) | 2015-07-01 |
Family
ID=53591405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310728145.9A Pending CN104751843A (en) | 2013-12-25 | 2013-12-25 | Voice service switching method and voice service switching system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104751843A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469797A (en) * | 2015-12-31 | 2016-04-06 | 广东翼卡车联网服务有限公司 | Method and system for controlling switching-over from intelligent voice identification to manual services |
| CN106356062A (en) * | 2015-07-17 | 2017-01-25 | 深圳前海智云谷科技有限公司 | Machine intelligent recognition and manual service combined voice recognition method and system |
| CN106493747A (en) * | 2016-10-12 | 2017-03-15 | 苏州小璐机器人有限公司 | The method that intelligent robot turns manual service automatically |
| CN107305483A (en) * | 2016-04-25 | 2017-10-31 | 北京搜狗科技发展有限公司 | A kind of voice interactive method and device based on semantics recognition |
| CN107430853A (en) * | 2015-05-27 | 2017-12-01 | 谷歌公司 | Data for the voice activity with the offline ability of selectivity are held locally within the electronic installation for supporting speech |
| WO2019051805A1 (en) * | 2017-09-15 | 2019-03-21 | Bayerische Motoren Werke Aktiengesellschaft | Data processing device and method for performing speech-based human machine interaction |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| US11087762B2 (en) | 2015-05-27 | 2021-08-10 | Google Llc | Context-sensitive dynamic update of voice to text model in a voice-enabled electronic device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101847406A (en) * | 2010-05-18 | 2010-09-29 | 中国农业大学 | Speech recognition query method and system |
| CN102006373A (en) * | 2010-11-24 | 2011-04-06 | 深圳市子栋科技有限公司 | Vehicle-mounted service system and method based on voice command control |
| CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN103402028A (en) * | 2013-07-23 | 2013-11-20 | 广东欧珀移动通信有限公司 | Method and device for selecting services in service calls |
| CN103458056A (en) * | 2013-09-24 | 2013-12-18 | 贵阳世纪恒通科技有限公司 | Speech intention judging method based on automatic classification technology for automatic outbound system |
-
2013
- 2013-12-25 CN CN201310728145.9A patent/CN104751843A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101847406A (en) * | 2010-05-18 | 2010-09-29 | 中国农业大学 | Speech recognition query method and system |
| CN102006373A (en) * | 2010-11-24 | 2011-04-06 | 深圳市子栋科技有限公司 | Vehicle-mounted service system and method based on voice command control |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
| CN103402028A (en) * | 2013-07-23 | 2013-11-20 | 广东欧珀移动通信有限公司 | Method and device for selecting services in service calls |
| CN103458056A (en) * | 2013-09-24 | 2013-12-18 | 贵阳世纪恒通科技有限公司 | Speech intention judging method based on automatic classification technology for automatic outbound system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107430853A (en) * | 2015-05-27 | 2017-12-01 | 谷歌公司 | Data for the voice activity with the offline ability of selectivity are held locally within the electronic installation for supporting speech |
| US11676606B2 (en) | 2015-05-27 | 2023-06-13 | Google Llc | Context-sensitive dynamic update of voice to text model in a voice-enabled electronic device |
| US11087762B2 (en) | 2015-05-27 | 2021-08-10 | Google Llc | Context-sensitive dynamic update of voice to text model in a voice-enabled electronic device |
| US10986214B2 (en) | 2015-05-27 | 2021-04-20 | Google Llc | Local persisting of data for selectively offline capable voice action in a voice-enabled electronic device |
| CN107430853B (en) * | 2015-05-27 | 2020-11-03 | 谷歌有限责任公司 | Locally saving data for voice actions with selective offline capability in a voice-enabled electronic device |
| CN106356062A (en) * | 2015-07-17 | 2017-01-25 | 深圳前海智云谷科技有限公司 | Machine intelligent recognition and manual service combined voice recognition method and system |
| CN105469797A (en) * | 2015-12-31 | 2016-04-06 | 广东翼卡车联网服务有限公司 | Method and system for controlling switching-over from intelligent voice identification to manual services |
| CN107305483A (en) * | 2016-04-25 | 2017-10-31 | 北京搜狗科技发展有限公司 | A kind of voice interactive method and device based on semantics recognition |
| CN106493747A (en) * | 2016-10-12 | 2017-03-15 | 苏州小璐机器人有限公司 | The method that intelligent robot turns manual service automatically |
| EP3682213A4 (en) * | 2017-09-15 | 2021-04-07 | Bayerische Motoren Werke Aktiengesellschaft | Data processing device and method for performing speech-based human machine interaction |
| CN111094924A (en) * | 2017-09-15 | 2020-05-01 | 宝马股份公司 | Data processing apparatus and method for performing voice-based human-machine interaction |
| WO2019051805A1 (en) * | 2017-09-15 | 2019-03-21 | Bayerische Motoren Werke Aktiengesellschaft | Data processing device and method for performing speech-based human machine interaction |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| CN109981910B (en) * | 2019-02-22 | 2021-08-10 | 中国联合网络通信集团有限公司 | Service recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751843A (en) | Voice service switching method and voice service switching system | |
| US10380992B2 (en) | Natural language generation based on user speech style | |
| US7783028B2 (en) | System and method of using speech recognition at call centers to improve their efficiency and customer satisfaction | |
| CN102006373B (en) | Vehicle-mounted service system and method based on voice command control | |
| CN106816149A (en) | The priorization content loading of vehicle automatic speech recognition system | |
| CN103187077B (en) | Vehicle-mounted equipment, and audio control method and device applied to vehicle-mounted equipment | |
| CN105869626A (en) | Automatic speech rate adjusting method and terminal | |
| CN105744090A (en) | Voice information processing method and device | |
| CN108777751A (en) | A kind of call center system and its voice interactive method, device and equipment | |
| CN102693725A (en) | Speech recognition dependent on text message content | |
| CN105390136A (en) | Vehicle control device and method used for user-adaptable service | |
| CN103177721A (en) | Voice recognition method and system | |
| CN105225665A (en) | A kind of audio recognition method and speech recognition equipment | |
| CN107093427A (en) | The automatic speech recognition of not smooth language | |
| US20200211560A1 (en) | Data Processing Device and Method for Performing Speech-Based Human Machine Interaction | |
| CN103634480A (en) | Method and device for communication in mobile communication terminal | |
| CN111354363A (en) | Vehicle-mounted voice recognition method and device, readable storage medium and electronic equipment | |
| CN105357295A (en) | Voice interaction method, device and system | |
| CN105577943A (en) | Bus stop reporting prompting method and system and mobile terminal | |
| CN105282332A (en) | Voice dialing method and device | |
| CN104655146A (en) | Method and system for navigation or communication in vehicle | |
| CN106981289A (en) | A kind of identification model training method and system and intelligent terminal | |
| CN109360565A (en) | A method of precision of identifying speech is improved by establishing resources bank | |
| CN106887231A (en) | A kind of identification model update method and system and intelligent terminal | |
| CN104064184B (en) | The construction method of isomery decoding network and system, audio recognition method and system |
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 |
Application publication date: 20150701 |
|
| RJ01 | Rejection of invention patent application after publication |