CN106328137A - Voice control method, voice control device and voice control system - Google Patents
Voice control method, voice control device and voice control system Download PDFInfo
- Publication number
- CN106328137A CN106328137A CN201610696964.3A CN201610696964A CN106328137A CN 106328137 A CN106328137 A CN 106328137A CN 201610696964 A CN201610696964 A CN 201610696964A CN 106328137 A CN106328137 A CN 106328137A
- Authority
- CN
- China
- Prior art keywords
- data
- terminal unit
- speech
- transmission data
- speech 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title abstract description 19
- 230000005540 biological transmission Effects 0.000 description 44
- 238000001914 filtration Methods 0.000 description 25
- 238000011946 reduction process Methods 0.000 description 8
- 238000004378 air conditioning Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009545 invasion Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010365 information processing 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
- 230000004899 motility Effects 0.000 description 1
- 230000004044 response Effects 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
- G10L15/22—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
-
- 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)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a voice control method, a voice control device and a voice control system. The voice control method comprises the steps of receiving transmitting data which are acquired by at least one set of terminal equipment and comprise voice data; on the condition that a submission request exists in the transmitting data, submitting the voice data to a voice identification server for identification, thereby obtaining an identification result; receiving the identification result, and performing matching on the identification result and all preset control commands; and on the condition that the preset control command which matches the identification result exists, transmitting the selected preset control command to objective terminal equipment which is related with the preset control command, thereby controlling the objective terminal equipment. The voice control method, the voice control device and the voice control system can ensure high safety and high convenience in voice controlling.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to a kind of sound control method, Apparatus and system.
Background technology
Along with the development of speech recognition technology, the accuracy of speech recognition improves constantly, and the scope that speech recognition is supported is also
Constantly expanding.For Mu Qian, speech recognition standard pronunciation to world languages achieves the identification close to 80%
Rate, is constantly improving also with the growth of data base the accuracy of the identification of various dialects.Simultaneously because speech recognition skill
The maturation of art, increasing field all begins to use speech recognition as the interface of man-machine interaction.
Along with the application in domestic environment of more and more speech recognition apparatus, the safety of home voice collection, effect
Also user's very concern is become with reliability.In prior art, the voice collecting of equipment all uses the mode of unit to enter
OK, being sent to special speech recognition server by network and be identified after having gathered, recognition result returns again to this equipment.
But, when there are illegal invasion data in acquisition mode of the prior art, it is impossible to identifies invalid data, it is impossible to protects
Demonstrate,prove voice-operated safety.
Summary of the invention
Present invention solves the technical problem that it is how to ensure voice-operated safety.
For solving above-mentioned technical problem, the embodiment of the present invention provides a kind of sound control method, and sound control method includes:
Receiving the transmission data that at least one terminal unit gathers, described transmission data include speech data；When described
When sending existence submission request in data, described speech data is committed to speech recognition server and is identified, to be identified
Result；Receive described recognition result, and described recognition result is mated with all default control orders；When existing with described
During the described default control order that recognition result matches, selected described default control order is sent to described default control
The target terminal equipment of order association processed, to control described target terminal equipment.
Optionally, described sound control method also includes: when there is not described submission request in described transmission data, will
Described speech data is judged as invalid data and abandons.
Optionally, described sound control method also includes: when do not exist match with described recognition result described preset
During control command, send information to sending the terminal unit of described transmission data, to point out user to re-enter institute's predicate
Sound data.
Optionally, described transmission Data Source is at least two terminal unit, wherein, starts to gather at first terminal equipment
Time, notify that at least one other-end equipment starts synchronous acquisition, to obtain described transmission data.
Optionally, also include after the transmission data of at least one terminal unit collection of described reception: described in combination at least
The transmission data that two terminal units gather, carry out noise reduction process to described speech data, to filter environment noise.
Optionally, described described speech data is carried out noise reduction process include: the language to described at least two terminal unit
Sound data carry out noise analysis, to obtain filtering profile；According to the described filtering profile language to described at least two terminal unit
Sound data carry out noise filtering.
For solving above-mentioned technical problem, the embodiment of the invention also discloses a kind of phonetic controller, phonetic controller
Including:
Receiving unit, be suitable to receive the transmission data that at least one terminal unit gathers, described transmission data include voice
Data；Submit unit to, when being suitable to exist submission request in described transmission data, described speech data is committed to speech recognition
Server is identified, to be identified result；Matching unit, is suitable to receive described recognition result, and by described recognition result
Mate with all default control orders；Control command transmitting element, is suitable to when existing and described recognition result matches
During described default control order, selected described default control order is sent to the target with described default control order association
Terminal unit, to control described target terminal equipment.
Optionally, described phonetic controller also includes: safe unit, is suitable to not exist in described transmission data described
When submitting request to, described speech data is judged as invalid data and abandons.
Optionally, described phonetic controller also includes: Tip element, is suitable to not exist and described recognition result phase
During the described default control order joined, send information to sending the terminal unit of described transmission data, to point out user weight
Newly inputted described speech data.
Optionally, described transmission Data Source is at least two terminal unit, wherein, starts to gather at first terminal equipment
Time, notify that at least one other-end equipment starts synchronous acquisition, to obtain described transmission data.
Optionally, described phonetic controller also includes: noise filtering unit, is suitable to combine described at least two terminal and sets
The standby transmission data gathered, carry out noise reduction process to described speech data, to filter environment noise.
Optionally, described noise filtering unit includes: noise analysis subelement, is suitable to described at least two terminal unit
Speech data carry out noise analysis, to obtain filtering profile；Noise filtering subelement, is suitable to according to described filtering profile institute
The speech data stating at least two terminal unit carries out noise filtering.
For solving above-mentioned technical problem, the embodiment of the invention also discloses a kind of speech control system, described Voice command
System includes: phonetic controller；The speech recognition server coupled with described phonetic controller.
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 receiving the transmission data that at least one terminal unit gathers, and described transmission data include language
Sound data；When described transmission data exist submission request, described speech data is committed to speech recognition server and carries out
Identify, to be identified result；Receive described recognition result, and described recognition result and all default control orders are carried out
Join；When there is the described default control order matched with described recognition result, selected described default control order is sent out
Deliver to and the target terminal equipment of described default control order association, to control described target terminal equipment.By at least one
The speech data of terminal unit collection controlled target terminal equipment later through speech recognition so that the acquisition range of speech data
Expand, the control to target terminal equipment of at least one terminal unit can be realized simultaneously, improve Voice command and use just
Victory；When submitting request to by existing in sending data, described speech data is committed to speech recognition server and knows
Not, it is ensured that the safety in speech data source, and then voice-operated safety is ensured.
Further, when described transmission data do not exist described submission request, described speech data is judged as illegally
Data also abandon.By submission request is judged, when it is impossible to ensure that speech data is originated, speech data is lost
Abandon, be further ensured that voice-operated safety.
Further, when a terminal unit starts to gather, notify that at least one other terminal unit starts to adopt simultaneously
Collection, the transmission data gathered in conjunction with described at least two terminal unit, described speech data is carried out noise reduction process, to filter ring
Border noise.By environment noise is filtered, it is ensured that the accuracy of the recognition result of speech data, and then ensure voice
The accuracy controlled.
Accompanying drawing explanation
Fig. 1 is the flow chart of a kind of sound control method of the embodiment of the present invention；
Fig. 2 is the flow chart of embodiment of the present invention another kind sound control method；
Fig. 3 is the structural representation of a kind of phonetic controller of the embodiment of the present invention；
Fig. 4 is the structural representation of embodiment of the present invention another kind phonetic controller；
Fig. 5 is the schematic diagram of a kind of speech control system of the embodiment of the present invention.
Detailed description of the invention
As described in the background art, when there is illegal invasion in acquisition mode of the prior art, it is impossible to identifies illegal number
According to, it is impossible to ensure voice-operated safety；Meanwhile, the acquisition range of stand-alone device is limited, and bigger at environmental noise
When the speech data that collects of poor quality, discrimination is low.
User how can be made both can to have used speech recognition safely, various noisy environment can be conveniently implemented in again
Under, and realize under different azimuth being very distinct issues to the effective speech identification of voice messaging.
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 sound control method of the embodiment of the present invention.
Described sound control method may include that
Step S101: receive the transmission data that at least one terminal unit gathers；
Step S102: when there is submission request in described transmission data, described speech data is committed to speech recognition
Server is identified, to be identified result；
Step S103: receive described recognition result, and described recognition result is mated with all default control orders；
Step S104: when there is the described default control order matched with described recognition result, by described default control
System order sends to the target terminal equipment with described default control order association, to control described target terminal equipment.
Below in conjunction with Fig. 1, above-mentioned steps S101 is described in detail to step S104.
In step S101, the transmission data of at least one terminal unit collection can include speech data.Wherein, described
Send data and may come from a terminal unit, it is also possible to come from multiple terminal unit.Come from multiple when sending data
During terminal unit, the position relationship of multiple terminal units can be distributed.It is to say, be not limited to residing for multiple device end
Position, as long as speech data can be collected.
Specifically, described transmission data can also include submitting request to, and submission request can be a kind of order, in order to refer to
Show and speech data is committed to speech recognition server.
In step s 102, according to submitting the instruction asked to, described speech data is committed to speech recognition server and enters
Row identifies, to be identified result.Specifically, when choosing speech recognition server, it may be considered that the class of languages of speech data
Type, identifies speech data more accurately realizing speech recognition server.
It is understood that speech recognition server can be the server of speech recognition operator.
In step s 103, described recognition result is mated with all default control orders.Specifically, all default
Control command can be pre-configured with, and can be stored in data base.After receiving recognition result, according to recognition result
Content is mated with all default control orders in data base.Such as, the content of recognition result is " temperature was once raising ",
The default control order so matched is then " temperature adds 1 ".
Specifically, default control order is associated with at least one terminal unit, may be used for the end controlling to be associated
End equipment.Such as, when default control order is " temperature adds 1 ", the terminal unit being associated with this default control order is air-conditioning；
When default control order is " channel adds 1 ", the terminal unit being associated with this default control order is TV.
In step S104, when there is the described default control order matched with described recognition result, by selected institute
State default control order to send to the target terminal equipment with described default control order association.Wherein, target terminal equipment can
To be intended to the terminal unit controlled.Target terminal equipment can be with the terminal at least one terminal unit gathering speech data
Equipment is identical, it is also possible to different from the terminal unit at least one terminal unit gathering speech data.For example, it may be it is logical
Cross speech data that television equipment collects to control air-conditioning equipment；It can also be the speech data collected by television equipment
Control television equipment.
When as previously mentioned, there are multiple terminal unit, the position relationship of multiple terminal units can be distributed.Target is eventually
Position relationship between end equipment and the terminal unit gathering speech data can also be distributed, then the embodiment of the present invention
The mutual phase control being between the terminal unit of diverse location can be realized.Meanwhile, by the distributed position of terminal unit
Relation, it is possible to achieve under whole Voice command uses environment, carry out data under voice and Voice command in gamut.Example
As, speech data can be gathered by being positioned at the television equipment in parlor, to control to be positioned at the air-conditioning equipment in bedroom.
The speech data that the embodiment of the present invention is gathered by least one terminal unit controlled mesh later through speech recognition
Mark terminal unit so that the acquisition range of speech data expands, can realize at least one terminal unit to target terminal simultaneously
The control of equipment, improves the convenience that Voice command uses；When submitting request to by existing in sending data, by institute's predicate
Sound data are committed to speech recognition server and are identified, it is ensured that the safety in speech data source, and then ensure voice
The safety controlled.
Fig. 2 is the flow chart of embodiment of the present invention another kind sound control method.
Described sound control method may include that
Step S201: receive the transmission data that at least two terminal unit gathers；
Step S202: combine the transmission data that described at least two terminal unit gathers, described speech data is dropped
Make an uproar process, to filter environment noise；
Step S203: judge whether there is submission request in described transmission data；It is then to enter step S204, otherwise enters
Step S205；
Step S204: described speech data is committed to speech recognition server and is identified, to be identified result；
Step S205: described speech data is judged as invalid data and abandons；
Step S206: receive described recognition result, and described recognition result is mated with all default control orders；
Step S207: judge whether the described default control order matched with described recognition result；The most then enter
Enter step S208, otherwise enter step S209；
Step S208: selected described default control order is sent to the target with described default control order association eventually
End equipment, to control described target terminal equipment.
Step S209: send information to sending the terminal unit of described transmission data, to point out user to re-enter
Described speech data.
Below in conjunction with Fig. 2, above-mentioned steps S201 is described in detail to step S209.
In the present embodiment, send data instance with at least two terminal unit collection.Send Data Source at least two
Terminal unit, wherein, first the first terminal equipment in above-mentioned at least two terminal unit collect transmission data, first eventually
When end equipment starts to gather, notify that at least one other-end equipment starts synchronous acquisition, to obtain described transmission data.Example
As, when the television equipment being positioned at parlor starts to gather speech data, notice is positioned at the air-conditioning equipment in bedroom and is positioned at kitchen
Refrigerator apparatus synchronize start acquisition operations.Specifically, notice operation can be realized by the way of communication between devices.
It is understood that owing to the distance for equipment room that communicates between terminal unit is restricted, therefore at least two terminal
Equipment distance between any two is in setpoint distance.The size of setpoint distance can be according to actual applied environment and communication
Mode custom-configures.
In step S202, described speech data is carried out noise reduction process and may include that described at least two terminal is set
Standby speech data carries out noise analysis, to obtain filtering profile；According to described filtering profile, described at least two terminal is set
Standby speech data carries out noise filtering.Specifically, the terminal unit during filtering profile can be at least two terminal unit
The speech data gathered, this speech data is when noise analysis, and noise is few, therefore this speech data can be as filtering profile.Warp
Speech data after being filtered by filtering profile, its environment noise can be filtered, it is ensured that the recognition result of speech data
Accuracy, and then ensure voice-operated accuracy.
Such as, for being positioned at the television equipment in parlor, being positioned at the air-conditioning equipment in bedroom and be positioned at the refrigerator apparatus in kitchen
The speech data gathered, owing to bedroom is quiet, environment noise is few, therefore the speech data that the air-conditioning equipment being positioned at bedroom gathers is permissible
As filtering profile, the speech data of television equipment and refrigerator apparatus collection is carried out noise filtering.
In step S205, when described transmission data do not exist described submission request, described speech data is judged
For invalid data and abandon.Specifically, after collection completes, send submission request owing to gathering the terminal unit of speech data,
Speech data is submitted to carry out speech recognition with instruction.Therefore when there is not transmission request in sending data, then show to send data
In speech data from not clear equipment, it is possible to determine that for invalid data, and this speech data is abandoned, to be controlled to ensure
The control security of target terminal equipment.
In step S209, if there is not the default control order that the recognition result with speech data matches, then it represents that
This speech data is imperfect, or this speech data content can not form control command, and such as, speech data is not complete one
Word, causes voice identification result imperfect, to such an extent as to can not mate default control instruction；Or, the identification of speech data
The scope that result instructs beyond default control, it is impossible to be used for controlling target terminal equipment.Then can send information to sending out
Go out the terminal unit of described transmission data, to point out user to re-enter described speech data.
Specifically, it is also possible to being after default control instruction arrives target terminal equipment, target terminal equipment feedback can not
Instruct in response to this default control, then, now can send information to sending the terminal unit of described transmission data, with
Prompting user re-enters described speech data.
The detailed description of the invention of the embodiment of the present invention can refer to aforementioned corresponding embodiment, and here is omitted.
Fig. 3 is the structural representation of a kind of phonetic controller of the embodiment of the present invention.
Phonetic controller 30 may include that reception unit 301, submits unit 302, matching unit 303 and control command to
Transmitting element 304.
Wherein, receive unit 301 to be suitable to receive the transmission data that at least one terminal unit gathers, described transmission packet
Include speech data；
When submitting to unit 302 to be suitable to existence submission request in described transmission data, described speech data is committed to language
Sound identification server is identified, to be identified result；
Matching unit 303 is suitable to receive described recognition result, and is entered with all default control orders by described recognition result
Row coupling；
Control command transmitting element 304 is suitable to when there is the described default control order matched with described recognition result
Time, described default control order is sent to the target terminal equipment with described default control order association, to control described mesh
Mark terminal unit.
The speech data that the embodiment of the present invention is gathered by least one terminal unit controlled mesh later through speech recognition
Mark terminal unit so that the acquisition range of speech data expands, can realize at least one terminal unit to target terminal simultaneously
The control of equipment, improves the convenience that Voice command uses；When submitting request to by existing in sending data, by institute's predicate
Sound data are committed to speech recognition server and are identified, it is ensured that the safety in speech data source, and then ensure voice
The safety controlled.
The detailed description of the invention of the embodiment of the present invention can refer to aforementioned corresponding embodiment, and here is omitted.
Fig. 4 is the structural representation of embodiment of the present invention another kind phonetic controller.
Phonetic controller 30 may include that reception unit 401, noise filtering unit 402, submits to unit 403, safety single
Unit 404, matching unit 405, control command transmitting element 406 and Tip element 407.
Wherein, receive unit 401 to be suitable to receive the transmission data that at least one terminal unit gathers, described transmission packet
Include speech data.
Noise filtering unit 402 is suitable to combine the transmission data that described at least two terminal unit gathers, to described voice
Data carry out noise reduction process, to filter environment noise.Specifically, noise filtering unit 402 can include noise analysis sub-list
Unit's (not shown) and noise filtering subelement (not shown).Noise analysis subelement, is suitable to described at least two terminal unit
Speech data carry out noise analysis, to obtain filtering profile；Noise filtering subelement, is suitable to according to described filtering profile institute
The speech data stating at least two terminal unit carries out noise filtering.
When submitting to unit 403 to be suitable to existence submission request in described transmission data, described speech data is committed to language
Sound identification server is identified, to be identified result；Safe unit 404 is suitable to not exist in described transmission data described
When submitting request to, described speech data is judged as invalid data and abandons.
Matching unit 405 is suitable to receive described recognition result, and is entered with all default control orders by described recognition result
Row coupling.
Control command transmitting element 406 is suitable to when there is the described default control order matched with described recognition result
Time, described default control order is sent to the target terminal equipment with described default control order association, to control described mesh
Mark terminal unit.
In being embodied as, Tip element 407 is suitable to there is not the described default control matched with described recognition result
During order, send information to sending the terminal unit of described transmission data, to point out user to re-enter described voice number
According to.
The detailed description of the invention of the embodiment of the present invention can refer to aforementioned corresponding embodiment, and here is omitted.
The embodiment of the invention also discloses a kind of speech control system, speech control system can include voice shown in Fig. 3
Control phonetic controller 40 shown in device 30 or Fig. 4, and speech recognition server.
Wherein, speech recognition server is in order to carry out speech recognition to the speech data received, to be identified result.
Described phonetic controller is in order to receive the described speech data that at least one terminal unit gathers, and is committed to the knowledge of described voice
Other server, after coupling obtains the default control order corresponding with described recognition result, sends described default control order
To target terminal equipment.
Specifically, phonetic controller 30 or phonetic controller 40 can realize in the way of using server.Language
Sound identification server can be the server of speech recognition operator.
The speech control system of the embodiment of the present invention can be applied at domestic environment, such that it is able to realize between housed device
Based on speech data mutual phase control, improve convenience and motility that housed device is controlled by user.
As it is shown in figure 5, the schematic diagram of Fig. 5 a kind of speech control system that is the embodiment of the present invention.
Terminal unit 501 can include multiple terminal unit: terminal unit 1, terminal unit 2 and terminal unit 3.Can manage
Solving, the quantity of terminal unit can custom-configure according to actual applied environment, and the embodiment of the present invention is to this not
Limit.
With user near terminal unit 1, whole voice control is described as a example by needing to control terminal unit 3 by voice
Process processed.
When user is near terminal unit 1, terminal unit 1 gathers speech data, and sends to phonetic controller 502.
Phonetic controller 502 checks whether as user speech identification content by submission request, if being, is submitted to speech recognition clothes
Business device 503.Voice identification result is returned phonetic controller 502 by speech recognition server 503, and phonetic controller 502 is again
Order request form according to terminal unit 3 sends corresponding default control order to terminal unit 3.
Furthermore, the multiple terminal units in terminal unit 501 all can gather speech data, therefore sets in terminal
During standby 1 collection user speech, other-end equipment (terminal unit 2 and/or terminal unit 3) can be with synchronous acquisition.Final collection
To speech data can carry out further noise reduction process at phonetic controller 502, thus improve voice-operated quality.
The speech control system of the embodiment of the present invention, it is possible to achieve make full use of terminal unit and carry out data under voice；
In conjunction with the noise reduction process of speech data, and by the distributed position relationship of various terminal units, it is formed at Voice command
Voice collecting in system-operating environment gamut.
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 (13)
1. a sound control method, it is characterised in that including:
Receiving the transmission data that at least one terminal unit gathers, described transmission data include speech data；
When described transmission data exist submission request, described speech data is committed to speech recognition server and knows
Not, to be identified result；
Receive described recognition result, and described recognition result is mated with all default control orders；
When there is the described default control order matched with described recognition result, selected described default control order is sent out
Deliver to and the target terminal equipment of described default control order association, to control described target terminal equipment.
Sound control method the most according to claim 1, it is characterised in that also include:
When described transmission data do not exist described submission request, described speech data is judged as invalid data and abandons.
Sound control method the most according to claim 1, it is characterised in that also include:
When there is not the described default control order matched with described recognition result, send information to sending described sending out
Send the terminal unit of data, to point out user to re-enter described speech data.
Sound control method the most according to claim 1, it is characterised in that described transmission Data Source is at least two eventually
End equipment, wherein, when first terminal equipment starts to gather, notifies that at least one other-end equipment starts synchronous acquisition, with
Obtain described transmission data.
Sound control method the most according to claim 4, it is characterised in that at least one terminal unit of described reception gathers
Transmission data after also include:
The transmission data gathered in conjunction with described at least two terminal unit, carry out noise reduction process to described speech data, to filter
Environment noise.
Sound control method the most according to claim 5, it is characterised in that described described speech data is carried out at noise reduction
Reason includes:
The speech data of described at least two terminal unit is carried out noise analysis, to obtain filtering profile；
According to described filtering profile, the speech data of described at least two terminal unit is carried out noise filtering.
7. a phonetic controller, it is characterised in that including:
Receiving unit, be suitable to receive the transmission data that at least one terminal unit gathers, described transmission data include speech data；
Submit unit to, when being suitable to exist submission request in described transmission data, described speech data is committed to speech recognition
Server is identified, to be identified result；
Matching unit, is suitable to receive described recognition result, and is mated with all default control orders by described recognition result；
Control command transmitting element, is suitable to when there is the described default control order matched with described recognition result, will choosing
Fixed described default control order sends to the target terminal equipment with described default control order association, to control described target
Terminal unit.
Phonetic controller the most according to claim 7, it is characterised in that also include:
Safe unit, when being suitable to not exist described submission request in described transmission data, is judged as non-by described speech data
Method data also abandon.
Phonetic controller the most according to claim 7, it is characterised in that also include:
Tip element, is suitable to when there is not the described default control order matched with described recognition result,
Send information to sending the terminal unit of described transmission data, to point out user to re-enter described speech data.
Phonetic controller the most according to claim 7, it is characterised in that described transmission Data Source is at least two
Terminal unit, wherein, when first terminal equipment starts to gather, notifies that at least one other-end equipment starts synchronous acquisition,
To obtain described transmission data.
11. phonetic controllers according to claim 10, it is characterised in that also include:
Noise filtering unit, is suitable to combine the transmission data that described at least two terminal unit gathers, enters described speech data
Row noise reduction process, to filter environment noise.
12. phonetic controllers according to claim 11, it is characterised in that described noise filtering unit includes:
Noise analysis subelement, is suitable to the speech data of described at least two terminal unit be carried out noise analysis, to obtain
Filter template；
Noise filtering subelement, is suitable to make an uproar the speech data of described at least two terminal unit according to described filtering profile
Sound filters.
13. 1 kinds of speech control systems, it is characterised in that including:
Phonetic controller as described in any one of claim 7 to 12；
The speech recognition server coupled with described phonetic controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610696964.3A CN106328137A (en) | 2016-08-19 | 2016-08-19 | Voice control method, voice control device and voice control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610696964.3A CN106328137A (en) | 2016-08-19 | 2016-08-19 | Voice control method, voice control device and voice control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106328137A true CN106328137A (en) | 2017-01-11 |
Family
ID=57742260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610696964.3A Pending CN106328137A (en) | 2016-08-19 | 2016-08-19 | Voice control method, voice control device and voice control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106328137A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107195300A (en) * | 2017-05-15 | 2017-09-22 | 珠海格力电器股份有限公司 | voice control method and system |
| CN107861398A (en) * | 2017-12-21 | 2018-03-30 | 重庆金鑫科技产业发展有限公司 | The system and intelligent domestic system of a kind of voice control electric appliance |
| CN108156497A (en) * | 2018-01-02 | 2018-06-12 | 联想(北京)有限公司 | A kind of control method, control device and control system |
| CN108847231A (en) * | 2018-05-30 | 2018-11-20 | 出门问问信息科技有限公司 | Far field audio recognition method, apparatus and system |
| CN109286832A (en) * | 2017-07-20 | 2019-01-29 | 中兴通讯股份有限公司 | The method, apparatus and set-top box and computer readable storage medium of realization speech control |
| CN109308018A (en) * | 2018-11-20 | 2019-02-05 | 重庆大学 | A smart home distributed voice control system |
| CN109410929A (en) * | 2017-08-17 | 2019-03-01 | 上海擎感智能科技有限公司 | Vehicle part control method and device, computer readable storage medium, terminal |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1367619A (en) * | 2001-06-01 | 2002-09-04 | 周涛 | Multimedia wireless speech intercommunication teaching system |
| CN1637857A (en) * | 2004-01-07 | 2005-07-13 | 株式会社电装 | Noise eliminating system, sound identification system and vehicle navigation system |
| US20090292528A1 (en) * | 2008-05-21 | 2009-11-26 | Denso Corporation | Apparatus for providing information for vehicle |
| JP2011237621A (en) * | 2010-05-11 | 2011-11-24 | Honda Motor Co Ltd | Robot |
| CN103460281A (en) * | 2011-10-25 | 2013-12-18 | 奥林巴斯医疗株式会社 | System for endoscopic surgery |
| CN104599675A (en) * | 2015-02-09 | 2015-05-06 | 宇龙计算机通信科技(深圳)有限公司 | Speech processing method, device and terminal |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN105654943A (en) * | 2015-10-26 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Voice wakeup method, apparatus and system thereof |
| CN105739977A (en) * | 2016-01-26 | 2016-07-06 | 北京云知声信息技术有限公司 | Wakeup method and apparatus for voice interaction device |
| CN105741838A (en) * | 2016-01-20 | 2016-07-06 | 百度在线网络技术（北京）有限公司 | Voice wakeup method and voice wakeup device |
| CN105845135A (en) * | 2015-01-12 | 2016-08-10 | 芋头科技（杭州）有限公司 | Sound recognition system and method for robot system |
| CN105869637A (en) * | 2016-05-26 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Voice wake-up method and device |
-
2016
- 2016-08-19 CN CN201610696964.3A patent/CN106328137A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1367619A (en) * | 2001-06-01 | 2002-09-04 | 周涛 | Multimedia wireless speech intercommunication teaching system |
| CN1637857A (en) * | 2004-01-07 | 2005-07-13 | 株式会社电装 | Noise eliminating system, sound identification system and vehicle navigation system |
| US20090292528A1 (en) * | 2008-05-21 | 2009-11-26 | Denso Corporation | Apparatus for providing information for vehicle |
| JP2011237621A (en) * | 2010-05-11 | 2011-11-24 | Honda Motor Co Ltd | Robot |
| CN103460281A (en) * | 2011-10-25 | 2013-12-18 | 奥林巴斯医疗株式会社 | System for endoscopic surgery |
| CN105845135A (en) * | 2015-01-12 | 2016-08-10 | 芋头科技（杭州）有限公司 | Sound recognition system and method for robot system |
| CN104599675A (en) * | 2015-02-09 | 2015-05-06 | 宇龙计算机通信科技(深圳)有限公司 | Speech processing method, device and terminal |
| CN105654943A (en) * | 2015-10-26 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Voice wakeup method, apparatus and system thereof |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN105741838A (en) * | 2016-01-20 | 2016-07-06 | 百度在线网络技术（北京）有限公司 | Voice wakeup method and voice wakeup device |
| CN105739977A (en) * | 2016-01-26 | 2016-07-06 | 北京云知声信息技术有限公司 | Wakeup method and apparatus for voice interaction device |
| CN105869637A (en) * | 2016-05-26 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Voice wake-up method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107195300A (en) * | 2017-05-15 | 2017-09-22 | 珠海格力电器股份有限公司 | voice control method and system |
| CN107195300B (en) * | 2017-05-15 | 2019-03-19 | 珠海格力电器股份有限公司 | voice control method and system |
| CN109286832A (en) * | 2017-07-20 | 2019-01-29 | 中兴通讯股份有限公司 | The method, apparatus and set-top box and computer readable storage medium of realization speech control |
| CN109410929A (en) * | 2017-08-17 | 2019-03-01 | 上海擎感智能科技有限公司 | Vehicle part control method and device, computer readable storage medium, terminal |
| CN107861398A (en) * | 2017-12-21 | 2018-03-30 | 重庆金鑫科技产业发展有限公司 | The system and intelligent domestic system of a kind of voice control electric appliance |
| CN108156497A (en) * | 2018-01-02 | 2018-06-12 | 联想(北京)有限公司 | A kind of control method, control device and control system |
| CN108156497B (en) * | 2018-01-02 | 2020-12-18 | 联想(北京)有限公司 | Control method, control equipment and control system |
| US11301208B2 (en) | 2018-01-02 | 2022-04-12 | Lenovo (Beijing) Co., Ltd. | Control method, control device, and control system |
| CN108847231A (en) * | 2018-05-30 | 2018-11-20 | 出门问问信息科技有限公司 | Far field audio recognition method, apparatus and system |
| CN109308018A (en) * | 2018-11-20 | 2019-02-05 | 重庆大学 | A smart home distributed voice control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106328137A (en) | Voice control method, voice control device and voice control system | |
| CN110085233B (en) | Voice control method and device, electronic equipment and computer readable storage medium | |
| CN108510984A (en) | A kind of voice cooperative control method of intelligent appliance equipment | |
| US10558791B1 (en) | Setting up a system with a mobile device | |
| CN105045140A (en) | Method and device for intelligently controlling controlled equipment | |
| CN104102181A (en) | Intelligent home control method, device and system | |
| US10481569B2 (en) | Household appliance control method and device, and central processing device | |
| CN108399526A (en) | Schedule based reminding method and device | |
| WO2018041029A1 (en) | Smart router for home voice control centre, and signal transmission method therefor | |
| WO2020103397A1 (en) | Smart home system, control method, device, and medium | |
| CN105137937A (en) | Control method and device of intelligent IoT electrical appliances, and intelligent IoT electrical appliances | |
| CN103885350A (en) | Method and device for voice control over household appliances | |
| CN104360736A (en) | Gesture-based terminal control method and system | |
| CN105654953A (en) | Voice control method and system | |
| CN103310612B (en) | Main station system and the station remote control thereof of end system and system | |
| CN109147780B (en) | Voice recognition method and system under free chat scene | |
| CN103944983A (en) | Error correction method and system for voice control instruction | |
| CN104978955A (en) | Voice control method and system | |
| WO2018035986A1 (en) | Voice control method, device, and computer storage medium | |
| CN106251873A (en) | Sound control method and speech control system | |
| CN109143879A (en) | Method for controlling household appliances by taking air conditioner as center | |
| CN104978956A (en) | Voice control method and system | |
| CN105516903A (en) | Control method and system for achieving connection with multiple Bluetooth devices | |
| CN107086038A (en) | Voice control method and voice controller | |
| CN108427301A (en) | Control method, system and the control device of smart home device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170111 |