CN104637480A - voice recognition control method, device and system - Google Patents
voice recognition control method, device and system Download PDFInfo
- Publication number
- CN104637480A CN104637480A CN201510042373.XA CN201510042373A CN104637480A CN 104637480 A CN104637480 A CN 104637480A CN 201510042373 A CN201510042373 A CN 201510042373A CN 104637480 A CN104637480 A CN 104637480A
- Authority
- CN
- China
- Prior art keywords
- equipment
- identified
- voice
- target identification
- signal
- 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.)
- Granted
Links
Abstract
The embodiment of the invention discloses a voice recognition control method, device and system, wherein the method comprises the steps that first equipment to be recognized receives target voice signals, generates local voice attribute information according to the target voice signals, and receives voice attribute information respectively sent by each second equipment to be recognized in at least one second equipment to be recognized; according to the local voice attribute information and the voice attribute information respectively sent by the second equipment to be recognized, target recognition equipment is selected out from the first equipment to be recognized and the at least one second equipment to be recognized; recognition commands are sent to the target recognition equipment so that the target recognition equipment carries out recognition on the target voice signals according to the recognition commands. When the method, the device and the system are adopted, each music player in a wireless music system can be effectively subjected voice control in a unified way.
Description
Technical field
The present invention relates to electronic technology field, particularly relate to a kind of control audio recognition method, device and system.
Background technology
Current speech recognition technology is more and more ripe, can be controlled the operation such as broadcasting, time-out of music player in prior art by speech recognition technology.Such as, user says " time-out played songs " certain music player, then this music player can identify user's said " time-out played songs ", and makes response to suspend current play song according to recognition result.
Now also have a kind of wireless music system in the art, this wireless music system can be made up of multiple music player being placed on zones of different, and each music player is connected by network each other.Each music player in existing wireless music system can possess speech recognition technology, when user sends voice signal to existing wireless music system, each music player in existing wireless music system all will identify this voice signal, because the speech recognition duration of each music player and recognition result may the property of there are differences, so each music player in wireless music system may be made cannot to unify to control, cause and control chaotic scene.
Summary of the invention
The embodiment of the present invention provides a kind of and controls audio recognition method, device and system, can unify, effectively carry out Voice command to each music player in wireless music system.
Embodiments provide a kind of control audio recognition method, comprising:
First equipment receiving target voice signal to be identified, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
The voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described;
Described first equipment to be identified sends recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal;
Wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified.
Wherein, the voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment, comprising:
In the signal reception time point that the voice attributes information that the signal reception time point comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, select echo signal time of reception point;
The target identification equipment corresponding with described echo signal time of reception point is selected in described first equipment to be identified and at least one second equipment to be identified described.
Wherein, the voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment, comprising:
In the signal strength values that the voice attributes information that the signal strength values comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, select Target Signal Strength value;
The target identification equipment corresponding with described Target Signal Strength value is selected in described first equipment to be identified and at least one second equipment to be identified described.
Wherein, described first equipment to be identified send recognition command to described target identification equipment step after, also comprise:
Described first equipment to be identified notifies that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
Wherein, described first equipment to be identified send recognition command to described target identification equipment step after, also comprise:
Described first equipment to be identified receives the described recognition result that described target identification equipment sends;
Described first equipment to be identified controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
Accordingly, the embodiment of the present invention also provides a kind of and controls speech recognition equipment, is applied to the first equipment to be identified, comprises:
Receive generation module, for receiving target voice signal, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
Select module, for the voice attributes information sent respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment;
Sending module, for sending recognition command to described target identification equipment, identifies to obtain recognition result to described targeted voice signal according to described recognition command to make described target identification equipment;
Wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified.
Wherein, described selection module comprises:
Time point selection unit, in the signal reception time point that the voice attributes information sent respectively for the signal reception time point that comprises at described local voice attribute information and described each second equipment to be identified comprises, select echo signal time of reception point;
First object selection unit, for selecting the target identification equipment corresponding with described echo signal time of reception point in described first equipment to be identified and at least one second equipment to be identified described.
Wherein, described selection module comprises:
Intensity selection unit, in the signal strength values that the voice attributes information sent respectively for the signal strength values that comprises at described local voice attribute information and described each second equipment to be identified comprises, selects Target Signal Strength value;
Second target selection unit, for selecting the target identification equipment corresponding with described Target Signal Strength value in described first equipment to be identified and at least one second equipment to be identified described.
Wherein, also comprise:
Notification module, for notifying that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
Wherein, also comprise:
Recognition result receiver module, for receiving the described recognition result that described target identification equipment sends;
Control module, performs the operation corresponding with described recognition result for controlling the equipment to be identified corresponding with described recognition result.
Accordingly, the embodiment of the present invention also provides a kind of and controls speech recognition system, comprises the first equipment to be identified and at least one second equipment to be identified;
Described first equipment to be identified comprises above-mentioned control speech recognition equipment;
Each second equipment to be identified at least one second equipment to be identified described, all for receiving target voice signal, and generates corresponding voice attributes information according to described targeted voice signal.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet controlling audio recognition method that the embodiment of the present invention provides;
Fig. 2 is the schematic flow sheet of the another kind control audio recognition method that the embodiment of the present invention provides;
Fig. 3 is the schematic flow sheet of another control audio recognition method that the embodiment of the present invention provides;
Fig. 4 is a kind of structural representation controlling speech recognition equipment that the embodiment of the present invention provides;
Fig. 5 is a kind of structural representation selecting module that the embodiment of the present invention provides;
Fig. 6 is a kind of structural representation controlling speech recognition system that the embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1, be a kind of schematic flow sheet controlling audio recognition method that the embodiment of the present invention provides, described method can comprise:
S101, the first equipment receiving target voice signal to be identified, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
Concrete, wireless music system can comprise multiple equipment to be identified, and each equipment to be identified can be all a kind of music player, such as audio amplifier, and described multiple equipment to be identified at least comprises the first equipment to be identified and at least one second equipment to be identified.Wherein, First can be defined as described first equipment to be identified by the music player joined in wireless music system, or can by MAC (Media Access Control maximum in wireless music system, medium access control) music player of address value is defined as described first equipment to be identified, or also can selects the first equipment to be identified by other rules in wireless music system.
Select described first equipment to be identified in wireless music system after, described first equipment to be identified can open the voice collecting function of microphone in real time, when described first equipment to be identified receives targeted voice signal, described first equipment to be identified can generate local voice attribute information according to described targeted voice signal, and described local voice attribute information can comprise signal reception time point and/or signal strength values.Simultaneously, described first equipment to be identified can also receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively, wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified, described each second equipment to be identified also can open the voice collecting function of microphone in real time, the voice attributes information that described each second equipment to be identified sends respectively all can comprise signal reception time point and/or signal strength values.Wherein, the detailed process that described first equipment to be identified receives the voice attributes information that described each second equipment to be identified sends respectively can be: described first equipment to be identified receives the voice attributes information that in wireless music system, at least one equipment to be identified sends, and statistics is from generating the duration of described local voice attribute information to reception first voice attributes information, from generating the duration of described local voice attribute information to reception second voice attributes information, from generating the duration of described local voice attribute information to reception n-th voice attributes information, judge whether each duration added up is less than default duration threshold value again, and the equipment to be identified corresponding to voice attributes information added up duration being less than default duration threshold value is defined as the second equipment to be identified, to obtain at least one second equipment to be identified.By selecting at least one second equipment to be identified in wireless music system, can ensure that described first equipment to be identified and at least one targeted voice signal received by the second equipment to be identified described are identical voice signal, thus voice-operated accuracy can be improved further.
S102, the voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, in the voice attributes information that described first equipment to be identified can send respectively at described local voice attribute information and described each second equipment to be identified, select target voice attribute information, to obtain target identification equipment corresponding to described target voice attribute information, namely the voice attributes information that sends respectively according to described local voice attribute information and described each second equipment to be identified of described first equipment to be identified, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described.Such as, if described local voice attribute information and each voice attributes information include signal reception time point, described signal reception time point refers to the time point receiving described targeted voice signal, then can carry out select target voice attributes information by selecting signal reception time point the earliest, to select target identification equipment, owing to being signal reception time point the earliest, so described target identification equipment receives described targeted voice signal at first, therefore, the signal quality of the described targeted voice signal received by described target identification equipment also can be relatively good.Again such as, if described local voice attribute information and each voice attributes information include signal strength values, then can carry out select target voice attributes information by selecting maximum signal strength values, to select target identification equipment, owing to being maximum signal strength values, so the signal quality of described targeted voice signal received by described target identification equipment is best.
S103, described first equipment to be identified sends recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal;
Concrete, after described first equipment choice to be identified goes out target identification equipment, recognition command can be sent to described target identification equipment, identify to obtain recognition result to described targeted voice signal according to described recognition command to make described target identification equipment.Wherein, the non-targeted identification equipment not receiving recognition command can not identify described targeted voice signal; Or described first equipment to be identified can send and stop recognition command to non-targeted identification equipment, stop making described non-targeted identification equipment identifying described targeted voice signal and deleting described targeted voice signal; Described non-targeted identification equipment refers to the equipment to be identified in described first equipment to be identified and at least one second equipment to be identified described except described target identification equipment.
Alternatively, after described first equipment to be identified sends recognition command to described target identification equipment, described first equipment to be identified can also notify that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result further.Such as, if described recognition result is " equipment all to be identified in hall stops played songs ", then described first equipment to be identified can notify that the equipment all to be identified that described target identification equipment controls in hall stops played songs.
Alternatively, after described first equipment to be identified sends recognition command to described target identification equipment, described first equipment to be identified can receive the described recognition result that described target identification equipment sends, then the control to be identified equipment corresponding with described recognition result performs the operation corresponding with described recognition result.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
Refer to Fig. 2, be the schematic flow sheet of the another kind control audio recognition method that the embodiment of the present invention provides, described method can comprise:
S201, the first equipment receiving target voice signal to be identified, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
The specific implementation of S201 step see the S101 step in the corresponding embodiment of above-mentioned Fig. 1, no longer can repeat here.
S202, in the signal reception time point that the voice attributes information that the signal reception time point comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, selects echo signal time of reception point;
Concrete, described signal reception time point refers to the time point receiving described targeted voice signal.In the signal reception time point that described first equipment to be identified can comprise at described local voice attribute information and the signal reception time point that the voice attributes information that described each second equipment to be identified sends respectively comprises, echo signal time of reception point is selected according to the selective rule preset, described default selective rule can for selecting signal reception time point the earliest, is about to signal reception time point the earliest as echo signal time of reception point.Certainly with other selective rule select target signal reception time point, no longer can also repeat here.
S203, selects the target identification equipment corresponding with described echo signal time of reception point in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, after described first equipment choice to be identified goes out echo signal time of reception point, the target identification equipment corresponding with described echo signal time of reception point can be selected in described first equipment to be identified and at least one second equipment to be identified described.Wherein, by using signal reception time point the earliest as echo signal time of reception point, can ensure that described target identification equipment is the equipment to be identified receiving described targeted voice signal at first, therefore, the signal quality of the described targeted voice signal received by described target identification equipment also can be relatively good, thus can improve the accuracy of speech recognition further.
S204, described first equipment to be identified sends recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal;
The specific implementation of S204 step see the S103 step in the corresponding embodiment of above-mentioned Fig. 1, no longer can repeat here.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
Refer to Fig. 3, be the schematic flow sheet of another control audio recognition method that the embodiment of the present invention provides, described method can comprise:
S301, the first equipment receiving target voice signal to be identified, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
The specific implementation of S301 step see the S101 step in the corresponding embodiment of above-mentioned Fig. 1, no longer can repeat here.
S302, in the signal strength values that the voice attributes information that the signal strength values comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, selects Target Signal Strength value;
Concrete, in the signal strength values that described first equipment to be identified comprises at described local voice attribute information and the signal strength values that the voice attributes information that described each second equipment to be identified sends respectively comprises, Target Signal Strength value is selected according to the selective rule preset, described default selective rule can for selecting maximum signal strength values, by maximum signal strength values as Target Signal Strength value.Certainly with other selective rule select target signal strength values, no longer can also repeat here.
S303, selects the target identification equipment corresponding with described Target Signal Strength value in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, after described first equipment choice to be identified goes out Target Signal Strength value, the target identification equipment corresponding with described Target Signal Strength value can be selected in described first equipment to be identified and at least one second equipment to be identified described.Wherein, by using maximum signal strength values as Target Signal Strength value, can ensure that the signal quality of the described targeted voice signal received by described target identification equipment is best, thus the accuracy of speech recognition can be improved further.
S304, described first equipment to be identified sends recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal;
The specific implementation of S304 step see the S103 step in the corresponding embodiment of above-mentioned Fig. 1, no longer can repeat here.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
Refer to Fig. 4, it is a kind of structural representation controlling speech recognition equipment 1 that the embodiment of the present invention provides, described control speech recognition equipment 1 is applied to the first equipment to be identified, and described control speech recognition equipment 1 can comprise: receive generation module 10, select module 20, sending module 30, notification module 40, recognition result receiver module 50, control module 60;
Described reception generation module 10, for receiving target voice signal, and generates local voice attribute information according to described targeted voice signal, and receives the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
Concrete, wireless music system can comprise multiple equipment to be identified, and each equipment to be identified can be all a kind of music player, such as audio amplifier, and described multiple equipment to be identified at least comprises the first equipment to be identified and at least one second equipment to be identified.Wherein, First can be defined as described first equipment to be identified by the music player joined in wireless music system, or the music player of MAC Address numerical value maximum in wireless music system described first equipment to be identified can be defined as, or also the first equipment to be identified can be selected by other rules in wireless music system.
Select described first equipment to be identified in wireless music system after, described first equipment to be identified can open the voice collecting function of microphone in real time, when described reception generation module 10 receives targeted voice signal, described reception generation module 10 can generate local voice attribute information according to described targeted voice signal, and described local voice attribute information can comprise signal reception time point and/or signal strength values.Simultaneously, described reception generation module 10 can also receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively, wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified, described each second equipment to be identified also can open the voice collecting function of microphone in real time, the voice attributes information that described each second equipment to be identified sends respectively all can comprise signal reception time point and/or signal strength values.Wherein, the detailed process that described reception generation module 10 receives the voice attributes information that described each second equipment to be identified sends respectively can be: described reception generation module 10 receives the voice attributes information that in wireless music system, at least one equipment to be identified sends, and statistics is from generating the duration of described local voice attribute information to reception first voice attributes information, from generating the duration of described local voice attribute information to reception second voice attributes information, from generating the duration of described local voice attribute information to reception n-th voice attributes information, judge whether each duration added up is less than default duration threshold value again, and the equipment to be identified corresponding to voice attributes information added up duration being less than default duration threshold value is defined as the second equipment to be identified, to obtain at least one second equipment to be identified.By selecting at least one second equipment to be identified in wireless music system, can ensure that described first equipment to be identified and at least one targeted voice signal received by the second equipment to be identified described are identical voice signal, thus voice-operated accuracy can be improved further.
Described selection module 20, for the voice attributes information sent respectively according to described local voice attribute information and described each second equipment to be identified, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, in the voice attributes information that described selection module 20 can send respectively at described local voice attribute information and described each second equipment to be identified, select target voice attribute information, to obtain target identification equipment corresponding to described target voice attribute information, namely the voice attributes information that sends respectively according to described local voice attribute information and described each second equipment to be identified of described selection module 20, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described.Such as, if described local voice attribute information and each voice attributes information include signal reception time point, described signal reception time point refers to the time point receiving described targeted voice signal, then described selection module 20 can carry out select target voice attributes information by selecting signal reception time point the earliest, to select target identification equipment, owing to being signal reception time point the earliest, so described target identification equipment receives described targeted voice signal at first, therefore, the signal quality of the described targeted voice signal received by described target identification equipment also can be relatively good.Again such as, if described local voice attribute information and each voice attributes information include signal strength values, then described selection module 20 can carry out select target voice attributes information by selecting maximum signal strength values, to select target identification equipment, owing to being maximum signal strength values, so the signal quality of described targeted voice signal received by described target identification equipment is best.
Described sending module 30, for sending recognition command to described target identification equipment, identifies to obtain recognition result to described targeted voice signal according to described recognition command to make described target identification equipment;
Concrete, after described selection module 20 selects target identification equipment, described sending module 30 can send recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal.Wherein, the non-targeted identification equipment not receiving recognition command can not identify described targeted voice signal; Or described sending module 30 can send further and stop recognition command to non-targeted identification equipment, stop making described non-targeted identification equipment identifying described targeted voice signal and deleting described targeted voice signal; Described non-targeted identification equipment refers to the equipment to be identified in described first equipment to be identified and at least one second equipment to be identified described except described target identification equipment.
Described notification module 40, for notifying that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result;
Concrete, after described sending module 30 sends recognition command to described target identification equipment, described notification module 40 can notify that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result further.Such as, if described recognition result is " equipment all to be identified in hall stops played songs ", then described notification module 40 can notify that the equipment all to be identified that described target identification equipment controls in hall stops played songs.
Described recognition result receiver module 50, for receiving the described recognition result that described target identification equipment sends;
Described control module 60, performs the operation corresponding with described recognition result for controlling the equipment to be identified corresponding with described recognition result;
Concrete, after described sending module 30 sends recognition command to described target identification equipment, described recognition result receiver module 50 can receive the described recognition result that described target identification equipment sends, then controls the to be identified equipment corresponding with described recognition result by described control module 60 and perform the operation corresponding with described recognition result.
Further, refer to Fig. 5 again, be a kind of structural representation selecting module 20 that the embodiment of the present invention provides, described selection module 20 can comprise: time point selection unit 201, first object selection unit 202, intensity selection unit 203, second target selection unit 204;
Described time point selection unit 201, in the signal reception time point that the voice attributes information sent respectively for the signal reception time point that comprises at described local voice attribute information and described each second equipment to be identified comprises, select echo signal time of reception point;
Concrete, described signal reception time point refers to the time point receiving described targeted voice signal.In the signal reception time point that described time point selection unit 201 can comprise at described local voice attribute information and the signal reception time point that the voice attributes information that described each second equipment to be identified sends respectively comprises, echo signal time of reception point is selected according to the selective rule preset, described default selective rule can for selecting signal reception time point the earliest, is about to signal reception time point the earliest as echo signal time of reception point.Certainly, described time point selection unit 201 with other selective rule select target signal reception time point, no longer can also repeat here.
Described first object selection unit 202, for selecting the target identification equipment corresponding with described echo signal time of reception point in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, after described time point selection unit 201 selects echo signal time of reception point, described first object selection unit 202 can select the target identification equipment corresponding with described echo signal time of reception point in described first equipment to be identified and at least one second equipment to be identified described.Wherein, by using signal reception time point the earliest as echo signal time of reception point, can ensure that described target identification equipment is the equipment to be identified receiving described targeted voice signal at first, therefore, the signal quality of the described targeted voice signal received by described target identification equipment also can be relatively good, thus can improve the accuracy of speech recognition further.
Described intensity selection unit 203, in the signal strength values that the voice attributes information sent respectively for the signal strength values that comprises at described local voice attribute information and described each second equipment to be identified comprises, selects Target Signal Strength value;
Concrete, in the signal strength values that described intensity selection unit 203 comprises at described local voice attribute information and the signal strength values that the voice attributes information that described each second equipment to be identified sends respectively comprises, Target Signal Strength value is selected according to the selective rule preset, described default selective rule can for selecting maximum signal strength values, by maximum signal strength values as Target Signal Strength value.Certainly, described intensity selection unit 203 with other selective rule select target signal strength values, no longer can also repeat here.
Described second target selection unit 204, for selecting the target identification equipment corresponding with described Target Signal Strength value in described first equipment to be identified and at least one second equipment to be identified described;
Concrete, after described intensity selection unit 203 selects Target Signal Strength value, described second target selection unit 204 can select the target identification equipment corresponding with described Target Signal Strength value in described first equipment to be identified and at least one second equipment to be identified described.Wherein, by using maximum signal strength values as Target Signal Strength value, can ensure that the signal quality of the described targeted voice signal received by described target identification equipment is best, thus the accuracy of speech recognition can be improved further.
Wherein, when described time point selection unit 201 performs corresponding operating, described intensity selection unit 203 and described second target selection unit 204 can shut-down operations; When described intensity selection unit 203 performs corresponding operating, described time point selection unit 201 and described first object selection unit 202 can shut-down operations.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
Referring to Fig. 6, is a kind of structural representation controlling speech recognition system that the embodiment of the present invention provides, and described system can comprise first equipment 300 to be identified and at least one second equipment 400 to be identified;
Described first equipment 300 to be identified all can be connected by network with each second equipment 400 to be identified at least one second equipment 400 to be identified described, and each second equipment 400 to be identified described also can be connected by network each other.
Described first equipment 300 to be identified can comprise control speech recognition equipment, the specific implementation that described control speech recognition equipment is corresponding see the described control speech recognition equipment 1 of the arbitrary illustrated embodiment of above-mentioned Fig. 4 to Fig. 5, no longer can repeat here;
Each second equipment 400 to be identified at least one second equipment 400 to be identified described, all for receiving target voice signal, and generates corresponding voice attributes information according to described targeted voice signal.
The embodiment of the present invention is by generating the local voice attribute information corresponding with targeted voice signal, and receive the voice attributes information corresponding with targeted voice signal that at least one second equipment to be identified, each second equipment to be identified sends respectively, target identification equipment can be selected in the first equipment to be identified and at least one second equipment to be identified and speech recognition is carried out to targeted voice signal, namely can select a target identification equipment (i.e. music player) and carry out speech recognition in wireless music system, make it possible to avoid each music player in wireless music system all to carry out speech recognition, thus can unify, effectively Voice command is carried out to each music player in wireless music system.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in a computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (11)
1. control an audio recognition method, it is characterized in that, comprising:
First equipment receiving target voice signal to be identified, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
The voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, selects target identification equipment in described first equipment to be identified and at least one second equipment to be identified described;
Described first equipment to be identified sends recognition command to described target identification equipment, identifies to obtain recognition result according to described recognition command to make described target identification equipment to described targeted voice signal;
Wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified.
2. the method for claim 1, it is characterized in that, the voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment, comprising:
In the signal reception time point that the voice attributes information that the signal reception time point comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, select echo signal time of reception point;
The target identification equipment corresponding with described echo signal time of reception point is selected in described first equipment to be identified and at least one second equipment to be identified described.
3. the method for claim 1, it is characterized in that, the voice attributes information that described first equipment to be identified sends respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment, comprising:
In the signal strength values that the voice attributes information that the signal strength values comprised at described local voice attribute information and described each second equipment to be identified send respectively comprises, select Target Signal Strength value;
The target identification equipment corresponding with described Target Signal Strength value is selected in described first equipment to be identified and at least one second equipment to be identified described.
4. the method for claim 1, is characterized in that, described first equipment to be identified send recognition command to described target identification equipment step after, also comprise:
Described first equipment to be identified notifies that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
5. the method for claim 1, is characterized in that, described first equipment to be identified send recognition command to described target identification equipment step after, also comprise:
Described first equipment to be identified receives the described recognition result that described target identification equipment sends;
Described first equipment to be identified controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
6. control a speech recognition equipment, be applied to the first equipment to be identified, it is characterized in that, comprising:
Receive generation module, for receiving target voice signal, and generate local voice attribute information according to described targeted voice signal, and receive the voice attributes information that at least one second equipment to be identified, each second equipment to be identified sends respectively;
Select module, for the voice attributes information sent respectively according to described local voice attribute information and described each second equipment to be identified, in described first equipment to be identified and at least one second equipment to be identified described, select target identification equipment;
Sending module, for sending recognition command to described target identification equipment, identifies to obtain recognition result to described targeted voice signal according to described recognition command to make described target identification equipment;
Wherein, the voice attributes information that described each second equipment to be identified sends respectively is generated according to the described targeted voice signal received respectively by described each second equipment to be identified.
7. device as claimed in claim 6, it is characterized in that, described selection module comprises:
Time point selection unit, in the signal reception time point that the voice attributes information sent respectively for the signal reception time point that comprises at described local voice attribute information and described each second equipment to be identified comprises, select echo signal time of reception point;
First object selection unit, for selecting the target identification equipment corresponding with described echo signal time of reception point in described first equipment to be identified and at least one second equipment to be identified described.
8. device as claimed in claim 6, it is characterized in that, described selection module comprises:
Intensity selection unit, in the signal strength values that the voice attributes information sent respectively for the signal strength values that comprises at described local voice attribute information and described each second equipment to be identified comprises, selects Target Signal Strength value;
Second target selection unit, for selecting the target identification equipment corresponding with described Target Signal Strength value in described first equipment to be identified and at least one second equipment to be identified described.
9. device as claimed in claim 6, is characterized in that, also comprise:
Notification module, for notifying that described target identification equipment controls the to be identified equipment corresponding with described recognition result and performs the operation corresponding with described recognition result.
10. device as claimed in claim 6, is characterized in that, also comprise:
Recognition result receiver module, for receiving the described recognition result that described target identification equipment sends;
Control module, performs the operation corresponding with described recognition result for controlling the equipment to be identified corresponding with described recognition result.
11. 1 kinds control speech recognition system, it is characterized in that, comprise the first equipment to be identified and at least one second equipment to be identified;
Described first equipment to be identified comprises the control speech recognition equipment described in any one of claim 6 to 10;
Each second equipment to be identified at least one second equipment to be identified described, all for receiving target voice signal, and generates corresponding voice attributes information according to described 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 true CN104637480A (en) | 2015-05-20 |
| CN104637480B 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) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107015504A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | The method that electric cooker is controlled based on song |
| CN107015503A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | A kind of electric cooker controlled based on music 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 |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1288225A (en) * | 1999-07-27 | 2001-03-21 | 索尼公司 | Speech voice identification control system, and method therefor |
| US20030045279A1 (en) * | 2001-09-05 | 2003-03-06 | Robert Shostak | Voice-controlled wireless communications system and method |
| CN1426216A (en) * | 2002-12-31 | 2003-06-25 | 艾威梯软件技术(北京)有限公司 | Method for transfering coming call for blue tooth mobile phone |
| CN1859516A (en) * | 2005-04-30 | 2006-11-08 | 艾威梯软件技术(北京)有限公司 | Method for one blue tooth terminal and multiple blue tooth gateway connecting to call and receive telephone |
| CN101188565A (en) * | 2006-11-22 | 2008-05-28 | 佳能株式会社 | Control station apparatus and control method thereof, communication apparatus and control method thereof, and wireless communication system |
| US20080228493A1 (en) * | 2007-03-12 | 2008-09-18 | Chih-Lin Hu | Determining voice commands with cooperative voice recognition |
| US20090204409A1 (en) * | 2008-02-13 | 2009-08-13 | Sensory, Incorporated | Voice Interface and Search for Electronic Devices including Bluetooth Headsets and Remote Systems |
| CN101742548A (en) * | 2009-12-22 | 2010-06-16 | 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 |
| CN101946472A (en) * | 2008-01-10 | 2011-01-12 | 苹果公司 | Apparatus and methods for network resource allocation |
| US20110167058A1 (en) * | 2010-01-06 | 2011-07-07 | Van Os Marcel | Device, Method, and Graphical User Interface for Mapping Directions Between Search Results |
| CN102930297A (en) * | 2012-11-05 | 2013-02-13 | 北京理工大学 | Emotion recognition method for enhancing coupling hidden markov model (HMM) voice-vision fusion |
| CN103369477A (en) * | 2013-07-02 | 2013-10-23 | 华为技术有限公司 | Method, device and client for displaying medium information, graphic control display method and device |
| CN103945494A (en) * | 2014-03-21 | 2014-07-23 | 海尔集团公司 | User terminal and method for controlling intelligent household appliance to have access to wireless router |
| CN104038966A (en) * | 2013-03-05 | 2014-09-10 | 华为技术有限公司 | Data flow scheduling method and apparatus under long term evolution network |
| CN104145304A (en) * | 2012-03-08 | 2014-11-12 | Lg电子株式会社 | An apparatus and method for multiple device voice control |
| CN104200816A (en) * | 2014-07-31 | 2014-12-10 | 广东美的制冷设备有限公司 | Speech control method and system |
| 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 |
-
2015
- 2015-01-27 CN CN201510042373.XA patent/CN104637480B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1288225A (en) * | 1999-07-27 | 2001-03-21 | 索尼公司 | Speech voice identification control system, and method therefor |
| US20030045279A1 (en) * | 2001-09-05 | 2003-03-06 | Robert Shostak | Voice-controlled wireless communications system and method |
| CN1426216A (en) * | 2002-12-31 | 2003-06-25 | 艾威梯软件技术(北京)有限公司 | Method for transfering coming call for blue tooth mobile phone |
| CN1859516A (en) * | 2005-04-30 | 2006-11-08 | 艾威梯软件技术(北京)有限公司 | Method for one blue tooth terminal and multiple blue tooth gateway connecting to call and receive telephone |
| CN101188565A (en) * | 2006-11-22 | 2008-05-28 | 佳能株式会社 | Control station apparatus and control method thereof, communication apparatus and control method thereof, and wireless communication system |
| US20080228493A1 (en) * | 2007-03-12 | 2008-09-18 | Chih-Lin Hu | Determining voice commands with cooperative voice recognition |
| CN101946472A (en) * | 2008-01-10 | 2011-01-12 | 苹果公司 | Apparatus and methods for network resource allocation |
| US20090204409A1 (en) * | 2008-02-13 | 2009-08-13 | Sensory, Incorporated | 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 |
| CN101742548A (en) * | 2009-12-22 | 2010-06-16 | 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 |
| US20110167058A1 (en) * | 2010-01-06 | 2011-07-07 | Van Os Marcel | Device, Method, and Graphical User Interface for Mapping Directions Between Search Results |
| CN104145304A (en) * | 2012-03-08 | 2014-11-12 | Lg电子株式会社 | An apparatus and method for multiple device voice control |
| CN102930297A (en) * | 2012-11-05 | 2013-02-13 | 北京理工大学 | Emotion recognition method for enhancing coupling hidden markov model (HMM) voice-vision fusion |
| CN104038966A (en) * | 2013-03-05 | 2014-09-10 | 华为技术有限公司 | Data flow scheduling method and apparatus under long term evolution network |
| CN103369477A (en) * | 2013-07-02 | 2013-10-23 | 华为技术有限公司 | Method, device and client for displaying medium information, graphic control display method and device |
| CN103945494A (en) * | 2014-03-21 | 2014-07-23 | 海尔集团公司 | User terminal and method for controlling intelligent household appliance to have access to wireless router |
| CN104200816A (en) * | 2014-07-31 | 2014-12-10 | 广东美的制冷设备有限公司 | Speech control method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107015504A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | The method that electric cooker is controlled based on song |
| CN107015503A (en) * | 2017-04-13 | 2017-08-04 | 马导利 | A kind of electric cooker controlled based on music 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104637480B (en) | 2018-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190012134A1 (en) | Audio playing method,apparatus, device and server | |
| CN106302997B (en) | Output control method, electronic equipment and system | |
| CN109195090B (en) | Method and system for testing electroacoustic parameters of microphone in product | |
| CN105630586A (en) | Information processing method and electronic device | |
| CN104978964A (en) | Voice control instruction error correction method and system | |
| CN105337822B (en) | A kind of selection method and relevant device of main playback equipment | |
| CN105025390B (en) | A kind of broadcasting scene store method, system, playback terminal and controlling terminal | |
| CN105094808A (en) | Control device and method | |
| CN103929692B (en) | Audio information processing method and electronic equipment | |
| CN104637480A (en) | voice recognition control method, device and system | |
| CN106024035A (en) | Audio processing method and terminal | |
| CN101931479B (en) | Method and device for playing audio signal | |
| CN104698884A (en) | Control packet method, device and system | |
| CN104660197A (en) | Volume control method and playing equipment | |
| CN105679350A (en) | Audio playing method and device | |
| CN105812905B (en) | Control method for playing back and device in a kind of audio-video frequency playing system | |
| CN112533188B (en) | Output processing method and device of play source | |
| CN105427873B (en) | A kind of switching method and relevant device of main playback equipment | |
| CN103744505B (en) | Information processing method and electronic equipment | |
| CN103414983A (en) | Method and system for achieving multi-position transmission in loudspeaker based on Bluetooth communication | |
| CN105681886B (en) | Bluetooth connection control method, device and the playback equipment of playback equipment | |
| CN108124213A (en) | A kind of method of adjustment, device and the electronic equipment of earphone music | |
| CN101727899B (en) | Method and system for processing audio data | |
| CN105959466A (en) | Method and device for processing audio data | |
| CN109473096B (en) | Intelligent voice equipment and control method thereof |
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 |
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. |
|
| CP01 | Change in the name or title of a patent holder |