CN105185375B - A kind of information processing method and electronic equipment - Google Patents
A kind of information processing method and electronic equipment Download PDFInfo
- Publication number
- CN105185375B CN105185375B CN201510486189.4A CN201510486189A CN105185375B CN 105185375 B CN105185375 B CN 105185375B CN 201510486189 A CN201510486189 A CN 201510486189A CN 105185375 B CN105185375 B CN 105185375B
- Authority
- CN
- China
- Prior art keywords
- languages
- identification module
- identification
- speech recognition
- voice data
- 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.)
- Active
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of information processing method and electronic equipments, wherein the information processing method includes: acquisition voice data；The voice data is sent to the first identification module and at least two second identification modules simultaneously, wherein, first identification module is for identifying languages, second identification module is used to carry out voice content identification to the voice of corresponding languages, and different second identification modules corresponds to different languages；It controls first identification module and languages identification is carried out according to the voice data, obtain the corresponding languages of the voice data；Meanwhile each second identification module of control carries out speech recognition to the voice data respectively, obtains multiple speech recognition results；Determine the second identification module corresponding to the corresponding languages of the voice data；The speech recognition result that second identification module determined by exporting obtains.
Description
Technical field
The present invention relates to the communication technology more particularly to a kind of information processing methods and electronic equipment.
Background technique
Currently become normality across communication, service of electronic equipment such as customer service, translation etc. is frequently necessary to towards multi-lingual
Kind, and often unknown other side's languages the case where.Under unknown multilingual situation, existing solution includes:
1, preset multiple signal languages in the electronic device, content is identical but languages are different, by plaing in order multiple languages
The prompt tone of kind (such as mandarin, English, French) prompts the other user's manual key to select languages, to be able to confirmation language
Plant and start the speech recognition of corresponding languages.But the process tedious of the prompt tone of multiple languages is playd in order, it is unable to reach fast
The requirement of victory identification.Moreover, this method can not judge whether languages change, when languages change, still according to
Languages before, which carry out speech recognition, will lead to identification mistake, therefore, the case where this method is not suitable for languages switching at runtime,
The transnational meeting scene that such as languages may convert.
2, after first identifying that the languages of user, completion languages identify and confirm result, corresponding languages are started to subsequent voice
Speech recognition.But it first carries out languages and identifies that carrying out speech recognition again will lead to speech recognition delay obviously, be unable to satisfy voice
The real-time demand of identification.
Therefore, quickly judge that the speech recognition that simultaneously real-time perfoming corresponds to languages of other side's languages becomes the urgent demand of user.
Summary of the invention
In view of this, to solve technical problem of the existing technology, the embodiment of the present invention provides a kind of information processing side
Method and electronic equipment.
The embodiment of the present invention provides a kind of information processing method, and the information processing method includes:
Obtain voice data；
The voice data is sent to the first identification module and at least two second identification modules simultaneously, wherein described
For identifying to languages, second identification module is used to carry out in voice the voice of corresponding languages first identification module
Hold identification, different second identification modules corresponds to different languages；
It controls first identification module and languages identification is carried out according to the voice data, it is corresponding to obtain the voice data
Languages；Meanwhile
It controls each second identification module and speech recognition is carried out to the voice data respectively, obtain multiple speech recognitions
As a result；
Determine the second identification module corresponding to the corresponding languages of the voice data；
The speech recognition result that second identification module determined by exporting obtains.
Wherein, the method also includes:
It controls first identification module and stops languages identification, and control cannot identify that the voice data corresponds to languages
The second identification module stop speech recognition.
Wherein, the method also includes:
Control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
Wherein, the method also includes:
Detect whether the languages identified change；
When languages change, it is determined to the second identification module of languages after identification change；
Second identification module determined after control change restores speech recognition；
The speech recognition result that second identification module determined after output change obtains.
Wherein, the method also includes:
In preset time interval, there is no second identifications that when change, control determines before changing for languages
Module stops speech recognition.
Wherein, the method also includes:
Control restores the second identification module of speech recognition according to the time parameter of the voice data received, determination need into
The voice data of row speech recognition；
It is described that need the voice data for carrying out speech recognition include receiving in preset time period before restoring speech recognition
Voice data.
The embodiment of the present invention provides a kind of electronic equipment, and the electronic equipment includes the first identification module and at least two the
Two identification modules, wherein for identifying to languages, second identification module is used for corresponding first identification module
The voice of languages carries out voice content identification, and different second identification modules corresponds to different languages, the electronic equipment
It further include processing unit；
The processing unit, for obtaining voice data；
The voice data is sent to first identification module and at least two second identification modules simultaneously；
It controls first identification module and languages identification is carried out according to the voice data, it is corresponding to obtain the voice data
Languages；Meanwhile
It controls each second identification module and speech recognition is carried out to the voice data respectively, obtain multiple speech recognitions
As a result；
Determine the second identification module corresponding to the corresponding languages of the voice data；
The speech recognition result that second identification module determined by exporting obtains.
Wherein, the processing unit is also used to control first identification module and stops languages identification, and controlling cannot
The second identification module that identification voice data corresponds to languages stops speech recognition.
Wherein, the processing unit, being also used to control cannot identify that the voice data corresponds to the second identification mould of languages
Block stops speech recognition.
Wherein, the processing unit is also used to detect whether the languages identified change；
When languages change, it is determined to the second identification module of languages after identification change；
Second identification module determined after control change restores speech recognition；
The speech recognition result that second identification module determined after output change obtains.
Wherein, the processing unit is also used in preset time interval, and there is no controlling when change for languages
Second identification module determined before changing stops speech recognition.
Wherein, the processing unit is also used to control the second identification module for restoring speech recognition according to the voice received
The time parameter of data determines the voice data for needing to carry out speech recognition；
It is described that need the voice data for carrying out speech recognition include receiving in preset time period before restoring speech recognition
Voice data.
From the foregoing, it will be observed that technical solution provided in an embodiment of the present invention includes: acquisition voice data；The voice data is same
When be sent to the first identification module and at least two second identification modules, wherein first identification module be used for languages into
Row identification, second identification module are used to carry out the voice of corresponding languages voice content identification, and different described second knows
Other module corresponds to different languages；It controls first identification module and languages identification is carried out according to the voice data, obtain institute
State the corresponding languages of voice data；Meanwhile each second identification module of control carries out voice knowledge to the voice data respectively
Not, multiple speech recognition results are obtained；Determine the second identification module corresponding to the corresponding languages of the voice data；Output institute
The speech recognition result that the second determining identification module obtains.First identification module and at least two second in the embodiment of the present invention
Identification module concurrent working simultaneously, as a result, the embodiment of the present invention can fast, identify languages and voice in real time, and be applicable in
In the languages switching at runtime the case where.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the first embodiment of information processing method provided by the invention；
Fig. 2 is a kind of flow diagram of the second embodiment of information processing method provided by the invention；
Fig. 3 is a kind of flow diagram of the 3rd embodiment of information processing method provided by the invention；
Fig. 4 is a kind of flow diagram of the fourth embodiment of information processing method provided by the invention；
Fig. 5 is a kind of flow diagram of 5th embodiment of information processing method provided by the invention；
Fig. 6 is a kind of flow diagram of the sixth embodiment of information processing method provided by the invention；
Fig. 7 is the structural schematic diagram of the first embodiment of a kind of electronic equipment provided by the invention；
Fig. 8 is the workflow schematic diagram of a kind of electronic equipment provided by the invention.
Specific embodiment
The technical solution of the present invention is further elaborated in the following with reference to the drawings and specific embodiments.
The first embodiment of a kind of information processing method provided by the invention, as shown in Figure 1, the information processing method packet
It includes:
Step 101 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 102 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Specifically, the languages may include English, French, Spanish, Chinese etc.；The second identification module having can be right
English is identified that the second identification module having can identify French, second identification module having etc. to Spanish into
Row identification, the second identification module having the Chinese such as can identify.
Here, it should be noted that hereinafter, first identification module is also referred to as languages identification module, and described
Two identification modules are also referred to as speech recognition module.
Step 103, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；
Step 104, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 105 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 106 exports the speech recognition result that identified second identification module obtains.
Here, the step 103 and step 104 carry out simultaneously.
Languages identification and multilingual speech recognition process parallelization in the embodiment of the present invention, in the identification of real-time perfoming languages
Meanwhile the parallel multilingual voice content identification supported.It is anti-to user immediately when languages are judged in languages identification
Present the speech recognition result of corresponding languages.Languages judgement and voice content identification under multilingual situation to reach near real-time
Effect.
The second embodiment of a kind of information processing method provided by the invention, as shown in Fig. 2, the information processing method packet
It includes:
Step 201 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 202 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Step 203, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；
Step 204, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 205 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 206 exports the speech recognition result that identified second identification module obtains.
Step 207, control first identification module stop languages identification, and control cannot identify the voice data
Second identification module of corresponding languages stops speech recognition.
Here, step 203 and step 204 carry out simultaneously.
In practical applications, when the corresponding languages of voice data do not change, for example, when being in intercommunication state, it can
Stop languages identification to control first identification module, and control cannot identify that the voice data corresponds to the second of languages
Identification module stops speech recognition.This way it is possible to avoid unnecessary processing, to save resource.
The 3rd embodiment of a kind of information processing method provided by the invention, as shown in figure 3, the information processing method packet
It includes:
Step 301 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 302 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Step 303, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；
Step 304, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 305 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 306 exports the speech recognition result that identified second identification module obtains.
Step 307, control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
Here, step 303 and step 304 carry out simultaneously.
In practical applications, when the corresponding languages of voice data can change, for example, when being in multi-party communication state, it can
It cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages to control, keep the first identification module
It works normally, the voice of the languages in this way, can not only save resource, but also after being changed in time when languages change is known
Not.
The fourth embodiment of a kind of information processing method provided by the invention, as shown in figure 4, the information processing method packet
It includes:
Step 401 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 402 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Step 403, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；
Step 404, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 405 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 406 exports the speech recognition result that identified second identification module obtains.
Step 407, control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
Whether the languages that step 408, detection identify change；
Step 409, when languages change, be determined to identification change after languages the second identification module；
Second identification module determined after step 410, control change restores speech recognition；
The speech recognition result that second identification module determined after step 411, output change obtains.
Here, step 403 and step 404 carry out simultaneously.
In practical applications, it can be changed with timely learning languages, thus the second identification module of replacement.In this way, in the presence of
Languages can be with the voice content recognition result after the current languages of real-time judge and the switching of Real-time Feedback languages in the case where switching.
5th embodiment of a kind of information processing method provided by the invention, as shown in figure 5, the information processing method packet
It includes:
Step 501 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 502 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Step 503, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；Meanwhile
Step 504, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 505 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 506 exports the speech recognition result that identified second identification module obtains.
Step 507, control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
Whether the languages that step 508, detection identify change；
Step 509, when languages change, be determined to identification change after languages the second identification module；
Second identification module determined after step 510, control change restores speech recognition；
The speech recognition result that second identification module determined after step 511, output change obtains.
Step 512, in preset time interval, languages there is no change when, control before changing determine it is described
Second identification module stops speech recognition.
Here, step 503 and step 504 carry out simultaneously.
In practical applications, there are languages switching in the case where, in preset time interval, languages there is no
When change, second identification module determined before changing is controlled at this time and stops speech recognition, can save resource.
The sixth embodiment of a kind of information processing method provided by the invention, as shown in fig. 6, the information processing method packet
It includes:
Step 601 obtains voice data；
The voice data is sent to the first identification module and at least two second identification modules by step 602 simultaneously；
Wherein, for identifying to languages, second identification module is used for corresponding language first identification module
The voice of kind carries out voice content identification, and different second identification modules corresponds to different languages；
Step 603, control first identification module carry out languages identification according to the voice data, obtain the voice
The corresponding languages of data；
Step 604, each second identification module of control carry out speech recognition to the voice data respectively, obtain multiple
Speech recognition result；
Step 605 determines the second identification module corresponding to the corresponding languages of the voice data；
Step 606 exports the speech recognition result that identified second identification module obtains.
Step 607, control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
Whether the languages that step 608, detection identify change；
Step 609, when languages change, be determined to identification change after languages the second identification module；
Second identification module determined after step 610, control change restores speech recognition；
Step 611, control restore the second identification module of speech recognition according to the time parameter of the voice data received, really
Surely need to carry out the voice data of speech recognition；
Here, the voice data for needing to carry out speech recognition includes receiving in preset time period before restoring speech recognition
The voice data arrived.
The speech recognition result that second identification module determined after step 612, output change obtains.
Here, step 603 and step 604 carry out simultaneously.
In practical applications, there are languages switching in the case where, control restore speech recognition the second identification module according to
The time parameter of the voice data received determines the voice data for needing to carry out speech recognition.In this manner it is ensured that after change
The result that second identification module identifies is continuous, does not lack.
Information processing mainly includes that voice data receives and distributes, real-time languages identify, more in real time in the embodiment of the present invention
The Four processes such as the identification of languages voice content, recognition result feedback.
Technology in the embodiment of the present invention realizes that main points include:
After voice data receives, it need to be distributed to languages identification module and speech recognition module simultaneously.
Languages identification and speech recognition process concurrently carry out simultaneously, and while starting languages identify, starting is supported complete
Portion's speech recognition.
Preset supported languages, such as support mandarin, English and French totally 3 languages, then system is equipped with mandarin
3 speech recognition modules such as speech recognition, English Phonetics identification and French speech recognition.
When languages unconfirmed, multiple speech recognition modules start simultaneously at and the voice of the parallel respective languages of progress
Identification process.
Result, that is, voice content of the speech recognition of corresponding languages is fed back after languages recognition and verification languages.
In the case where languages identification module confirms current languages, system can be configured to stop or do not stop language as needed
Kind identification module.Do not stop languages identification module will meet there may be the real-time demands of the scene of languages switching at runtime, such as
Transnational meeting.
In the case where languages identification module confirms current languages, system can be configured to stop or do not stop non-as needed
The speech recognition module of current languages.Do not stop languages identification module will meet there may be the realities of the scene of languages switching at runtime
When property demand, such as transnational meeting.
From the foregoing, it will be observed that technical solution provided in an embodiment of the present invention has the advantage that 1, without the language of additional redundancy
Kind selection interactive process.It 2, can be with real-time judge languages and Real-time Feedback voice content recognition result in the case where unknown languages.
It 3, can be with the voice content identification after the current languages of real-time judge and the switching of Real-time Feedback languages in the case where switching there are languages
As a result.
The first embodiment of a kind of electronic equipment provided by the invention, as shown in fig. 7, the electronic equipment includes the first knowledge
Other module 701 and at least two second identification modules 702, wherein first identification module 701 is for knowing languages
Not, second identification module 702 is used to carry out the voice of corresponding languages voice content identification, different second identification
The corresponding different languages of module 702, the electronic equipment further includes processing unit 703；
The processing unit 703, for obtaining voice data；
The voice data is sent to first identification module and at least two second identification modules simultaneously；
It controls first identification module and languages identification is carried out according to the voice data, it is corresponding to obtain the voice data
Languages；Meanwhile
It controls each second identification module and speech recognition is carried out to the voice data respectively, obtain multiple speech recognitions
As a result；
Determine the second identification module corresponding to the corresponding languages of the voice data；
The speech recognition result that second identification module determined by exporting obtains.
Specifically, the languages may include English, French, Spanish, Chinese etc.；The second identification module having can be right
English is identified that the second identification module having can identify French, second identification module having etc. to Spanish into
Row identification, the second identification module having the Chinese such as can identify.
Languages identification and multilingual speech recognition process parallelization in the embodiment of the present invention, in the identification of real-time perfoming languages
Meanwhile the parallel multilingual voice content identification supported.It is anti-to user immediately when languages are judged in languages identification
Present the speech recognition result of corresponding languages.Languages judgement and voice content identification under multilingual situation to reach near real-time
Effect.
The present invention can under unknown languages situation real-time perfoming languages identification and speech recognition, with seamless interactive experience
Mode provides real-time interactive service or real time translation service.
In one embodiment, the processing unit 703 is also used to control first identification module and stops languages identification,
And controlling cannot identify that voice data corresponds to the second identification module stopping speech recognition of languages.
In practical applications, when the corresponding languages of voice data do not change, for example, when being in intercommunication state, it can
Stop languages identification to control first identification module, and control cannot identify that the voice data corresponds to the second of languages
Identification module stops speech recognition.This way it is possible to avoid unnecessary processing, to save resource.
In one embodiment, the processing unit 703, being also used to control cannot identify that the voice data corresponds to languages
Second identification module stops speech recognition.
In practical applications, when the corresponding languages of voice data can change, for example, when being in multi-party communication state, it can
It cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages to control, keep the first identification module
It works normally, the voice of the languages in this way, can not only save resource, but also after being changed in time when languages change is known
Not.
In one embodiment, the processing unit 703 is also used to detect whether the languages identified change；
When languages change, it is determined to the second identification module of languages after identification change；
Second identification module determined after control change restores speech recognition；
The speech recognition result that second identification module determined after output change obtains.
In practical applications, it can be changed with timely learning languages, thus the second identification module of replacement.In this way, in the presence of
Languages can be with the voice content recognition result after the current languages of real-time judge and the switching of Real-time Feedback languages in the case where switching.
In one embodiment, the processing unit 703 is also used to when in preset time interval, languages there is no
When change, second identification module that control determines before changing stops speech recognition.
In practical applications, there are languages switching in the case where, in preset time interval, languages there is no
When change, second identification module determined before changing is controlled at this time and stops speech recognition, can save resource.
In one embodiment, the processing unit 703, be also used to control restore speech recognition the second identification module according to
The time parameter of the voice data received determines the voice data for needing to carry out speech recognition；
It is described that need the voice data for carrying out speech recognition include receiving in preset time period before restoring speech recognition
Voice data.
In practical applications, there are languages switching in the case where, control restore speech recognition the second identification module according to
The time parameter of the voice data received determines the voice data for needing to carry out speech recognition.In this manner it is ensured that after change
The result that second identification module identifies is continuous, does not lack.
In practical application, the processing unit 703 can be by central processing unit (CPU, the Central in electronic equipment
Processing Unit), digital signal processor (DSP, Digital Signal Processor) or field programmable gate
Array (FPGA, Field-Programmable Gate Array) is realized.
Shown in Figure 8, the workflow of electronic equipment provided in an embodiment of the present invention is as follows:
Voice data reception starts；
Start languages identification module, starts the whole speech recognition modules supported；
Whole speech recognition modules that the voice data received is distributed to languages identification module respectively and is supported；
Languages identification module carries out the identification of languages based on the voice data of input；
Meanwhile the speech recognition module of each preset languages carries out voice content identification based on the voice data of input.It is more
A speech recognition module concurrent working；
Languages identification module judges current languages；
The speech recognition module of current languages works on, and Real-time Feedback its voice content recognition result.
In conclusion technical solution provided in an embodiment of the present invention has the advantage that 1, without the language of additional redundancy
Kind selection interactive process.It 2, can be with real-time judge languages and Real-time Feedback voice content recognition result in the case where unknown languages.
It 3, can be with the voice content identification after the current languages of real-time judge and the switching of Real-time Feedback languages in the case where switching there are languages
As a result.
In several embodiments provided by the present invention, it should be understood that disclosed method, apparatus and electronic equipment,
It may be implemented in other ways.Apparatus embodiments described above are merely indicative, for example, the unit is drawn
Point, only a kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can
To combine, or it is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed
The mutual coupling of each component part or direct-coupling or communication connection can be through some interfaces, equipment or unit
Indirect coupling or communication connection can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit
The component shown can be or may not be physical unit, both can be located in one place, and may be distributed over multiple network lists
In member；Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated in one processing unit, it can also
To be each unit individually as a unit, can also be integrated in one unit with two or more units；It is above-mentioned
Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can store in computer-readable storage medium, which exists
When execution, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes: movable storage device, read-only deposits
Reservoir (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or
The various media that can store program code such as CD.
If alternatively, the above-mentioned integrated unit of the embodiment of the present invention is realized in the form of software function module and as independence
Product when selling or using, also can store in a computer readable storage medium.Based on this understanding, this hair
Substantially the part that contributes to existing technology can body in the form of software products in other words for the technical solution of bright embodiment
Reveal and, which is stored in a storage medium, including some instructions are with so that a computer is set
Standby (can be personal computer, server or network equipment etc.) executes the whole of each embodiment the method for the present invention
Or part.And storage medium above-mentioned include: movable storage device, read-only memory (ROM, Read-Only Memory), with
Machine accesses various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (12)
1. a kind of information processing method, the information processing method include:
Obtain voice data；
The voice data is sent to the first identification module and at least two second identification modules simultaneously, wherein described first
For identifying to languages, second identification module is used to carry out voice content knowledge to the voice of corresponding languages identification module
Not, different second identification modules corresponds to different languages；
It controls first identification module and languages identification is carried out according to the voice data, obtain the corresponding language of the voice data
Kind；Meanwhile
It controls each second identification module and speech recognition is carried out to the voice data respectively, obtain multiple speech recognition knots
Fruit；
Determine the second identification module corresponding to the corresponding languages of the voice data；
The speech recognition result that second identification module determined by exporting obtains.
2. information processing method according to claim 1, which is characterized in that the method also includes:
It controls first identification module and stops languages identification, and control and cannot identify that the voice data corresponds to the of languages
Two identification modules stop speech recognition.
3. information processing method according to claim 1, which is characterized in that the method also includes:
Control cannot identify that the voice data corresponds to the second identification module stopping speech recognition of languages.
4. information processing method according to claim 3, which is characterized in that the method also includes:
Detect whether the languages identified change；
When languages change, it is determined to the second identification module of languages after identification change；
Second identification module determined after control change restores speech recognition；
The speech recognition result that second identification module determined after output change obtains.
5. information processing method according to claim 4, which is characterized in that the method also includes:
In preset time interval, there is no second identification modules that when change, control determines before changing for languages
Stop speech recognition.
6. information processing method according to claim 4, which is characterized in that the method also includes:
Control restores the second identification module of speech recognition according to the time parameter of the voice data received, and determination needs to carry out language
The voice data of sound identification；
It is described that need the voice data for carrying out speech recognition include the voice received in preset time period before restoring speech recognition
Data.
7. a kind of electronic equipment, which is characterized in that the electronic equipment includes the first identification module and at least two second identifications
Module, wherein for identifying to languages, second identification module is used for corresponding languages first identification module
Voice carries out voice content identification, and different second identification modules corresponds to different languages, and the electronic equipment further includes
Processing unit；
The processing unit, for obtaining voice data；
The voice data is sent to first identification module and at least two second identification modules simultaneously；
It controls first identification module and languages identification is carried out according to the voice data, obtain the corresponding language of the voice data
Kind；Meanwhile
It controls each second identification module and speech recognition is carried out to the voice data respectively, obtain multiple speech recognition knots
Fruit；
Determine the second identification module corresponding to the corresponding languages of the voice data；
The speech recognition result that second identification module determined by exporting obtains.
8. electronic equipment according to claim 7, which is characterized in that the processing unit is also used to control described first
Identification module stops languages identification, and control cannot identify that voice data corresponds to the second identification module stopping voice knowledge of languages
Not.
9. electronic equipment according to claim 7, which is characterized in that the processing unit, being also used to control cannot identify
The second identification module that the voice data corresponds to languages stops speech recognition.
10. electronic equipment according to claim 9, which is characterized in that the processing unit is also used to what detection identified
Whether languages change；
When languages change, it is determined to the second identification module of languages after identification change；
Second identification module determined after control change restores speech recognition；
The speech recognition result that second identification module determined after output change obtains.
11. electronic equipment according to claim 10, which is characterized in that the processing unit is also used to when preset
In time interval, there is no when change, second identification module that control determines before changing stops speech recognition for languages.
12. electronic equipment according to claim 10, which is characterized in that the processing unit is also used to control recovery language
Second identification module of sound identification determines the voice number for needing to carry out speech recognition according to the time parameter of the voice data received
According to；
It is described that need the voice data for carrying out speech recognition include the voice received in preset time period before restoring speech recognition
Data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510486189.4A CN105185375B (en) | 2015-08-10 | 2015-08-10 | A kind of information processing method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510486189.4A CN105185375B (en) | 2015-08-10 | 2015-08-10 | A kind of information processing method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105185375A CN105185375A (en) | 2015-12-23 |
| CN105185375B true CN105185375B (en) | 2019-03-08 |
Family
ID=54907403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510486189.4A Active CN105185375B (en) | 2015-08-10 | 2015-08-10 | A kind of information processing method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105185375B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105895088A (en) * | 2016-05-27 | 2016-08-24 | 京东方科技集团股份有限公司 | Intelligent wearable device and voice error correction system |
| CN107545887A (en) * | 2016-06-24 | 2018-01-05 | 中兴通讯股份有限公司 | Phonetic order processing method and processing device |
| CN107995376A (en) * | 2017-11-07 | 2018-05-04 | 平安科技（深圳）有限公司 | A kind of user reports a case to the security authorities processing method and terminal device |
| CN109285563B (en) * | 2018-10-15 | 2022-05-06 | 华为技术有限公司 | Voice data processing method and device in online translation process |
| CN109243458A (en) * | 2018-11-22 | 2019-01-18 | 苏州米机器人有限公司 | A kind of speech recognition system for intelligent robot |
| CN110111770A (en) * | 2019-05-10 | 2019-08-09 | 濮阳市顶峰网络科技有限公司 | A kind of multilingual social interpretation method of network, system, equipment and medium |
| CN110503938A (en) * | 2019-08-30 | 2019-11-26 | 北京太极华保科技股份有限公司 | The recognition methods of machine conversational language and device, identification engine switching method and device |
| CN115376490A (en) * | 2022-08-19 | 2022-11-22 | 北京字跳网络技术有限公司 | Voice recognition method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1598924A (en) * | 2003-08-11 | 2005-03-23 | 索尼电子有限公司 | System and method for performing speech recognition by utilizing a multi-language dictionary |
| CN103164397A (en) * | 2011-12-19 | 2013-06-19 | 新疆信息产业有限责任公司 | Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof |
| CN104143329A (en) * | 2013-08-19 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and device for conducting voice keyword search |
| CN104391673A (en) * | 2014-11-20 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Voice interaction method and voice interaction device |
| CN104640323A (en) * | 2015-02-12 | 2015-05-20 | 上海欧美拉光电股份有限公司 | Voice control system of LED (Light Emitting Diode) lamp |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI224771B (en) * | 2003-04-10 | 2004-12-01 | Delta Electronics Inc | Speech recognition device and method using di-phone model to realize the mixed-multi-lingual global phoneme |
| US7689404B2 (en) * | 2004-02-24 | 2010-03-30 | Arkady Khasin | Method of multilingual speech recognition by reduction to single-language recognizer engine components |
| US20050197837A1 (en) * | 2004-03-08 | 2005-09-08 | Janne Suontausta | Enhanced multilingual speech recognition system |
| US20150006147A1 (en) * | 2013-07-01 | 2015-01-01 | Toyota Motor Engineering & Manufacturing North America, Inc. | Speech Recognition Systems Having Diverse Language Support |
-
2015
- 2015-08-10 CN CN201510486189.4A patent/CN105185375B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1598924A (en) * | 2003-08-11 | 2005-03-23 | 索尼电子有限公司 | System and method for performing speech recognition by utilizing a multi-language dictionary |
| CN103164397A (en) * | 2011-12-19 | 2013-06-19 | 新疆信息产业有限责任公司 | Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof |
| CN104143329A (en) * | 2013-08-19 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and device for conducting voice keyword search |
| CN104391673A (en) * | 2014-11-20 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Voice interaction method and voice interaction device |
| CN104640323A (en) * | 2015-02-12 | 2015-05-20 | 上海欧美拉光电股份有限公司 | Voice control system of LED (Light Emitting Diode) lamp |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105185375A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105185375B (en) | A kind of information processing method and electronic equipment | |
| US10089300B2 (en) | Apparatus and method for amending language analysis error | |
| KR101821358B1 (en) | Method and system for providing multi-user messenger service | |
| CN107180632A (en) | Sound control method, device and readable storage medium storing program for executing | |
| US10601740B1 (en) | Chatbot artificial intelligence | |
| CN106997762A (en) | The sound control method and device of household electrical appliance | |
| KR20200021162A (en) | System and method for learning counseling chatter robot based on counceling contents of counselor | |
| US8509396B2 (en) | Automatic creation of complex conversational natural language call routing system for call centers | |
| CN108306804A (en) | A kind of Ethercat main station controllers and its communication means and system | |
| EP3107089B1 (en) | Speech recognition on board of an aircraft | |
| CN103853703A (en) | Information processing method and electronic equipment | |
| CN110704590B (en) | Method and apparatus for augmenting training samples | |
| CN113840040B (en) | Man-machine cooperation outbound method, device, equipment and storage medium | |
| CN106293920A (en) | Method for scheduling task and device | |
| CN105227557A (en) | A kind of account number processing method and device | |
| CN107633844A (en) | Apparatus control method and device | |
| CN107748720A (en) | A kind of method and device of the service parameter of detection function test cases | |
| US10572220B2 (en) | Method for controlling controller and host computer with voice | |
| CN107967363B (en) | Data processing method and device and electronic equipment | |
| CN112002325B (en) | Multi-language voice interaction method and device | |
| CN110047486A (en) | Sound control method, device, server, system and storage medium | |
| CN111737442B (en) | Intelligent customer service multi-round session management method and device | |
| CN111400475A (en) | Information processing method and device and electronic equipment | |
| US9858918B2 (en) | Root cause analysis and recovery systems and methods | |
| CN110543556A (en) | Dialogue configuration method, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |