CN106228974A - Control method based on speech recognition, Apparatus and system - Google Patents
Control method based on speech recognition, Apparatus and system Download PDFInfo
- Publication number
- CN106228974A CN106228974A CN201610700858.8A CN201610700858A CN106228974A CN 106228974 A CN106228974 A CN 106228974A CN 201610700858 A CN201610700858 A CN 201610700858A CN 106228974 A CN106228974 A CN 106228974A
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- identified
- speech
- speech data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 12
- 230000008878 coupling Effects 0.000 claims abstract description 11
- 238000010168 coupling process Methods 0.000 claims abstract description 11
- 238000005859 coupling reaction Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 5
- 241001672694 Citrus reticulata Species 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Telephonic Communication Services (AREA)
Abstract
A kind of control method based on speech recognition, Apparatus and system, control method based on speech recognition includes: obtain speech data to be identified from source device;Determine the language form of described speech data to be identified, and choose the speech recognition server of coupling according to described language form;Sending described speech data to be identified to selected speech recognition server, described speech recognition server is in order to process described speech data to be identified, to be identified result;Receiving the recognition result of described speech recognition server feedback, described recognition result is converted to executable operational order, and send described operational order to target device, described operational order is used for controlling described target device.The embodiment of the present invention achieves user and uses convenience and the high efficiency of speech recognition.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to a kind of control method based on speech recognition, device and
System.
Background technology
Along with the development of speech recognition technology, the field that speech recognition is supported constantly is expanding, speech recognition accurate
Degree is also constantly improving.Speech recognition at present can achieve the identification close to 80% to the standard pronunciation of world languages
Various dialects are identified that the growth also with data base is constantly increasing by rate.Simultaneously because the maturation of speech recognition technology,
And the reduction of speech recognition cost, use the potential field of speech recognition to get more and more, what increasing field used sets
For all beginning to use speech recognition as the interface of man-machine interaction.
In prior art, speech recognition is broadly divided into two ways, and a kind of mode is for being provided clothes by speech-recognition services business
Business, the data form being met Carrier Requirements by the service submission buying service provider realizes speech recognition;Another kind side
Formula is to use special voice recognition chip to realize speech recognition.
But, in the voice recognition mode of prior art, first kind of way needs certain exploitation for a user
Work and corresponding technology requirement;Second way hardware cost is higher, and identify be limited in scope.
Summary of the invention
Present invention solves the technical problem that it is how to improve user to use convenience and the high efficiency of speech recognition.
For solving above-mentioned technical problem, the embodiment of the present invention provides a kind of control method based on speech recognition, based on language
The control method of sound identification includes:
Speech data to be identified is obtained from source device;Determine the language form of described speech data to be identified, and according to
Described language form chooses the speech recognition server of coupling;Described speech data to be identified is sent to selected speech recognition
Server, described speech recognition server is in order to process described speech data to be identified, to be identified result;Receive
The recognition result of described speech recognition server feedback, is converted to executable operational order by described recognition result, and sends
Described operational order is to target device, and described operational order is used for controlling described target device.
Optionally, described control method based on speech recognition also includes: cannot respond to described behaviour at described target device
When instructing, described speech data to be identified is forwarded to manual service platform.
Optionally, described acquisition before speech data to be identified from source device also includes: to described source device and institute
State target device and carry out P2P address registration.
Optionally, obtain described speech data to be identified and the described operational order of transmission is grasped by P2P communication modes
Make.
Optionally, the described language form determining described speech data to be identified includes: according to described voice number to be identified
According to the geographical position of described source device determine language mode to be selected;Utilize described language mode to be selected to described language to be identified
Sound data are mated, to determine described language form.
Optionally, described transmission by described speech data to be identified to selected speech recognition server includes: by described
Speech data to be identified is converted into the audio file with preset format;The audio file with preset format is sent to selected
Speech recognition server, described audio file includes the recognition mode of described source device.
For solving above-mentioned technical problem, the embodiment of the invention also discloses a kind of control device based on speech recognition, base
Control device in speech recognition includes:
Acquiring unit, is suitable to obtain speech data to be identified from source device;Matching unit, is adapted to determine that described to be identified
The language form of speech data, and the speech recognition server of coupling is chosen according to described language form;Transmitting element, be suitable to by
Described speech data to be identified sends to selected speech recognition server, and described speech recognition server is in order to know described waiting
Other speech data processes, to be identified result;Control unit, is suitable to receive the knowledge of described speech recognition server feedback
Other result, is converted to executable operational order by described recognition result, and sends described operational order to target device, described
Operational order is used for controlling described target device.
Optionally, described control device based on speech recognition also includes: retransmission unit, be suitable to described target device without
When method responds described operational order, described speech data to be identified is forwarded to manual service platform.
Optionally, described control device based on speech recognition also includes: address registration unit, is suitable to set described source
Standby and described target device carries out P2P address registration.
Optionally, obtain described speech data to be identified and the described operational order of transmission is grasped by P2P communication modes
Make.
Optionally, described matching unit includes: speech pattern determines subelement, is suitable to according to described speech data to be identified
The geographical position of described source device determine language mode to be selected;Sound-type determines subelement, is suitable to utilize described to be selected
Described speech data to be identified is mated by language mode, to determine described language form.
Optionally, described transmitting element includes: format conversion subelement, is suitable to be converted into described speech data to be identified
There is the audio file of preset format;Send subelement, be suitable to send to selected language the audio file with preset format
Sound identification server, described audio file includes the recognition mode of described source device.
The embodiment of the invention also discloses a kind of control system based on speech recognition, control system based on speech recognition
Including:
Control device based on speech recognition;At least one speech recognition server.
Optionally, described control system based on speech recognition also includes: P2P client server, in order to provide P2P communication
Address, carries out P2P communication for described source device.
Compared with prior art, the technical scheme of the embodiment of the present invention has the advantages that
The embodiment of the present invention is by obtaining speech data to be identified from source device;Determine described speech data to be identified
Language form, and the speech recognition server of coupling is chosen according to described language form;Described speech data to be identified is sent
To selected speech recognition server, described speech recognition server in order to described speech data to be identified is processed, with
It is identified result;Receive the recognition result of described speech recognition server feedback, be converted to perform by described recognition result
Operational order, and send described operational order to target device, described operational order is used for controlling described target device.Pass through
Speech data to be identified is sent and carries out speech recognition to the speech recognition server mated with its language form, improve user
Use the accuracy of speech recognition;Additionally, by recognition result being converted to control instruction to control target device, it is possible to achieve
Voice command to the target device not possessing speech identifying function, is conducive to improving Consumer's Experience.
Further, when described target device cannot respond to described operational order, described speech data to be identified is forwarded
To manual service platform.Source device cannot respond to described operational order and shows speech recognition server recognition result mistake, passes through
It is forwarded to manual service platform to be identified by manual service platform, is conducive to improving the discrimination of speech recognition, thus controls
The accuracy of target device, improves Consumer's Experience further.
Further, obtain described speech data to be identified and the described operational order of transmission is grasped by P2P communication modes
Make.The high speed communication of speech recognition process can be realized by P2P communication modes, be conducive to improving Consumer's Experience further.
Further, described speech data to be identified is converted into there is the audio file of preset format;To have default lattice
The audio file of formula sends to selected speech recognition server.By being converted into by speech data to be identified, there is preset format
The conversion operation of audio file, it is ensured that speech data to be identified can be received by speech recognition server;And then make to treat
Identify that speech data can support multiple format, reduce the speech recognition server requirement to speech data to be identified, thus
Avoid the technology development work of user side, user cost can be reduced.
Accompanying drawing explanation
Fig. 1 is the flow chart of a kind of control method based on speech recognition of the embodiment of the present invention;
Fig. 2 is the flow chart of the another kind of control method based on speech recognition of the embodiment of the present invention;
Fig. 3 is a kind of structural representation controlling device based on speech recognition of the embodiment of the present invention;
Fig. 4 is the another kind of structural representation controlling device based on speech recognition of the embodiment of the present invention;
Fig. 5 is the schematic diagram of a kind of control system based on speech recognition of the embodiment of the present invention.
Detailed description of the invention
As described in the background art, in the voice recognition mode of prior art, first kind of way needs for a user
There are certain development and corresponding technology requirement;Second way hardware cost is higher, and identify be limited in scope.
Understandable, below in conjunction with the accompanying drawings to the present invention for enabling the above-mentioned purpose of the present invention, feature and advantage to become apparent from
Specific embodiment be described in detail.
Fig. 1 is the flow chart of a kind of control method based on speech recognition of the embodiment of the present invention.
Described control method based on speech recognition may comprise steps of:
Step S101: obtain speech data to be identified from source device;
Step S102: determine the language form of described speech data to be identified, and choose coupling according to described language form
Speech recognition server;
Step S103: described speech data to be identified is sent to selected speech recognition server, described speech recognition
Server is in order to process described speech data to be identified, to be identified result;
Step S104: receiving the recognition result of described speech recognition server feedback, being converted to by described recognition result can
The operational order performed, and send described operational order to target device, described operational order is used for controlling described target device.
Below in conjunction with Fig. 1, above-mentioned steps S101 is described in detail to step S104.
In being embodied as, described source device can gather speech data.In step S101, the speech data got
For speech data to be identified, say, that speech data to be identified needs to carry out speech recognition operation.
It is understood that source device can be arbitrarily to implement the smart machine of voice collecting operation, the most permissible
Being to possess the air-conditioning of voice collecting function, TV, refrigerator, washing machine etc., the embodiment of the present invention is without limitation.
In being embodied as, choose the speech recognition server matched according to the language form of speech data to be identified.Institute
Stating sound-type can be languages, such as, and mandarin, English, Russian etc.;Can also be dialect, such as Shanghai native language, Sichuan words
Deng.Every kind of sound-type all possesses the speech recognition server matched, and described speech recognition server can possess and language
The corresponding speech database of sound type, thus ensure the accuracy of speech recognition.
It is understood that speech recognition server can be the server of speech recognition operator.
Specifically, it is determined that the language form of described speech data to be identified may include that according to described voice number to be identified
According to the geographical position of described source device determine language mode to be selected;Utilize described language mode to be selected to described language to be identified
Sound data are mated, to determine described language form.Specifically, in the case of knowing the geographical position of source device,
The speech pattern to be selected that voice collecting uses can be determined, the voice to be selected determined according to languages corresponding to geographical position or dialect
Pattern can have one or more.Such as, if source device is positioned at Shanghai, then the speech pattern to be selected determined can have general
Call mode, Shanghai native language pattern, English mode.
In being embodied as, in step s 103, described speech data to be identified is sent to selected speech-recognition services
Device, in order to described speech data to be identified is identified by speech recognition server.
Specifically, described speech data to be identified is sent the most selected speech recognition server to may include that described
Speech data to be identified is converted into the audio file with preset format;The audio file with preset format is sent to selected
Speech recognition server, described audio file includes the recognition mode of described source device.Specifically, preset format and voice
Identification server is corresponding.It is to say, speech recognition server has call format for speech data to be identified, therefore sending
Speech data to be identified, to before speech recognition server, is converted into speech recognition server requirement by speech data to be identified
Form.
For various types of subscriber equipmenies, subscriber equipment only need to gather the audio file of reference format i.e.
Can, such as ADPCM, AMR, WAV, MP2, MP3 etc..Avoid subscriber equipment and do technical transformation, improve user and make
By the convenience of speech recognition.
Meanwhile, described recognition mode may refer to the different lexical types that different source device is arranged, the most permissible
It is compuword, film vocabulary, medical vocabulary etc..By recognition mode is sent to speech recognition server, beneficially language
Speech data to be identified is identified by sound identification server targetedly, improves the accuracy of recognition result.
In being embodied as, in step S104, described recognition result is converted to executable operational order, and in order to control
Target device processed.Specifically, target device can be identical with source device, it is also possible to different from source device.It is appreciated that
, according to actual application scenarios, target device and source device may be located at same LAN.
So far, control process based on speech recognition completes, and target device can perform corresponding behaviour according to control instruction
Make.Such as, air-conditioning can switch on power start working according to opening the instruction of control instruction.
The embodiment of the present invention carries out speech recognition by speech data to be identified is matched to speech recognition server, thus
Avoid the technology development work of user side, user cost can be reduced, improve user simultaneously and use the convenience of speech recognition;
Meanwhile, by recognition result being converted to control instruction to control target device, Consumer's Experience is improved.
Fig. 2 is the flow chart of the another kind of control method based on speech recognition of the embodiment of the present invention.
Described control method based on speech recognition may comprise steps of:
Step S201: described source device and described target device are carried out P2P address registration;
Step S202: obtain speech data to be identified from source device;
Step S203: determine the language form of described speech data to be identified, and choose coupling according to described language form
Speech recognition server;
Step S204: described speech data to be identified is sent to selected speech recognition server;
Step S205: receiving the recognition result of described speech recognition server feedback, being converted to by described recognition result can
The operational order performed, and send described operational order to target device;
Step S206: when described target device cannot respond to described operational order, turns described speech data to be identified
Send to manual service platform.
Below in conjunction with Fig. 2, above-mentioned steps S201 is described in detail to step S206.
In being embodied as, in step s 201, by described source device is carried out peer-to-peer network (Peer to Peer,
P2P) address registration, can pass through P2P so that obtain described speech data to be identified with sending described operational order
Communication modes operates.Thus, achieved the high speed communication of speech recognition process by P2P communication modes, improve further
Consumer's Experience.
In being embodied as, in step S202, speech data to be identified can be standard audio file, such as ADPCM,
AMR, WAV, MP2, MP3 etc..
In being embodied as, in step S204, it is that unified data-interface sends by the standard audio file of source device
To selected speech recognition server.Wherein, the recognition result after speech recognition server completes speech recognition can be text
File.
In being embodied as, through step S205, the recognition result of text formatting is converted into control according to the requirement of source device
Instruction processed is sent to target device.Control instruction controls target device and performs corresponding operation.In step S206, at described mesh
When marking device cannot respond to described operational order, show the recognition result mistake of speech recognition server, by described waiting being known
Other speech data is forwarded to manual service platform and carries out more intelligent identification and artificial cognition, can improve the identification of speech recognition
Rate, thus reach to control the accuracy of target device, improve Consumer's Experience further.
Specifically, it is also possible to by user's feedback to control instruction, recognition result is unsatisfied with, then may be used by such as user
So that described speech data to be identified is forwarded to manual service platform.
The detailed description of the invention of embodiment of the present invention step S201 to S206 can refer to aforementioned corresponding embodiment to step
The description of S101 to S104, here is omitted.
The embodiment of the present invention uses the language form determining described speech data to be identified according to source device, chooses not
Mode with speech-recognition services operator;By forwarding speech data to be identified to come to manual service when recognition result is wrong
Improve the mode of discrimination;Realized the speech recognition of network high-speed communication by P2P user's service, reduce user cost, with
Shi Tigao user uses the convenience of speech recognition.
Fig. 3 is a kind of structural representation controlling device based on speech recognition of the embodiment of the present invention.
Control device 30 based on speech recognition may include that acquiring unit 301, matching unit 302, transmitting element 303
With control unit 304.
Wherein, acquiring unit 301 is suitable to obtain speech data to be identified from source device;
Matching unit 302 is adapted to determine that the language form of described speech data to be identified, and selects according to described language form
Take the speech recognition server of coupling;
Transmitting element 303 is suitable to send to selected speech recognition server, institute's predicate described speech data to be identified
Sound identification server is in order to process described speech data to be identified, to be identified result;
Control unit 304 is suitable to receive the recognition result of described speech recognition server feedback, is turned by described recognition result
Being changed to executable operational order, and send described operational order to target device, described operational order is used for controlling described mesh
Marking device.
In the present embodiment, carry out speech recognition by speech data to be identified being matched to speech recognition server, thus
Avoid the technology development work of user side, user cost can be reduced, improve user simultaneously and use the convenience of speech recognition;
Meanwhile, by recognition result being converted to control instruction to control target device, Consumer's Experience is improved.
Fig. 4 is the another kind of structural representation controlling device based on speech recognition of the embodiment of the present invention.
Control device 40 based on speech recognition may include that address registration unit 401, acquiring unit 402, matching unit
403, transmitting element 404, control unit 405 and retransmission unit 406.
Wherein, address registration unit 401 is suitable to described source device and described target device are carried out P2P address note
Volume.
Acquiring unit 402 is suitable to obtain speech data to be identified from source device;
Matching unit 403 is adapted to determine that the language form of described speech data to be identified, and selects according to described language form
Take the speech recognition server of coupling.
In being embodied as, matching unit 403 may include that speech pattern determines that subelement (not shown) and sound-type are true
Stator unit (not shown).
Wherein, speech pattern determines that subelement is suitable to the geography of the described source device according to described speech data to be identified
Position determines language mode to be selected;Sound-type determines that subelement is suitable to utilize described language mode to be selected to described language to be identified
Sound data are mated, to determine described language form.
Transmitting element 404 is suitable to send to selected speech recognition server, institute's predicate described speech data to be identified
Sound identification server is in order to process described speech data to be identified, to be identified result.
Specifically, transmitting element 404 can include format conversion subelement (not shown) and send subelement (not shown).
Wherein, format conversion subelement, be suitable to described speech data to be identified is converted into the audio frequency with preset format
File;Send subelement, be suitable to send to selected speech recognition server, described sound the audio file with preset format
Frequency file includes the recognition mode of described source device
Control unit 405 is suitable to receive the recognition result of described speech recognition server feedback, is turned by described recognition result
Being changed to executable operational order, and send described operational order to target device, described operational order is used for controlling described mesh
Marking device.Retransmission unit 406 is suitable to when described target device cannot respond to described operational order, by described voice number to be identified
According to being forwarded to manual service platform.
The embodiment of the present invention detailed description of the invention controlling device 40 based on speech recognition can refer to aforementioned based on voice
The corresponding embodiment of the control method identified, here is omitted.
The embodiment of the invention also discloses a kind of control system based on speech recognition.Described system can include based on language
The control device of sound identification and at least one speech recognition server, speech recognition server is in order to enter speech data to be identified
Row processes, to be identified result.
Wherein, the described device that controls based on speech recognition sends extremely in order to the speech data described to be identified that will get
The speech recognition server of coupling, and the most described recognition result is converted to executable operational order, described operational order is used
To control the source device of described speech data to be identified.
In being embodied as, described system can also include P2P client server, and P2P client server leads in order to provide P2P
News address, carries out P2P communication for described source device.
The embodiment of the present invention builds P2P network by combining P2P client server, thus constitutes base based on speech recognition
Plinth service system, makes the accuracy of speech recognition and real-time improve further;Make the integration between internal system more simultaneously
Simply.
As it is shown in figure 5, the schematic diagram of Fig. 5 a kind of control system based on speech recognition that is the embodiment of the present invention.
In the present embodiment, control device 501 based on speech recognition can be to realize in the manner of a server.
In the present embodiment, for various types of source device 501, source device 501 need to gather the audio frequency literary composition of standard
Part.And after being submitted to control device 502 based on speech recognition, control device 502 based on speech recognition is according to source device
The address of 501 judges the language form of audio file, and matches suitable speech recognition server 503 according to language form.
Such as it may be that for the speech recognition server A of mandarin identification, for the speech recognition server B of English identification or use
Speech recognition server C in Shanghai native language identification.
Audio file is converted to the form that speech recognition server 503 requires by control device 502 based on speech recognition,
And it is committed to speech recognition server 503 according to corresponding form.
Speech recognition server 503 carries out speech recognition to audio file, and returns recognition result to based on speech recognition
Control device 502, recognition result is assembled into the demand form of source device 501 by the device 502 that controls based on speech recognition
Send to source device 501.
If speech recognition server 503 None-identified or source device 501 feedback identifying result are wrong, Ke Yijing
By, audio file is submitted to manual service platform 505 by based on speech recognition control device 502 again, carries out more intelligent knowledge
Not or manual service.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
Completing instructing relevant hardware by program, this program can be stored in in computer-readable recording medium, storage
Medium may include that ROM, RAM, disk or CD etc..
Although present disclosure is as above, but the present invention is not limited to this.Any those skilled in the art, without departing from this
In the spirit and scope of invention, all can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Limit in the range of standard.
Claims (14)
1. a control method based on speech recognition, it is characterised in that including:
Speech data to be identified is obtained from source device;
Determine the language form of described speech data to be identified, and choose the speech-recognition services of coupling according to described language form
Device;
Sending described speech data to be identified to selected speech recognition server, described speech recognition server is in order to institute
State speech data to be identified to process, to be identified result;
Receive the recognition result of described speech recognition server feedback, described recognition result is converted to executable operation and refers to
Order, and send described operational order to target device, described operational order is used for controlling described target device.
Control method based on speech recognition the most according to claim 1, it is characterised in that also include:
When described target device cannot respond to described operational order, described speech data to be identified is forwarded to manual service
Platform.
Control method based on speech recognition the most according to claim 1, it is characterised in that described from source device acquisition
Also include before speech data to be identified:
Described source device and described target device are carried out P2P address registration.
Control method based on speech recognition the most according to claim 3, it is characterised in that obtain described voice to be identified
Data and the described operational order of transmission are operated by P2P communication modes.
Control method based on speech recognition the most according to claim 1, it is characterised in that described determine described to be identified
The language form of speech data includes:
The geographical position of the described source device according to described speech data to be identified determines language mode to be selected;
Utilize described language mode to be selected that described speech data to be identified is mated, to determine described language form.
6. according to the control method based on speech recognition described in any one of claim 1 to 5, it is characterised in that described by institute
State speech data to be identified transmission to include to selected speech recognition server:
Described speech data to be identified is converted into the audio file with preset format;
Sending the audio file with preset format to selected speech recognition server, described audio file includes described next
The recognition mode of source device.
7. a control device based on speech recognition, it is characterised in that including:
Acquiring unit, is suitable to obtain speech data to be identified from source device;
Matching unit, is adapted to determine that the language form of described speech data to be identified, and chooses coupling according to described language form
Speech recognition server;
Transmitting element, is suitable to send to selected speech recognition server, described speech recognition described speech data to be identified
Server is in order to process described speech data to be identified, to be identified result;
Control unit, is suitable to receive the recognition result of described speech recognition server feedback, and being converted to by described recognition result can
The operational order performed, and send described operational order to target device, described operational order is used for controlling described target device.
Control device based on speech recognition the most according to claim 7, it is characterised in that also include:
Retransmission unit, is suitable to, when described target device cannot respond to described operational order, be turned by described speech data to be identified
Send to manual service platform.
Control device based on speech recognition the most according to claim 7, it is characterised in that also include:
Address registration unit, is suitable to described source device and described target device are carried out P2P address registration.
Control device based on speech recognition the most according to claim 9, it is characterised in that obtain described language to be identified
Sound data and the described operational order of transmission are operated by P2P communication modes.
11. control devices based on speech recognition according to claim 7, it is characterised in that described matching unit includes:
Speech pattern determines subelement, and the geographical position being suitable to the described source device according to described speech data to be identified determines
Language mode to be selected;
Sound-type determines subelement, is suitable to utilize described language mode to be selected to mate described speech data to be identified,
To determine described language form.
12. according to the control device based on speech recognition described in any one of claim 7 to 11, it is characterised in that described
Unit is sent to include:
Format conversion subelement, is suitable to described speech data to be identified is converted into the audio file with preset format;
Send subelement, be suitable to send to selected speech recognition server, described sound the audio file with preset format
Frequency file includes the recognition mode of described source device.
13. 1 kinds of control systems based on speech recognition, including:
Control device based on speech recognition as described in any one of claim 7 to 12;
At least one described speech recognition server.
14. control systems based on speech recognition according to claim 13, it is characterised in that also include:
P2P client server, in order to provide P2P address, for described source device and described control based on speech recognition
Device processed carries out P2P communication.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610700858.8A CN106228974A (en) | 2016-08-19 | 2016-08-19 | Control method based on speech recognition, Apparatus and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610700858.8A CN106228974A (en) | 2016-08-19 | 2016-08-19 | Control method based on speech recognition, Apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106228974A true CN106228974A (en) | 2016-12-14 |
Family
ID=57552739
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610700858.8A Pending CN106228974A (en) | 2016-08-19 | 2016-08-19 | Control method based on speech recognition, Apparatus and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106228974A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN107276864A (en) * | 2017-07-25 | 2017-10-20 | 广东美的制冷设备有限公司 | The method of intelligent sound equipment control household electrical appliances, apparatus and system |
CN107342083A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Method and apparatus for providing voice service |
CN107622771A (en) * | 2017-09-30 | 2018-01-23 | 广东美的制冷设备有限公司 | Home appliance and its control method, system and computer-readable recording medium |
CN107885481A (en) * | 2017-10-26 | 2018-04-06 | 中国地质大学(武汉) | The page sound control method and voice browser of a kind of browser of mobile terminal |
CN108921562A (en) * | 2018-05-24 | 2018-11-30 | 佛山市竣智文化传播股份有限公司 | A kind of on-line payment and its device based on Application on Voiceprint Recognition |
CN109189365A (en) * | 2018-08-17 | 2019-01-11 | 平安普惠企业管理有限公司 | A kind of audio recognition method, storage medium and terminal device |
CN109599112A (en) * | 2019-01-02 | 2019-04-09 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and air-conditioning |
CN111477227A (en) * | 2020-04-07 | 2020-07-31 | 四川虹美智能科技有限公司 | Voice interaction method and system for voice intelligent household appliance and voice intelligent household appliance |
CN112581959A (en) * | 2020-12-15 | 2021-03-30 | 四川虹美智能科技有限公司 | Intelligent device control method and system and voice server |
CN113299285A (en) * | 2020-02-22 | 2021-08-24 | 北京声智科技有限公司 | Device control method, device, electronic device and computer-readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
CN102538143A (en) * | 2012-02-06 | 2012-07-04 | 广东美的电器股份有限公司 | Intelligent phonic search engine air-conditioning system and control method thereof |
CN103456303A (en) * | 2013-08-08 | 2013-12-18 | 四川长虹电器股份有限公司 | Method for controlling voice and intelligent air-conditionier system |
CN104715752A (en) * | 2015-04-09 | 2015-06-17 | 刘文军 | Voice recognition method, voice recognition device and voice recognition system |
CN105872687A (en) * | 2016-03-31 | 2016-08-17 | 乐视控股(北京)有限公司 | Method and device for controlling intelligent equipment through voice |
-
2016
- 2016-08-19 CN CN201610700858.8A patent/CN106228974A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
CN102538143A (en) * | 2012-02-06 | 2012-07-04 | 广东美的电器股份有限公司 | Intelligent phonic search engine air-conditioning system and control method thereof |
CN103456303A (en) * | 2013-08-08 | 2013-12-18 | 四川长虹电器股份有限公司 | Method for controlling voice and intelligent air-conditionier system |
CN104715752A (en) * | 2015-04-09 | 2015-06-17 | 刘文军 | Voice recognition method, voice recognition device and voice recognition system |
CN105872687A (en) * | 2016-03-31 | 2016-08-17 | 乐视控股(北京)有限公司 | Method and device for controlling intelligent equipment through voice |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018219105A1 (en) * | 2017-05-31 | 2018-12-06 | Oppo广东移动通信有限公司 | Speech recognition and related products |
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 |
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 |
CN107342083B (en) * | 2017-07-05 | 2021-07-20 | 百度在线网络技术(北京)有限公司 | Method and apparatus for providing voice service |
CN107342083A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Method and apparatus for providing voice service |
US11360737B2 (en) | 2017-07-05 | 2022-06-14 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for providing speech service |
CN107276864A (en) * | 2017-07-25 | 2017-10-20 | 广东美的制冷设备有限公司 | The method of intelligent sound equipment control household electrical appliances, apparatus and system |
CN107622771A (en) * | 2017-09-30 | 2018-01-23 | 广东美的制冷设备有限公司 | Home appliance and its control method, system and computer-readable recording medium |
CN107885481A (en) * | 2017-10-26 | 2018-04-06 | 中国地质大学(武汉) | The page sound control method and voice browser of a kind of browser of mobile terminal |
CN108921562A (en) * | 2018-05-24 | 2018-11-30 | 佛山市竣智文化传播股份有限公司 | A kind of on-line payment and its device based on Application on Voiceprint Recognition |
CN109189365A (en) * | 2018-08-17 | 2019-01-11 | 平安普惠企业管理有限公司 | A kind of audio recognition method, storage medium and terminal device |
CN109599112A (en) * | 2019-01-02 | 2019-04-09 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and air-conditioning |
CN109599112B (en) * | 2019-01-02 | 2021-07-06 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
CN113299285A (en) * | 2020-02-22 | 2021-08-24 | 北京声智科技有限公司 | Device control method, device, electronic device and computer-readable storage medium |
CN111477227A (en) * | 2020-04-07 | 2020-07-31 | 四川虹美智能科技有限公司 | Voice interaction method and system for voice intelligent household appliance and voice intelligent household appliance |
CN112581959A (en) * | 2020-12-15 | 2021-03-30 | 四川虹美智能科技有限公司 | Intelligent device control method and system and voice server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106228974A (en) | Control method based on speech recognition, Apparatus and system | |
US9601114B2 (en) | Method for embedding voice mail in a spoken utterance using a natural language processing computer system | |
CN108010523B (en) | Information processing method and recording medium | |
CN106653008B (en) | Voice control method, device and system | |
US8938388B2 (en) | Maintaining and supplying speech models | |
CN105391730A (en) | Information feedback method, device and system | |
WO2020253064A1 (en) | Speech recognition method and apparatus, and computer device and storage medium | |
WO2007125151A1 (en) | A method, a system and a device for converting speech | |
JP2021501356A (en) | Creating modular conversations with implicit routing | |
CN108197091B (en) | Method, system and related equipment for creating data table | |
JP5368924B2 (en) | Apparatus and method for progressive development of natural language user interfaces | |
CN104575499B (en) | Voice control method of mobile terminal and mobile terminal | |
CN103076893A (en) | Method and equipment for realizing voice input | |
CN105120373A (en) | Voice transmission control method and voice transmission control system | |
JP2018120202A (en) | Information processing method and program | |
US20210249001A1 (en) | Dialog System Capable of Semantic-Understanding Mapping Between User Intents and Machine Services | |
CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
CN105632494A (en) | Intelligent household electrical appliance equipment control method and device | |
KR102357620B1 (en) | Chatbot integration agent platform system and service method thereof | |
CN107086949A (en) | It is a kind of to be used for people and the auxiliary intelligent apparatus of smart machine interactive operation | |
CN105489218A (en) | Speech control system, remote control and server | |
CN105206273A (en) | Voice transmission control method and system | |
US20140136620A1 (en) | Protocol conversion apparatus and method | |
CN104679733A (en) | Voice conversation translation method, device and system | |
CN104392366B (en) | The method of data comparison information acquisition, Apparatus and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161214 |