CN104637480B - A kind of control voice recognition methods, device and system - Google Patents
A kind of control voice recognition methods, device and system Download PDFInfo
- Publication number
- CN104637480B CN104637480B CN201510042373.XA CN201510042373A CN104637480B CN 104637480 B CN104637480 B CN 104637480B CN 201510042373 A CN201510042373 A CN 201510042373A CN 104637480 B CN104637480 B CN 104637480B
- Authority
- CN
- China
- Prior art keywords
- equipment
- identified
- voice
- signal
- target identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Telephonic Communication Services (AREA)
- Selective Calling Equipment (AREA)
Abstract
The embodiment of the invention discloses a kind of control voice recognition methods, device and system, wherein, method includes：First equipment to be identified receives targeted voice signal, and generates local voice attribute information according to the targeted voice signal, and receives the voice attributes information that each second equipment to be identified is sent respectively in at least one second equipment to be identified；According to the voice attributes information that the local voice attribute information and each second equipment to be identified are sent respectively, target identification equipment is selected in the described first equipment to be identified and at least one second equipment to be identified；Recognition command is sent to the target identification equipment, so that the target identification equipment is identified the targeted voice signal according to the recognition command to obtain recognition result.Using the present invention, it can unify, voice control effectively is carried out to each music player in wireless music system.
Description
Technical field
The present invention relates to a kind of electronic technology field more particularly to control voice recognition methods, device and systems.
Background technology
Current speech recognition technology is more and more ripe, can be controlled in the prior art by speech recognition technology
The operations such as broadcasting, the pause of music player processed.For example, user says some music player " pause plays song ", then should
Music player can identify " pause play song " described in user, and be responded according to recognition result to suspend current institute
The song of broadcasting.
Now there is a kind of wireless music system in the art, which can be placed on not same district by multiple
The music player composition in domain, each music player passes through network connection each other.In existing wireless music system
Each music player can possess speech recognition technology, when user sends voice signal to existing wireless music system
When, each music player in existing wireless music system will all be identified the voice signal, due to each sound
The speech recognition duration and recognition result of happy player may having differences property, it is possible that can make in wireless music system
Each music player can not be uniformly controlled, the scene for causing control chaotic.
The content of the invention
The embodiment of the present invention provides a kind of control voice recognition methods, device and system, can unify, effectively to nothing
Each music player in line music system carries out voice control.
An embodiment of the present invention provides a kind of control voice recognition methods, including：
First equipment to be identified receives targeted voice signal, and generates local voice attribute according to the targeted voice signal
Information, and receive the voice attributes information that each second equipment to be identified is sent respectively in at least one second equipment to be identified；
First equipment to be identified is distinguished according to the local voice attribute information and each second equipment to be identified
The voice attributes information of transmission selects mesh in the described first equipment to be identified and at least one second equipment to be identified
Mark identification equipment；
First equipment to be identified sends recognition command to the target identification equipment, so that the target identification equipment
The targeted voice signal is identified according to the recognition command to obtain recognition result；
Wherein, the voice attributes information that each second equipment to be identified is sent respectively to be identified is set by described each second
What back-up was not generated according to the targeted voice signal received.
Wherein, the described first equipment to be identified is according to the local voice attribute information and each second equipment to be identified
The voice attributes information sent respectively selects in the described first equipment to be identified and at least one second equipment to be identified
Go out target identification equipment, including：
The signal reception time point included in the local voice attribute information and each second equipment to be identified
In the signal reception time point that the voice attributes information sent respectively is included, echo signal receiving time point is selected；
It selects in the described first equipment to be identified and at least one second equipment to be identified and believes with the target
Number corresponding target identification equipment of receiving time point.
Wherein, the described first equipment to be identified is according to the local voice attribute information and each second equipment to be identified
The voice attributes information sent respectively selects in the described first equipment to be identified and at least one second equipment to be identified
Go out target identification equipment, including：
The signal strength values included in the local voice attribute information and each second equipment difference to be identified
In the signal strength values that the voice attributes information of transmission is included, Target Signal Strength value is selected；
It selects in the described first equipment to be identified and at least one second equipment to be identified and believes with the target
Number corresponding target identification equipment of intensity value.
Wherein, after the described first equipment transmission recognition command to be identified to the step of target identification equipment, also
Including：
First equipment to be identified notifies that the target identification equipment control is corresponding with the recognition result to be identified
Equipment performs operation corresponding with the recognition result.
Wherein, after the described first equipment transmission recognition command to be identified to the step of target identification equipment, also
Including：
First equipment to be identified receives the recognition result that the target identification equipment is sent；
The first equipment control equipment execution to be identified corresponding with the recognition result to be identified and the identification are tied
The corresponding operation of fruit.
Correspondingly, the embodiment of the present invention also provides a kind of control voice identification device, applied to the first equipment to be identified, bag
It includes：
Generation module is received, for receiving targeted voice signal, and local voice is generated according to the targeted voice signal
Attribute information, and receive the voice attributes letter that each second equipment to be identified is sent respectively in at least one second equipment to be identified
Breath；
Selecting module, for what is sent respectively according to the local voice attribute information and each second equipment to be identified
Voice attributes information selects target identification in the described first equipment to be identified and at least one second equipment to be identified
Equipment；
Sending module, for sending recognition command to the target identification equipment so that the target identification equipment according to
The recognition command is identified the targeted voice signal to obtain recognition result；
Wherein, the voice attributes information that each second equipment to be identified is sent respectively to be identified is set by described each second
What back-up was not generated according to the targeted voice signal received.
Wherein, the selecting module includes：
Time point selecting unit, for the signal reception time point included in the local voice attribute information and institute
It states in the signal reception time point that the voice attributes information that each second equipment to be identified is sent respectively is included, selects target letter
Number receiving time point；
First object selecting unit, in the described first equipment to be identified and at least one second equipment to be identified
In select target identification equipment corresponding with the echo signal receiving time point.
Wherein, the selecting module includes：
Intensity selecting unit, for the signal strength values included in the local voice attribute information and described each
In the signal strength values that the voice attributes information that two equipment to be identified are sent respectively is included, Target Signal Strength value is selected；
Second target selection unit, in the described first equipment to be identified and at least one second equipment to be identified
In select target identification equipment corresponding with the Target Signal Strength value.
Wherein, further include：
Notification module, for notifying the target identification equipment that equipment to be identified corresponding with the recognition result is controlled to hold
Row operation corresponding with the recognition result.
Wherein, further include：
Recognition result receiving module, for receiving the recognition result that the target identification equipment is sent；
Control module, it is corresponding with the recognition result for equipment to be identified corresponding with the recognition result to be controlled to perform
Operation.
Correspondingly, the embodiment of the present invention also provides a kind of control voice identifying system, including the first equipment to be identified and extremely
Few second equipment to be identified；
First equipment to be identified includes above-mentioned control voice identification device；
Each second equipment to be identified at least one second equipment to be identified is used to receive targeted voice signal,
And corresponding voice attributes information is generated according to the targeted voice signal.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of control voice recognition methods provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of another control voice recognition methods provided in an embodiment of the present invention；
Fig. 3 is the flow diagram of another control voice recognition methods provided in an embodiment of the present invention；
Fig. 4 is a kind of structure diagram of control voice identification device provided in an embodiment of the present invention；
Fig. 5 is a kind of structure diagram of selecting module provided in an embodiment of the present invention；
Fig. 6 is a kind of structure diagram of control voice identifying system provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment belongs to the scope of protection of the invention.
Fig. 1 is referred to, is a kind of flow diagram of control voice recognition methods provided in an embodiment of the present invention, the side
Method can include：
S101, the first equipment to be identified receives targeted voice signal, and generates local language according to the targeted voice signal
Sound attribute information, and receive the voice attributes letter that each second equipment to be identified is sent respectively in at least one second equipment to be identified
Breath；
Specifically, wireless music system can include multiple equipment to be identified, each equipment to be identified all can be a kind of
Music player, such as speaker, the multiple equipment to be identified are treated including at least the first equipment to be identified and at least one second
Identification equipment.It waits to know wherein it is possible to which the music player that First is added in wireless music system is determined as described first
Other equipment can by MAC (Media Access Control, medium access control) maximum in wireless music system
The music player of location numerical value is determined as the described first equipment to be identified or can also be by other rule in wireless music system
The first equipment to be identified is selected in system.
After the described first equipment to be identified is selected in wireless music system, first equipment to be identified can be real
The voice collecting function of Shi Kaiqi microphones, when the described first equipment to be identified receives targeted voice signal, described first
Equipment to be identified can generate local voice attribute information according to the targeted voice signal, and the local voice attribute information can
To include signal reception time point and/or signal strength values.Meanwhile first equipment to be identified can also receive it is at least one
The voice attributes information that each second equipment to be identified is sent respectively in second equipment to be identified, wherein, described each second is to be identified
The voice attributes information that equipment is sent respectively is respectively according to the target language received by each second equipment to be identified
What sound signal was generated, each second equipment to be identified can also open the voice collecting function of microphone in real time, described each
The voice attributes information that second equipment to be identified is sent respectively may each comprise signal reception time point and/or signal strength values.
Wherein, the described first equipment to be identified receives the specific mistake for the voice attributes information that each second equipment to be identified is sent respectively
Journey can be：First equipment to be identified receives the voice attributes that at least one equipment to be identified is sent in wireless music system
Information, and count from generate the local voice attribute information to receive the duration of first voice attributes information, from generation institute
State local voice attribute information to receive second voice attributes information duration ..., from generating the local voice attribute
Information to receive n-th of voice attributes information duration, then judge each duration counted whether be less than default duration threshold
Value, and the equipment to be identified that the duration counted is less than corresponding to the voice attributes information of default duration threshold value is determined as the
Two equipment to be identified, to obtain at least one second equipment to be identified.It is at least one by being selected in wireless music system
Second equipment to be identified, it is ensured that received by first equipment to be identified and at least one second equipment to be identified
Targeted voice signal for identical voice signal, so as to further improve the accuracy of voice control.
S102, first equipment to be identified is according to the local voice attribute information and each second equipment to be identified
The voice attributes information sent respectively selects in the described first equipment to be identified and at least one second equipment to be identified
Go out target identification equipment；
Specifically, first equipment to be identified can be in the local voice attribute information and described each second to be identified
In the voice attributes information that equipment is sent respectively, target voice attribute information is selected, is believed with obtaining the target voice attribute
Corresponding target identification equipment is ceased, i.e., described first equipment to be identified is according to the local voice attribute information and described each second
The voice attributes information that equipment to be identified is sent respectively, in the described first equipment to be identified and described at least one second to be identified
Target identification equipment is selected in equipment.If for example, the local voice attribute information and each voice attributes information include
Signal reception time point, the signal reception time point refer to the time point for receiving the targeted voice signal, then can lead to
It crosses and earliest signal reception time point is selected to carry out selection target voice attributes information, to select target identification equipment, due to being
Earliest signal reception time point, so the target identification equipment is initially received the targeted voice signal, therefore,
The signal quality of the targeted voice signal received by the target identification equipment also can be relatively good.It is in another example if described
Local voice attribute information and each voice attributes information include signal strength values, then can be by selecting maximum signal strong
Angle value carrys out selection target voice attributes information, to select target identification equipment, due to being the largest signal strength values, so institute
It is best to state the signal quality of the targeted voice signal received by target identification equipment.
S103, first equipment to be identified sends recognition command to the target identification equipment, so that the target is known
Other equipment is identified the targeted voice signal according to the recognition command to obtain recognition result；
Specifically, after first equipment to be identified selects target identification equipment, recognition command can be sent to institute
Target identification equipment is stated, so that the target identification equipment is identified the targeted voice signal according to the recognition command
To obtain recognition result.Wherein, the non-targeted identification equipment for being not received by recognition command will not be to the targeted voice signal
It is identified；Alternatively, first equipment to be identified, which can be sent, stops recognition command to non-targeted identification equipment, so that described
Non-targeted identification equipment stopping is identified the targeted voice signal and deletes the targeted voice signal；It is described non-targeted
Identification equipment refers in the described first equipment to be identified and at least one second equipment to be identified except the target identification
Equipment to be identified beyond equipment.
Optionally, the described first equipment to be identified sends recognition command to after the target identification equipment, and described first
Equipment to be identified can also further notify the target identification equipment to control equipment to be identified corresponding with the recognition result
Perform operation corresponding with the recognition result.If for example, the recognition result is " all equipment to be identified in hall stop
Play song ", then the described first equipment to be identified can notify all to be identified in the target identification equipment control hall
Equipment stops playing song.
Optionally, the described first equipment to be identified sends recognition command to after the target identification equipment, and described first
Equipment to be identified can receive the recognition result that the target identification equipment is sent, then control corresponding with the recognition result
Equipment to be identified perform corresponding with recognition result operation.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
Fig. 2 is referred to, is the flow diagram of another control voice recognition methods provided in an embodiment of the present invention, it is described
Method can include：
S201, the first equipment to be identified receives targeted voice signal, and generates local language according to the targeted voice signal
Sound attribute information, and receive the voice attributes letter that each second equipment to be identified is sent respectively in at least one second equipment to be identified
Breath；
The specific implementation of S201 steps may refer to above-mentioned Fig. 1 and correspond to S101 steps in embodiment, here no longer
It is repeated.
S202, the signal reception time point included in the local voice attribute information and described each second to be identified
In the signal reception time point that the voice attributes information that equipment is sent respectively is included, echo signal receiving time point is selected；
Specifically, the signal reception time point refers to the time point for receiving the targeted voice signal.Described first
The signal reception time point and described each second that equipment to be identified can be included in the local voice attribute information are waited to know
In the signal reception time point that the voice attributes information that other equipment is sent respectively is included, selected according to default selection rule
Echo signal receiving time point, it is described it is default select rule can be to select earliest signal reception time point, will be most
Early signal reception time point is as echo signal receiving time point.Certainly regular selection target letter can also be selected with others
Number receiving time point, is not discussed here.
S203 is selected and the mesh in the described first equipment to be identified and at least one second equipment to be identified
Mark the corresponding target identification equipment of signal reception time point；
Specifically, after first equipment to be identified selects echo signal receiving time point, it can be described first
It is selected in equipment to be identified and at least one second equipment to be identified corresponding with the echo signal receiving time point
Target identification equipment.Wherein, by regarding earliest signal reception time point as echo signal receiving time point, it is ensured that institute
It is the equipment to be identified for being initially received the targeted voice signal, therefore, the target identification equipment to state target identification equipment
The signal quality of the received targeted voice signal also can be relatively good, so as to further improve the standard of speech recognition
True property.
S204, first equipment to be identified sends recognition command to the target identification equipment, so that the target is known
Other equipment is identified the targeted voice signal according to the recognition command to obtain recognition result；
The specific implementation of S204 steps may refer to above-mentioned Fig. 1 and correspond to S103 steps in embodiment, here no longer
It is repeated.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
Fig. 3 is referred to, is the flow diagram of another control voice recognition methods provided in an embodiment of the present invention, it is described
Method can include：
S301, the first equipment to be identified receives targeted voice signal, and generates local language according to the targeted voice signal
Sound attribute information, and receive the voice attributes letter that each second equipment to be identified is sent respectively in at least one second equipment to be identified
Breath；
The specific implementation of S301 steps may refer to above-mentioned Fig. 1 and correspond to S101 steps in embodiment, here no longer
It is repeated.
S302, the signal strength values included in the local voice attribute information and each second equipment to be identified
In the signal strength values that the voice attributes information sent respectively is included, Target Signal Strength value is selected；
Specifically, signal strength values that first equipment to be identified is included in the local voice attribute information and
In the signal strength values that the voice attributes information that each second equipment to be identified is sent respectively is included, according to default selection
Rule selects Target Signal Strength value, it is described it is default select rule can be to select maximum signal strength values, will
Maximum signal strength values are as Target Signal Strength value.Certainly regular selection target signal strength can also be selected with others
Value, is not discussed here.
S303 is selected and the mesh in the described first equipment to be identified and at least one second equipment to be identified
Mark the corresponding target identification equipment of signal strength values；
Specifically, after first equipment to be identified selects Target Signal Strength value, can wait to know described first
Target identification corresponding with the Target Signal Strength value is selected in other equipment and at least one second equipment to be identified
Equipment.Wherein, by regarding maximum signal strength values as Target Signal Strength value, it is ensured that the target identification equipment institute
The signal quality of the targeted voice signal received is best, so as to further improve the accurate of speech recognition
Property.
S304, first equipment to be identified sends recognition command to the target identification equipment, so that the target is known
Other equipment is identified the targeted voice signal according to the recognition command to obtain recognition result；
The specific implementation of S304 steps may refer to above-mentioned Fig. 1 and correspond to S103 steps in embodiment, here no longer
It is repeated.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
Fig. 4 is referred to, is a kind of structure diagram of control voice identification device 1 provided in an embodiment of the present invention, it is described
Control voice identification device 1 is applied to the first equipment to be identified, and the control voice identification device 1 can include：Receive generation
Module 10, selecting module 20, sending module 30, notification module 40, recognition result receiving module 50, control module 60；
The reception generation module 10 for receiving targeted voice signal, and generates this according to the targeted voice signal
Ground voice attributes information, and receive the voice category that each second equipment to be identified is sent respectively in at least one second equipment to be identified
Property information；
Specifically, wireless music system can include multiple equipment to be identified, each equipment to be identified all can be a kind of
Music player, such as speaker, the multiple equipment to be identified are treated including at least the first equipment to be identified and at least one second
Identification equipment.It waits to know wherein it is possible to which the music player that First is added in wireless music system is determined as described first
The music player of MAC Address numerical value maximum in wireless music system can be determined as described first and treats by other equipment
Identification equipment can also select the first equipment to be identified by other rules in wireless music system.
After the described first equipment to be identified is selected in wireless music system, first equipment to be identified can be real
The voice collecting function of Shi Kaiqi microphones, when the reception generation module 10 receives targeted voice signal, the reception
Generation module 10 can generate local voice attribute information according to the targeted voice signal, and the local voice attribute information can
To include signal reception time point and/or signal strength values.Meanwhile it is described reception generation module 10 can also receive it is at least one
The voice attributes information that each second equipment to be identified is sent respectively in second equipment to be identified, wherein, described each second is to be identified
The voice attributes information that equipment is sent respectively is respectively according to the target language received by each second equipment to be identified
What sound signal was generated, each second equipment to be identified can also open the voice collecting function of microphone in real time, described each
The voice attributes information that second equipment to be identified is sent respectively may each comprise signal reception time point and/or signal strength values.
Wherein, the specific mistake for receiving generation module 10 and receiving the voice attributes information that each second equipment to be identified is sent respectively
Journey can be：The generation module 10 that receives receives the voice attributes that at least one equipment to be identified is sent in wireless music system
Information, and count from generate the local voice attribute information to receive the duration of first voice attributes information, from generation institute
State local voice attribute information to receive second voice attributes information duration ..., from generating the local voice attribute
Information to receive n-th of voice attributes information duration, then judge each duration counted whether be less than default duration threshold
Value, and the equipment to be identified that the duration counted is less than corresponding to the voice attributes information of default duration threshold value is determined as the
Two equipment to be identified, to obtain at least one second equipment to be identified.It is at least one by being selected in wireless music system
Second equipment to be identified, it is ensured that received by first equipment to be identified and at least one second equipment to be identified
Targeted voice signal for identical voice signal, so as to further improve the accuracy of voice control.
The selecting module 20, for being distinguished according to the local voice attribute information and each second equipment to be identified
The voice attributes information of transmission selects mesh in the described first equipment to be identified and at least one second equipment to be identified
Mark identification equipment；
Specifically, the selecting module 20 can be in the local voice attribute information and each second equipment to be identified
In the voice attributes information sent respectively, target voice attribute information is selected, to obtain the target voice attribute information pair
The target identification equipment answered, i.e., described selecting module 20 to be identified are set according to the local voice attribute information and described each second
The voice attributes information that back-up is not sent is selected in the described first equipment to be identified and at least one second equipment to be identified
Select out target identification equipment.If it is received for example, the local voice attribute information and each voice attributes information include signal
Time point, the signal reception time point refer to the time point for receiving the targeted voice signal, then the selecting module 20
Can by selecting earliest signal reception time point come selection target voice attributes information, to select target identification equipment,
Due to being earliest signal reception time point, so the target identification equipment is to be initially received the targeted voice signal
, therefore, the signal quality of the targeted voice signal received by the target identification equipment also can be relatively good.Example again
Such as, if the local voice attribute information and each voice attributes information include signal strength values, the selecting module 20
Can by selecting maximum signal strength values come selection target voice attributes information, to select target identification equipment, due to
Signal strength values are the largest, so the signal quality of the targeted voice signal received by the target identification equipment is
Best.
The sending module 30, for sending recognition command to the target identification equipment, so that the target identification is set
It is standby that the targeted voice signal is identified according to the recognition command to obtain recognition result；
Specifically, after the selecting module 20 selects target identification equipment, the sending module 30 can send knowledge
The target identification equipment Ming Ling not arrived so that the target identification equipment according to the recognition command to the target language message
It number is identified to obtain recognition result.Wherein, the non-targeted identification equipment for being not received by recognition command will not be to the mesh
Poster sound signal is identified；Alternatively, the sending module 30, which can further be sent, stops recognition command to non-targeted identification
Equipment, so that the non-targeted identification equipment stopping is identified the targeted voice signal and deletes the target language message
Number；The non-targeted identification equipment refer in the described first equipment to be identified and at least one second equipment to be identified except
Equipment to be identified beyond the target identification equipment.
The notification module 40, for notifying the target identification equipment control corresponding with the recognition result to be identified
Equipment performs operation corresponding with the recognition result；
Specifically, the sending module 30 sends recognition command to after the target identification equipment, the notification module
40 can further notify target identification equipment control equipment execution to be identified corresponding with the recognition result with it is described
The corresponding operation of recognition result.If for example, the recognition result is " all equipment to be identified in hall stop playing songs ",
Then the notification module 40 can notify all equipment to be identified in the target identification equipment control hall to stop playing song
It is bent.
The recognition result receiving module 50, for receiving the recognition result that the target identification equipment is sent；
The control module 60 is tied for equipment to be identified corresponding with the recognition result to be controlled to perform with the identification
The corresponding operation of fruit；
Specifically, the sending module 30 sends recognition command to after the target identification equipment, the recognition result
Receiving module 50 can receive the recognition result that the target identification equipment is sent, then by the control module 60 control with
The corresponding equipment to be identified of the recognition result performs operation corresponding with the recognition result.
Further, then Fig. 5 is referred to, is a kind of structure diagram of selecting module 20 provided in an embodiment of the present invention,
The selecting module 20 can include：Time point selecting unit 201, first object selecting unit 202, intensity selecting unit 203,
Second target selection unit 204；
The time point selecting unit 201, for the signal reception time included in the local voice attribute information
In the signal reception time point that the voice attributes information that point and each second equipment to be identified are sent respectively is included, selection
Go out echo signal receiving time point；
Specifically, the signal reception time point refers to the time point for receiving the targeted voice signal.The time
The signal reception time point and described each second that point selection unit 201 can be included in the local voice attribute information are treated
In the signal reception time point that the voice attributes information that identification equipment is sent respectively is included, according to default selection rule selection
Go out echo signal receiving time point, it is described it is default select rule can be to select earliest signal reception time point, will
Earliest signal reception time point is as echo signal receiving time point.Certainly, the time point selecting unit 201 can also be with
The regular selection target signal reception time point of others selection, is not discussed here.
The first object selecting unit 202, for being treated in the described first equipment to be identified and described at least one second
Target identification equipment corresponding with the echo signal receiving time point is selected in identification equipment；
Specifically, after the time point selecting unit 201 selects echo signal receiving time point, the first object
Selecting unit 202 can be selected in the described first equipment to be identified and at least one second equipment to be identified with it is described
The corresponding target identification equipment of echo signal receiving time point.Wherein, by regarding earliest signal reception time point as target
Signal reception time point, it is ensured that the target identification equipment is to be initially received the to be identified of the targeted voice signal to set
Standby, therefore, the signal quality of the targeted voice signal received by the target identification equipment also can be relatively good, so as to
To further improve the accuracy of speech recognition.
The intensity selecting unit 203, for the signal strength values that are included in the local voice attribute information and
In the signal strength values that the voice attributes information that each second equipment to be identified is sent respectively is included, echo signal is selected
Intensity value；
Specifically, the intensity selecting unit 203 the signal strength values that the local voice attribute information is included with
And in the signal strength values that are included of the voice attributes information that sends respectively of each second equipment to be identified, according to default choosing
It selects rule and selects Target Signal Strength value, it is described default to select rule be to select maximum signal strength values, i.e.,
Using maximum signal strength values as Target Signal Strength value.Certainly, the intensity selecting unit 203 can also be selected with others
Regular selection target signal strength values are selected, are not discussed here.
The second target selection unit 204, for being treated in the described first equipment to be identified and described at least one second
Target identification equipment corresponding with the Target Signal Strength value is selected in identification equipment；
Specifically, after the intensity selecting unit 203 selects Target Signal Strength value, the second target selection list
Member 204 can be selected in the described first equipment to be identified and at least one second equipment to be identified to be believed with the target
Number corresponding target identification equipment of intensity value.It wherein, can be with by regarding maximum signal strength values as Target Signal Strength value
The signal quality for ensureing the targeted voice signal received by the target identification equipment is best, so as into one
Step improves the accuracy of speech recognition.
Wherein, when the time point selecting unit 201 performs corresponding operating, the intensity selecting unit 203 and described
Second target selection unit 204 can stop operation；When the intensity selecting unit 203 performs corresponding operating, the time
Point selection unit 201 and the first object selecting unit 202 can stop operation.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
Fig. 6 is referred to, is a kind of structure diagram of control voice identifying system provided in an embodiment of the present invention, the system
System can include the first equipment 300 to be identified and at least one second equipment 400 to be identified；
First equipment 300 to be identified is waited to know with each second at least one second equipment 400 to be identified
Other equipment 400 can also be connected by network each other by network connection, each second equipment 400 to be identified
It connects.
First equipment 300 to be identified can include control voice identification device, the control voice identification device pair
The specific implementation answered may refer to the control voice identification device 1 of any illustrated embodiments of above-mentioned Fig. 4 to Fig. 5, this
In no longer repeated；
Each second equipment 400 to be identified at least one second equipment 400 to be identified is used to receive target voice
Signal, and corresponding voice attributes information is generated according to the targeted voice signal.
The embodiment of the present invention receives at least one by generating local voice attribute information corresponding with targeted voice signal
The voice attributes information corresponding with targeted voice signal that each second equipment to be identified is sent respectively in a second equipment to be identified,
Target identification equipment can be selected to target language message in the first equipment to be identified and at least one second equipment to be identified
Number carry out speech recognition, you can carry out to select target identification equipment (i.e. music player) in wireless music system
Speech recognition so that speech recognition can be all carried out to avoid each music player in wireless music system, so as to unite
First, voice control effectively is carried out to each music player in wireless music system.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent variations made according to the claims of the present invention, it is still within the scope of the present invention.
Claims (11)
1. a kind of control voice recognition methods, which is characterized in that including：
First equipment to be identified receives targeted voice signal, and generates local voice attribute letter according to the targeted voice signal
Breath, and receive the voice attributes information that each second equipment to be identified is sent respectively in at least one second equipment to be identified；It is described
When the voice attributes information that local voice attribute information and each second equipment to be identified are sent respectively includes signal reception
Between point and/or signal strength values；
First equipment to be identified is sent respectively according to the local voice attribute information and each second equipment to be identified
Voice attributes information, selected in the described first equipment to be identified and at least one second equipment to be identified target knowledge
Other equipment；If the voice attributes information that each second equipment to be identified is sent respectively includes at least signal reception time point,
Then the corresponding voice attributes information of the target identification equipment includes earliest signal reception time point；If described each second waits to know
The voice attributes information that other equipment is sent respectively includes at least signal strength values, then the corresponding voice of the target identification equipment
Attribute information includes maximum signal strength values；
First equipment to be identified sends recognition command to the target identification equipment so that the target identification equipment according to
The recognition command is identified the targeted voice signal to obtain recognition result, and controls corresponding with the recognition result
Equipment to be identified perform corresponding with recognition result operation；
Wherein, the voice attributes information that each second equipment to be identified is sent respectively is by each second equipment to be identified point
It is not generated according to the targeted voice signal received.
2. the method as described in claim 1, which is characterized in that first equipment to be identified is according to the local voice attribute
The voice attributes information that information and each second equipment to be identified are sent respectively, the described first equipment to be identified and it is described extremely
Target identification equipment is selected in few second equipment to be identified, including：
The signal reception time point included in the local voice attribute information and each second equipment difference to be identified
In the signal reception time point that the voice attributes information of transmission is included, echo signal receiving time point is selected；
It selects in the described first equipment to be identified and at least one second equipment to be identified and is connect with the echo signal
Receive time point corresponding target identification equipment.
3. the method as described in claim 1, which is characterized in that first equipment to be identified is according to the local voice attribute
The voice attributes information that information and each second equipment to be identified are sent respectively, the described first equipment to be identified and it is described extremely
Target identification equipment is selected in few second equipment to be identified, including：
The signal strength values and each second equipment to be identified included in the local voice attribute information are sent respectively
The signal strength values that are included of voice attributes information in, select Target Signal Strength value；
It is selected in the described first equipment to be identified and at least one second equipment to be identified strong with the echo signal
The corresponding target identification equipment of angle value.
4. the method as described in claim 1, which is characterized in that send recognition command described in the described first equipment to be identified
After the step of target identification equipment, further include：
First equipment to be identified notifies the target identification equipment to control equipment to be identified corresponding with the recognition result
Perform operation corresponding with the recognition result.
5. the method as described in claim 1, which is characterized in that send recognition command described in the described first equipment to be identified
After the step of target identification equipment, further include：
First equipment to be identified receives the recognition result that the target identification equipment is sent；
The first equipment control equipment execution to be identified corresponding with the recognition result to be identified and the recognition result pair
The operation answered.
6. a kind of control voice identification device, applied to the first equipment to be identified, which is characterized in that including：
Generation module is received, for receiving targeted voice signal, and local voice attribute is generated according to the targeted voice signal
Information, and receive the voice attributes information that each second equipment to be identified is sent respectively in at least one second equipment to be identified；Institute
It states local voice attribute information and voice attributes information that each second equipment to be identified is sent respectively includes signal and receives
Time point and/or signal strength values；
Selecting module, for the voice sent respectively according to the local voice attribute information and each second equipment to be identified
Attribute information, in the described first equipment to be identified and at least one second equipment to be identified selecting target identification sets
It is standby；If the voice attributes information that each second equipment to be identified is sent respectively includes at least signal reception time point, institute
Stating the corresponding voice attributes information of target identification equipment includes earliest signal reception time point；If described each second to be identified sets
The voice attributes information that back-up is not sent includes at least signal strength values, then the corresponding voice attributes of the target identification equipment
Information includes maximum signal strength values；
Sending module, for sending recognition command to the target identification equipment, so that the target identification equipment is according to
Recognition command is identified the targeted voice signal to obtain recognition result, and controls treat corresponding with the recognition result
Identification equipment performs operation corresponding with the recognition result；
Wherein, the voice attributes information that each second equipment to be identified is sent respectively is by each second equipment to be identified point
It is not generated according to the targeted voice signal received.
7. device as claimed in claim 6, which is characterized in that the selecting module includes：
Time point selecting unit, for the signal reception time point that is included in the local voice attribute information and described each
In the signal reception time point that the voice attributes information that second equipment to be identified is sent respectively is included, select echo signal and connect
Receive time point；
First object selecting unit, for being selected in the described first equipment to be identified and at least one second equipment to be identified
Select out target identification equipment corresponding with the echo signal receiving time point.
8. device as claimed in claim 6, which is characterized in that the selecting module includes：
Intensity selecting unit, signal strength values and described each second for being included in the local voice attribute information are treated
In the signal strength values that the voice attributes information that identification equipment is sent respectively is included, Target Signal Strength value is selected；
Second target selection unit, for being selected in the described first equipment to be identified and at least one second equipment to be identified
Select out target identification equipment corresponding with the Target Signal Strength value.
9. device as claimed in claim 6, which is characterized in that further include：
Notification module, for target identification equipment control equipment to be identified corresponding with the recognition result to be notified to perform and
The corresponding operation of the recognition result.
10. device as claimed in claim 6, which is characterized in that further include：
Recognition result receiving module, for receiving the recognition result that the target identification equipment is sent；
Control module, for equipment to be identified corresponding with the recognition result to be controlled to perform behaviour corresponding with the recognition result
Make.
11. a kind of control voice identifying system, which is characterized in that including the first equipment to be identified and at least one second to be identified
Equipment；
First equipment to be identified includes claim 6 to 10 any one of them control voice identification device；
Each second equipment to be identified at least one second equipment to be identified is used to receive targeted voice signal, and root
Corresponding voice attributes information is generated according to the targeted voice signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510042373.XA CN104637480B (en) | 2015-01-27 | 2015-01-27 | A kind of control voice recognition methods, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510042373.XA CN104637480B (en) | 2015-01-27 | 2015-01-27 | A kind of control voice recognition methods, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104637480A CN104637480A (en) | 2015-05-20 |
| CN104637480B true CN104637480B (en) | 2018-05-29 |
Family
ID=53216151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510042373.XA Active CN104637480B (en) | 2015-01-27 | 2015-01-27 | A kind of control voice recognition methods, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104637480B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107015503A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | A kind of electric cooker controlled based on music song |
| CN107015504A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | The method that electric cooker is controlled based on song |
| CN110232924A (en) * | 2019-06-03 | 2019-09-13 | 中国第一汽车股份有限公司 | Vehicle-mounted voice management method, device, vehicle and storage medium |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4314680B2 (en) * | 1999-07-27 | 2009-08-19 | ソニー株式会社 | Speech recognition control system and speech recognition control method |
| US6901255B2 (en) * | 2001-09-05 | 2005-05-31 | Vocera Communications Inc. | Voice-controlled wireless communications system and method |
| CN1186918C (en) * | 2002-12-31 | 2005-01-26 | 艾威梯软件技术(北京)有限公司 | Method for transfering coming call for blue tooth mobile phone |
| CN1859516B (en) * | 2005-04-30 | 2010-09-29 | 艾威梯技术(北京)有限公司 | Method for one blue tooth terminal and multiple blue tooth gateway connecting to call and receive telephone |
| JP5072329B2 (en) * | 2006-11-22 | 2012-11-14 | キヤノン株式会社 | Control device and control method thereof, communication device and control method thereof, wireless communication system, and program |
| US20080228493A1 (en) * | 2007-03-12 | 2008-09-18 | Chih-Lin Hu | Determining voice commands with cooperative voice recognition |
| US8854966B2 (en) * | 2008-01-10 | 2014-10-07 | Apple Inc. | Apparatus and methods for network resource allocation |
| US8099289B2 (en) * | 2008-02-13 | 2012-01-17 | Sensory, Inc. | Voice interface and search for electronic devices including bluetooth headsets and remote systems |
| US9305548B2 (en) * | 2008-05-27 | 2016-04-05 | Voicebox Technologies Corporation | System and method for an integrated, multi-modal, multi-device natural language voice services environment |
| CN101742548B (en) * | 2009-12-22 | 2012-08-29 | 武汉虹信通信技术有限责任公司 | H.324M protocol-based 3G video telephone audio and video synchronization device and method thereof |
| US8862576B2 (en) * | 2010-01-06 | 2014-10-14 | Apple Inc. | Device, method, and graphical user interface for mapping directions between search results |
| US20130238326A1 (en) * | 2012-03-08 | 2013-09-12 | Lg Electronics Inc. | Apparatus and method for multiple device voice control |
| CN102930297B (en) * | 2012-11-05 | 2015-04-29 | 北京理工大学 | Emotion recognition method for enhancing coupling hidden markov model (HMM) voice-vision fusion |
| CN104038966B (en) * | 2013-03-05 | 2018-03-09 | 华为技术有限公司 | Data stream scheduling method and its device under long-term evolving network |
| CN103369477B (en) * | 2013-07-02 | 2016-12-07 | 华为技术有限公司 | Display media method, device, client, graphical control display packing and device |
| CN103945494B (en) * | 2014-03-21 | 2018-02-09 | 海尔集团公司 | Control the user terminal and method of intelligent appliance equipment access wireless router |
| CN104200816B (en) * | 2014-07-31 | 2017-12-22 | 广东美的制冷设备有限公司 | Sound control method and system |
-
2015
- 2015-01-27 CN CN201510042373.XA patent/CN104637480B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104637480A (en) | 2015-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11282520B2 (en) | Method, apparatus and device for interaction of intelligent voice devices, and storage medium | |
| JP5996603B2 (en) | Server, speech control method, speech apparatus, speech system, and program | |
| CN104637480B (en) | A kind of control voice recognition methods, device and system | |
| CN107274902A (en) | Phonetic controller and method for household electrical appliances | |
| CN110209799A (en) | Message treatment method, the display methods of unread message, terminal | |
| CN107480181A (en) | Audio frequency playing method, device, equipment and server | |
| CN109195090B (en) | Method and system for testing electroacoustic parameters of microphone in product | |
| CN108564966A (en) | The method and its equipment of tone testing, the device with store function | |
| CN105848225A (en) | Wireless connection switching method and device applied to audio playing system | |
| CN108335697A (en) | Minutes method, apparatus, equipment and computer-readable medium | |
| CN105022297B (en) | A kind of sound box parameter collocation method, mobile terminal | |
| CN110097868A (en) | Play the methods, devices and systems of music | |
| CN105094808A (en) | Control device and method | |
| CN105323243A (en) | Method and device for secure voice communication based on instant messaging | |
| CN103929692B (en) | Audio information processing method and electronic equipment | |
| CN110211578A (en) | Speaker control method, device and equipment | |
| CN104092809A (en) | Communication sound recording method and recorded communication sound playing method and device | |
| CN105681886B (en) | Bluetooth connection control method, device and the playback equipment of playback equipment | |
| CN103744505B (en) | Information processing method and electronic equipment | |
| CN105959466B (en) | The treating method and apparatus of audio data | |
| CN105929941A (en) | Information processing method and device, and terminal device | |
| CN110018806A (en) | A kind of method of speech processing and device | |
| CN112700767B (en) | Man-machine conversation interruption method and device | |
| CN101727899B (en) | Method and system for processing audio data | |
| CN105025353B (en) | A kind of control method for playing back and user terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |