CN108520742A - Improve method, speech recognition equipment and the playing device of phonetic recognization rate - Google Patents
Improve method, speech recognition equipment and the playing device of phonetic recognization rate Download PDFInfo
- Publication number
- CN108520742A CN108520742A CN201810071058.3A CN201810071058A CN108520742A CN 108520742 A CN108520742 A CN 108520742A CN 201810071058 A CN201810071058 A CN 201810071058A CN 108520742 A CN108520742 A CN 108520742A
- Authority
- CN
- China
- Prior art keywords
- volume
- instruction
- playing device
- speech recognition
- voice playing
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000005540 biological transmission Effects 0.000 claims description 14
- 238000011038 discontinuous diafiltration by volume reduction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 4
- 230000002618 waking effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 9
- 230000008054 signal transmission Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention discloses a kind of method, speech recognition equipment and playing devices improving phonetic recognization rate.This method includes：Speech recognition equipment receives wake-up instruction input by user；Sending volume using voice playing device of the wireless signal into set distance range reduces instruction；And response wakes up instruction and enters speech recognition mode, phonetic order input by user is identified and be handled.By the above-mentioned means, the present invention can improve speech recognition equipment phonetic recognization rate, while can also reduce unnecessary cost when voice playing device is in broadcast state, the interference caused by other users is prevented.
Description
Technical field
The present invention relates to field of speech recognition, more particularly to improve the method for phonetic recognization rate, speech recognition equipment and
Playing device.
Background technology
It improves with the development of science and technology, the voice speaker products of voice assistant is supported to start universalness, in a space
(such as in a room) may be simultaneously present it is multiple support voice assistants voice speakers, and this multiple voice speaker all in
Broadcast state, at this time if user inputs phonetic order, the sound meeting that other voice speakers play to one of voice speaker
Phonetic order is received and identified to the voice speaker to interfere, and reduces the accuracy rate of speech recognition.
Invention content
The invention mainly solves the technical problem of providing the method, speech recognition equipment and the broadcastings that improve phonetic recognization rate
Device can improve speech recognition equipment phonetic recognization rate when other voice playing devices are in broadcast state.
In order to solve the above technical problems, one aspect of the present invention is：A kind of raising phonetic recognization rate is provided
Method, including：Speech recognition equipment receives wake-up instruction input by user；Using wireless signal into set distance range
Voice playing device, which sends volume, reduces instruction；And the response wake-up instruction enters speech recognition mode, with defeated to user
The phonetic order entered is identified and handles.
In order to solve the above technical problems, another technical solution used in the present invention is：A kind of raising speech recognition is provided
The method of rate, including：Voice playing device receives and parses through the volume sent by the wireless signal by speech recognition equipment
Reducing instruction, wherein the volume, which reduces, instructs the speech recognition equipment to be sent out when receiving user and waking up instruction,
The wake-up instruction is used to indicate the speech recognition equipment and enters speech recognition mode；Reducing instruction according to the volume reduces
The volume that itself is played.
The beneficial effects of the invention are as follows：The case where being different from the prior art, the present invention can receive it is input by user
After waking up instruction, the voice playing device into pre-determined distance, which sends volume, reduces instruction so that voice playing device drops
The volume of low broadcasting.To which speech recognition equipment can preferably receive phonetic order input by user, phonetic recognization rate is improved.
In addition, the voice playing device required nothing more than within the scope of pre-determined distance reduces volume, the operation for avoiding reduction volume is related to excessively
Voice playing device, reduce unnecessary resource consumption.
Description of the drawings
Fig. 1 is the flow diagram of the method first embodiment provided by the invention for improving phonetic recognization rate；
Fig. 2 is the flow diagram of the method second embodiment provided by the invention for improving phonetic recognization rate；
Fig. 3 is the structural schematic block diagram that speech recognition equipment provided by the invention is connected with voice playing device；
Fig. 4 is the structural schematic diagram of the device provided by the invention with store function.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is the flow signal of the method first embodiment provided by the invention for improving phonetic recognization rate
Figure.The method provided by the invention for improving phonetic recognization rate includes the following steps：
S101：Speech recognition equipment receives wake-up instruction input by user；
In a specific implement scene, such as in a room, there are multiple voice speakers for supporting voice assistant,
These voice speakers are in broadcast state, and respective wake-up instruction is different.When user needs one of voice sound
When case carries out an operation, wake-up instruction can be first sent out, the voice speaker is notified to prepare to receive phonetic order.
In this implement scene, user sends out wake-up instruction by the way of voice input, in other implement scenes,
It can be that user wakes up instruction by the other modes remote-transmitter such as the infrared ray of remote controler, bluetooth or WIFI, notify the language
Sound box with sound prepares to receive the phonetic order of user.
In another implement scene, inquiry instruction is periodically sent between multiple voice speakers in a room, and ring
Each inquiry instruction is answered to send respective status information, status information may include the location information and working condition of each voice speaker
Whether information, such as voice speaker are being in broadcast state.Voice speaker each in this way can recognize other of surrounding in real time
Voice speaker and itself spacing distance and their working condition.In other implement scenes, status information can be only
Including location information or work state information.Inquiry instruction and status information can be passed by any type wireless transmission method
It is defeated, such as bluetooth, WIFI, ultrasonic wave etc..
In this implement scene, speech recognition equipment is voice speaker, and in other implement scenes, speech recognition equipment is also
Can be the electric appliances such as other any electric appliances, such as mobile phone, tablet, TV or computer for supporting speech recognition.
In this implement scene, voice playing device is voice speaker, and in other implement scenes, voice playing device is also
Can be the electric appliance that mobile phone, tablet, TV or computer etc. can play sound.
S102：Sending volume using voice playing device of the wireless signal into set distance range reduces instruction；
In a specific implement scene, voice speaker has received wake-up instruction input by user, prepares to receive and use
The family phonetic order next to be inputted, and the other voice speakers of surrounding are in broadcast state at this time, environmental noise is larger,
The severe jamming identification of the voice speaker to phonetic order input by user.At this point, voice speaker can by wireless signal to
Voice playing device in set distance range, which sends volume, reduces instruction, so that the other voice speakers of surrounding are reduced and played
Volume can effectively promote discrimination of the voice speaker to phonetic order input by user to reduce ambient noise.
Furthermore only the voice speaker in set distance range is required to reduce volume, it can be to avoid the unnecessary wasting of resources, because can
There are some the voice speakers of distance farther out, the sound played will not interfere the speech recognition of the voice speaker energy,
Interference is relatively low caused by or, does not handle these voice speakers, can effectively economize on resources.
In this implement scene, wireless signal is ultrasonic signal, because the distance that ultrasonic signal itself transmits is suitable
Limited (generally 3-6 meters), and ultrasonic wave, after the objects such as wall, signal strength can become very weak, therefore be well suited for one
A limited space (such as in room) carries out signal transmission.The voice speaker sends volume by ultrasonic wave reduces instruction to week
The voice speaker enclosed makes them reduce the volume played, interference is reduced, to improve the phonetic recognization rate of itself.In addition, adopting
With ultrasonic transmission, can be not connected with network or the connection of multiple voice speakers in certain voice speakers is not the same network
When, information can be still transmitted, the stability of control is improved.
In another implement scene, wireless signal is Bluetooth signal, the communication distance of bluetooth generally between 8-30 meters,
Transmission range compared with for ultrasonic signal farther out.In another implement scene, wireless signal is WIFI signal, WIFI signal
Transmission range is generally between 10-25 meters, and transmission range is farther out compared with ultrasonic signal and Bluetooth signal.In current life pattern
Under, the ratio comparatively dense that people live, if reducing instruction using Bluetooth signal or WIFI signal transmission output level, removing can cause
Outside unnecessary resource consumption, it is also possible to other users voice playing device currently in use can be made to reduce volume, to
Affect user experience.Therefore, it if using Bluetooth signal or ultrasonic signal, needs that scheduled distance range is arranged, only
Sending volume to the voice playing device in the distance range reduces instruction.
In there are one implement scene, which is equipped with volume detector, can detect the noise of surrounding, work as inspection
When measuring the volume of noise more than predetermined threshold value, just peripherad voice speaker, which sends volume, reduces instruction.If current detection
To noise volume be not above predetermined threshold value, that is, do not interfere with the speech recognition of itself, then do not send volume reduction and refer to
It enables, the cost for sending instruction can be further reduced.
In this implement scene, inquiry instruction is periodically mutually sent between each voice speaker, and responds inquiry instruction hair
Status information, voice mail is sent to be recognized that the spacing distance with itself of other each voice speakers, so if using
Bluetooth or WIFI transmission output levels reduce instruction, the location information of each voice speaker must be just included in status information, thus
The voice speaker within the scope of pre-determined distance can be selected to send volume according to the spacing distance got reduces instruction.
It should be noted that if Bluetooth signal or WIFI signal transmission output level is taken to reduce instruction, each voice
It needs to pre-establish bluetooth connection or WIFI connections between speaker.
S103：It responds the wake-up instruction and enters speech recognition mode, phonetic order input by user to be identified
And it handles；
In a specific implement scene, the voice speaker after receiving wake-up input by user instruction, in addition to
Sending volume to other voice speakers reduces outside instruction, if itself being in broadcast state, can also reduce the volume of itself, reduces
The interference of speech recognition.After reducing interference, which enters speech recognition mode, with to following language input by user
Sound instruction is identified and handles.
According to foregoing description it is found that the speech recognition equipment of the present invention is by receiving wake-up instruction input by user
Afterwards, the voice playing device into predetermined distance range, which sends volume reduction instruction, makes it reduce the volume played, reduces surrounding
Noise jamming, promote the phonetic recognization rate of itself, while drop is required only for the voice playing device in predetermined distance range
Amount of bass avoids unnecessary resource cost.
Referring to Fig. 2, Fig. 2 is the flow signal of the method second embodiment provided by the invention for improving phonetic recognization rate
Figure.The method provided by the invention for improving phonetic recognization rate includes the following steps：
S201：Voice playing device receives and parses through the volume reduction sent by wireless signal by speech recognition equipment and refers to
It enables；
In a specific implement scene, such as in a room, there are multiple voice speakers for supporting voice assistant,
These voice speakers are in broadcast state, and respective wake-up instruction is different.When user needs one of voice sound
When case carries out an operation, wake-up instruction can be first sent out, the voice speaker is notified to enter speech recognition mode, received voice and refer to
It enables.And at this time around other voice speakers be in broadcast state, environmental noise is larger, the severe jamming voice speaker pair
The identification of phonetic order input by user.Therefore the voice speaker can be broadcast by voice of the wireless signal into set distance range
It puts device and sends volume reduction instruction, which reduces instruction and sent by wireless signal, and other voice speakers pass through the nothing
Line signal, which receives the volume, reduces instruction.The wireless signal can be any wireless signal such as bluetooth, WIFI, ultrasonic wave
Deng.
In another implement scene, inquiry instruction is periodically sent between multiple voice speakers in a room, and ring
Each inquiry instruction is answered to send respective status information, status information may include the location information and working condition of each voice speaker
Whether information, such as voice speaker are being in broadcast state.Voice speaker each in this way can recognize other of surrounding in real time
Voice speaker and itself spacing distance and their working condition.In other implement scenes, status information can be only
Including location information or work state information.Inquiry instruction and status information can pass through any type wireless signal transmission, example
Such as bluetooth, WIFI, ultrasonic wave.
In this implement scene, wireless signal is ultrasonic signal, and the distance that ultrasonic signal itself transmits is fairly limited
(generally 3-6 meters), and ultrasonic wave, after the objects such as wall, signal strength can become very weak, therefore be well suited for having at one
The space (such as in room) of limit carries out signal transmission.Using ultrasonic transmission, network can be not connected in certain voice speakers
Or the connection of multiple voice speakers be not the same network when, can still transmit information, improve the stability of control.
In another implement scene, wireless signal is Bluetooth signal, the communication distance of bluetooth generally between 8-30 meters,
Transmission range compared with for ultrasonic signal farther out.In another implement scene, wireless signal is WIFI signal, WIFI signal
For transmission range generally between 10-25 meters, transmission range is farther compared with ultrasonic signal and Bluetooth signal.In current life pattern
Under, the ratio comparatively dense that people live, if reducing instruction using Bluetooth signal or WIFI signal transmission output level, removing can cause
Outside unnecessary resource consumption, it is also possible to other users voice playing device currently in use can be made to reduce volume, to
Affect user experience.Therefore, it if using Bluetooth signal or WIFI signal, needs that scheduled distance range, and shape is arranged
The location information of each voice speaker must just be included in state information, can thus be selected pre- according to the spacing distance got
If the voice speaker in distance range, which sends volume, reduces instruction.
In this implement scene, speech recognition equipment is voice speaker, and in other implement scenes, speech recognition equipment is also
Can be the electric appliances such as other any electric appliances, such as mobile phone, tablet, TV or computer for supporting speech recognition.
In this implement scene, voice playing device is voice speaker, and in other implement scenes, voice playing device is also
Can be the electric appliance that mobile phone, tablet, TV or computer etc. can play sound.
S202：Reducing instruction according to the volume reduces the volume that itself is played.
In a specific implement scene, after voice speaker receives volume reduction instruction, judge whether itself is in
Broadcast state, if being in broadcast state, the volume for reducing itself broadcasting ignores this if being not at broadcast state
Volume reduces instruction, is not processed.
In another implement scene, when voice speaker judges that itself is in broadcast state, itself is further judged
Broadcasting volume whether be less than predetermined threshold value, if be not less than predetermined threshold value, by volume decrease down to predetermined threshold value, if low
In predetermined threshold value, then ignoring this volume reduces instruction, without processing.
In another implement scene, voice speaker volume of reception reduce instruction after directly by the volume decrease of broadcasting down to
0, the step of eliminating judgement, can accelerate the speed for reducing volume, also effectively remove noise jamming when speech recognition.
In another implement scene, status information is sent because respective inquiry instruction is responded between voice speaker,
The status information includes by location information.Spacing distance between recognizing respectively to each voice speaker, can be according to each
Spacing distance between simply estimates the threshold value for reducing volume, to make the value of volume decrease low-response, reaches both
Speech recognition is not influenced, the effect of the broadcasting of itself is nor affected on.
In the present embodiment, the volume that receives of voice playing device response, which reduces instruction, reduces the volume played, can be with
Interference when carrying out speech recognition to speech recognition equipment is effectively reduced, its phonetic recognization rate is improved.
Fig. 3 is please referred to, Fig. 3 is that the structure that speech recognition equipment provided by the invention is connected with voice playing device is shown
Meaning block diagram.Speech recognition equipment 10 includes processor 11, speech iput circuit 12 and telecommunication circuit 13, and processor 11 couples voice
Input circuit 12 and telecommunication circuit 13.Voice playing device 20 includes processor 21, player 22 and telecommunication circuit 23, processor
21 coupling players 22 and telecommunication circuit 23.When telecommunication circuit 13 and telecommunication circuit 23 are ultrasonic communication circuit, communication electricity
Road 13 and telecommunication circuit 23 need not pre-establish connection.When telecommunication circuit 13 and telecommunication circuit 23 are other wireless communication electricity
Road, such as bluetooth or WIFI telecommunication circuits, telecommunication circuit 13 and the needs of telecommunication circuit 23 pre-establish connection.
Assuming that voice playing device 20 is in running order at this time, and plays sound with higher volume, language is influenced whether
The phonetic recognization rate of sound identification device 10.At this point, the speech iput circuit 12 of speech recognition equipment 10 detects user's input
Wake-up instruction.In other implement scenes, wakes up instruction and can also be that user passes through other nothings such as infrared ray, bluetooth, WIFI
Line communication mode is inputted by telecommunication circuit 13.Processor 11 is immediately controlled telecommunication circuit 13 and uses wireless signal to speech play
Device 20, which sends volume, reduces instruction.The telecommunication circuit 23 of voice playing device 20, which receives the volume, reduces instruction, processor
21 are handled according to the instruction at once, judge whether itself is in broadcast state, if be in, control the reduction of player 22
Broadcast sound volume.If be not at, ignore this instruction, it is without any processing.
In other implement scenes, the processor of speech recognition equipment 10 can control telecommunication circuit 11 periodically to speech play
Device 20 sends inquiry instruction, and after the telecommunication circuit 23 of voice playing device 20 receives inquiry instruction, processor 21 is read should
Inquiry instructs, and responds inquiry instruction control telecommunication circuit 23 and send itself current state letter to speech recognition equipment 10
Breath.Status information may include the location information and work state information of voice playing device 20.Speech recognition equipment 10 in this way
The state of voice playing device 20 can be understood immediately.
If telecommunication circuit 13 and telecommunication circuit 23 are ultrasonic communication circuit, the distance phase that ultrasonic signal itself transmits
When limited (generally 3-6 meters), and ultrasonic wave, after the objects such as wall, signal strength can become very weak, therefore be well suited for
One limited space (such as in room) carries out signal transmission.Using ultrasonic transmission, can not connect in certain voice speakers
Connect network or multiple voice speakers connection be not the same network when, can still transmit information, improve the stabilization of control
Property.
If telecommunication circuit 13 and telecommunication circuit 23 are other radio communication circuits, such as bluetooth or WIFI telecommunication circuits,
Transmission range is farther compared with ultrasonic signal.Under current life pattern, the ratio comparatively dense that people live, if believed using bluetooth
Number or WIFI signal transmission output level reduce instruction, removing can cause outside unnecessary resource consumption, it is also possible to can make it
His user voice playing device currently in use reduces volume, to affect user experience.Therefore, if believing circuit 13 and leading to
Letter circuit 23 is other radio communication circuits, and needing setting to send volume reduces the scheduled distance range of instruction, and state is believed
The location information of each voice speaker must just be included in breath, can thus be selected scheduled according to the spacing distance got
Voice playing device 20 in distance range, which sends volume, reduces instruction.
In another implement scene, speech recognition equipment 10 is additionally provided with volume detector (not shown), volume detector
Processor 11 is coupled, the noise of surrounding can be detected, when detecting that the volume of noise is more than predetermined threshold value, processor 11 is just controlled
Telecommunication circuit 13 processed, which sends volume, reduces instruction.If currently detected noise volume is not above predetermined threshold value, that is, not
The speech recognition of itself can be influenced, then processor 11 controls telecommunication circuit 13 and do not send volume reduction instruction, can further subtract
Few cost for sending instruction.
In another implement scene, voice playing device 20 directly controls player 22 after volume of reception reduces instruction
By the volume decrease of broadcasting down to 0, the step of eliminating judgement, the speed for reducing volume can be accelerated, also effectively removed voice
Noise jamming when identification.
In another implement scene, because responding respective ask between voice playing device 20 and speech recognition equipment 10
It askes instruction and sends status information, which includes by location information.To voice playing device 20 and speech recognition
Device 10 recognize respectively between spacing distance, the processor 21 of voice playing device 20 can be according to interval between the two
Distance simply estimates the threshold value for reducing volume, so that volume is reduced corresponding value to control player 22, reaches both
Speech recognition is not influenced, the effect of the broadcasting of itself is nor affected on.
The processor 11 of speech recognition equipment also control voice identification circuit 12 is in running order, receives input by user
Phonetic order, processor 11 are identified and handle to the phonetic order received.
It is understood that in this implement scene, there are a voice playing devices 20, can in other implement scenes
With there are multiple voice playing devices 20, as described in the embodiment, details are not described herein again for operation principle.
By foregoing description it is found that the speech recognition equipment in the present embodiment is receiving wake-up instruction input by user
Afterwards, the voice playing device into preset range, which sends volume, reduces instruction, and voice playing device is receiving volume reduction
The volume of broadcasting is reduced after instruction, reduces the interference that phonetic order input by user is identified to speech recognition equipment.In addition, only right
Voice playing device in preset range requires to reduce volume, can be to avoid unnecessary cost, while being also prevented to neighbouring
Other users interfere.
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of the device provided by the invention with store function.With storage work(
At least one program or instruction 31 are stored in the device 30 of energy, program or instruction 31 are for executing as Figure 1-Figure 2 carry
The method of high phonetic recognization rate.In one embodiment, the device with store function can be storage chip in terminal, it is hard
The tool of disk either other read-write storages such as mobile hard disk or flash disk, CD, can also be server etc..
By foregoing description it is found that the program that is stored in the device embodiment with store function in the present embodiment or referring to
It enables and can be used for notifying the voice playing device within the scope of pre-determined distance to reduce broadcast sound volume, to improve speech recognition equipment
Phonetic recognization rate can also avoid unnecessary cost and prevent from interfering neighbouring other users, can be by effectively improving
User experience.
Being different from the prior art when middle voice playing device plays can interfere neighbouring speech recognition equipment to carry out voice knowledge
Not, speech recognition equipment after receiving wake-up instruction input by user, broadcast by the voice into pre-determined distance in the present invention
It puts device and sends voice reduction instruction so that voice playing device reduces the volume played, to which mitigation is to speech recognition equipment
Interference, the phonetic recognization rate of such speech recognition equipment is just improved, in addition, only to the speech play in preset range
Device, which sends volume, reduces instruction, can reduce unnecessary resource cost to avoid the control to voice playing device too far,
It is also prevented from simultaneously and other is interfered using the user of voice playing device.
Mode the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field is included within the scope of the present invention.
Claims (11)
1. a kind of method improving phonetic recognization rate, which is characterized in that including：
Speech recognition equipment receives wake-up instruction input by user；
Sending volume using voice playing device of the wireless signal into set distance range reduces instruction；And
It responds the wake-up instruction and enters speech recognition mode, phonetic order input by user is identified and be handled.
2. according to the method described in claim 1, it is characterized in that,
The wireless signal is ultrasonic signal；
The voice playing device transmission volume using from wireless signal to set distance range reduces the step of instructing and includes：
Sending volume using voice playing device of the ultrasonic signal into its ultrasonic transmission reduces instruction；Or
The wireless signal is Bluetooth signal or WIFI signal；
The voice playing device transmission volume using from wireless signal to set distance range reduces the step of instructing and includes：
In the voice playing device for pre-establishing wireless connection, the speech play in the set distance range is found out
Device, and send volume reduction to the voice playing device found out using the Bluetooth signal or the WIFI signal and refer to
It enables.
3. method according to claim 1, which is characterized in that before the wake-up instruction for receiving user, further include：
Periodically inquiry is sent to the voice playing device to instruct, and receive the voice playing device using the wireless signal
The status information replied according to inquiry instruction.
4. method according to claim 3, which is characterized in that the status information includes the position of the voice playing device
The working condition of information and/or the voice playing device；
It is described to utilize wireless signal to setpoint distance when the status information includes the working condition of the voice playing device
Voice playing device in range, which sends volume, reduces instruction, including：
Using wireless signal into set distance range and working condition be broadcast state voice playing device send volume decrease
Low instruction.
5. a kind of method improving phonetic recognization rate, which is characterized in that including：
Voice playing device is received and parsed through reduces instruction by speech recognition equipment by the volume that wireless signal is sent, wherein
The volume, which reduces, instructs the speech recognition equipment to be sent out when receiving user and waking up instruction, and the wake-up instruction is used
Enter speech recognition mode in the instruction speech recognition equipment；
Reducing instruction according to the volume reduces the volume that itself is played.
6. according to the method described in claim 5, it is characterized in that, the method further includes：
Response is instructed by the speech recognition equipment by the inquiry that the wireless signal is sent, and is instructed according to the inquiry,
By the wireless signal location information comprising itself and/or the state letter of working condition are sent to the speech recognition equipment
Breath.
7. according to the method described in claim 5, it is characterized in that, described reduced according to the volume instructs reduction itself to play
Volume the step of, including：
Judge whether itself is in broadcast state, if being in broadcast state, volume is carried out according to the reduction volume instructions
Adjustment；If being not at broadcast state, without processing.
8. the method according to the description of claim 7 is characterized in that described reduced according to the volume instructs reduction itself to play
Volume the step of, further comprise：
Judge whether the volume that itself is played is less than predetermined threshold value；
If being not less than the predetermined threshold value, by volume decrease down to the predetermined threshold value, if being less than the predetermined threshold value,
Without processing.
9. a kind of speech recognition equipment, which is characterized in that including：Processor, speech iput circuit, telecommunication circuit,
The processor couples the speech iput circuit and the telecommunication circuit, for realizing any one of such as claim 1-4
The method.
10. a kind of voice playing device, which is characterized in that including：Processor, player, telecommunication circuit,
The processor couples the player and the telecommunication circuit, for realizing such as claim 5-8 any one of them
Method.
11. a kind of device with storage function, which is characterized in that have program stored therein data, and described program data can be held
Row is to realize such as the step in any one of claim 1-8 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810071058.3A CN108520742A (en) | 2018-01-24 | 2018-01-24 | Improve method, speech recognition equipment and the playing device of phonetic recognization rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810071058.3A CN108520742A (en) | 2018-01-24 | 2018-01-24 | Improve method, speech recognition equipment and the playing device of phonetic recognization rate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108520742A true CN108520742A (en) | 2018-09-11 |
Family
ID=63432710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810071058.3A Withdrawn CN108520742A (en) | 2018-01-24 | 2018-01-24 | Improve method, speech recognition equipment and the playing device of phonetic recognization rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108520742A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658936A (en) * | 2019-01-03 | 2019-04-19 | 珠海市黑鲸软件有限公司 | A method of improving kettle phonetic recognization rate |
| CN109994119A (en) * | 2019-04-04 | 2019-07-09 | 珠海市杰理科技股份有限公司 | Wireless speech adaptive device, system and audio play control method |
| CN111210820A (en) * | 2020-01-21 | 2020-05-29 | 深圳前海达闼云端智能科技有限公司 | Robot control method, robot control device, electronic device, and storage medium |
| CN111246583A (en) * | 2020-03-27 | 2020-06-05 | 北京小米移动软件有限公司 | Wireless connection control method, apparatus and medium |
| CN111369989A (en) * | 2019-11-29 | 2020-07-03 | 添可智能科技有限公司 | Voice interaction method of cleaning equipment and cleaning equipment |
| CN111651135A (en) * | 2020-04-27 | 2020-09-11 | 珠海格力电器股份有限公司 | Sound awakening method and device, storage medium and electrical equipment |
| CN111933130A (en) * | 2019-04-24 | 2020-11-13 | 阿里巴巴集团控股有限公司 | Voice recognition method, device and system |
| CN111972920A (en) * | 2019-05-24 | 2020-11-24 | 科勒(中国)投资有限公司 | Control method, intelligent mirror and mirror cabinet |
| CN112669838A (en) * | 2020-12-17 | 2021-04-16 | 合肥飞尔智能科技有限公司 | Intelligent sound box audio playing method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070014420A1 (en) * | 2005-07-13 | 2007-01-18 | Brown William J | Auto-mute command stream by voice-activated remote control |
| CN102158606A (en) * | 2011-05-05 | 2011-08-17 | 宇龙计算机通信科技(深圳)有限公司 | Method for controlling peripheral environment volume of mobile terminal and mobile terminal |
| CN102833505A (en) * | 2012-09-14 | 2012-12-19 | 高亿实业有限公司 | Automatic regulation method and system for television volume, television and television remote control device |
| US20130169884A1 (en) * | 2012-01-02 | 2013-07-04 | Mstar Semiconductor, Inc. | Voice control system and associated control method applied to electronic apparatus |
| CN105120101A (en) * | 2015-09-01 | 2015-12-02 | 广东欧珀移动通信有限公司 | Volume control method and device of smart sound box, smart sound box and mobile terminal |
| CN106898348A (en) * | 2016-12-29 | 2017-06-27 | 北京第九实验室科技有限公司 | It is a kind of go out acoustic equipment dereverberation control method and device |
-
2018
- 2018-01-24 CN CN201810071058.3A patent/CN108520742A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070014420A1 (en) * | 2005-07-13 | 2007-01-18 | Brown William J | Auto-mute command stream by voice-activated remote control |
| CN102158606A (en) * | 2011-05-05 | 2011-08-17 | 宇龙计算机通信科技(深圳)有限公司 | Method for controlling peripheral environment volume of mobile terminal and mobile terminal |
| US20130169884A1 (en) * | 2012-01-02 | 2013-07-04 | Mstar Semiconductor, Inc. | Voice control system and associated control method applied to electronic apparatus |
| CN102833505A (en) * | 2012-09-14 | 2012-12-19 | 高亿实业有限公司 | Automatic regulation method and system for television volume, television and television remote control device |
| CN105120101A (en) * | 2015-09-01 | 2015-12-02 | 广东欧珀移动通信有限公司 | Volume control method and device of smart sound box, smart sound box and mobile terminal |
| CN106898348A (en) * | 2016-12-29 | 2017-06-27 | 北京第九实验室科技有限公司 | It is a kind of go out acoustic equipment dereverberation control method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658936A (en) * | 2019-01-03 | 2019-04-19 | 珠海市黑鲸软件有限公司 | A method of improving kettle phonetic recognization rate |
| CN109994119A (en) * | 2019-04-04 | 2019-07-09 | 珠海市杰理科技股份有限公司 | Wireless speech adaptive device, system and audio play control method |
| CN111933130A (en) * | 2019-04-24 | 2020-11-13 | 阿里巴巴集团控股有限公司 | Voice recognition method, device and system |
| CN111972920A (en) * | 2019-05-24 | 2020-11-24 | 科勒(中国)投资有限公司 | Control method, intelligent mirror and mirror cabinet |
| CN111369989A (en) * | 2019-11-29 | 2020-07-03 | 添可智能科技有限公司 | Voice interaction method of cleaning equipment and cleaning equipment |
| CN111210820A (en) * | 2020-01-21 | 2020-05-29 | 深圳前海达闼云端智能科技有限公司 | Robot control method, robot control device, electronic device, and storage medium |
| CN111246583A (en) * | 2020-03-27 | 2020-06-05 | 北京小米移动软件有限公司 | Wireless connection control method, apparatus and medium |
| CN111651135A (en) * | 2020-04-27 | 2020-09-11 | 珠海格力电器股份有限公司 | Sound awakening method and device, storage medium and electrical equipment |
| CN111651135B (en) * | 2020-04-27 | 2021-05-25 | 珠海格力电器股份有限公司 | Sound awakening method and device, storage medium and electrical equipment |
| CN112669838A (en) * | 2020-12-17 | 2021-04-16 | 合肥飞尔智能科技有限公司 | Intelligent sound box audio playing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520742A (en) | Improve method, speech recognition equipment and the playing device of phonetic recognization rate | |
| US20180182392A1 (en) | Method for performing voice control on device with microphone array, and device thereof | |
| US20180190308A1 (en) | De-reverberation control method and device of sound producing equipment | |
| CN110335601A (en) | Voice assistant equipment and its voice awakening method | |
| CN106126167B (en) | A kind of sound effect treatment method and terminal device | |
| CN110459221A (en) | The method and apparatus of more equipment collaboration interactive voices | |
| CN108449493B (en) | Voice call data processing method and device, storage medium and mobile terminal | |
| CN108024128B (en) | Control method and device for Bluetooth music playing, terminal equipment and storage medium | |
| CN106375774B (en) | Method, device and system for controlling display content of live broadcast room | |
| CN107274902A (en) | Phonetic controller and method for household electrical appliances | |
| CN108449503B (en) | Voice call data processing method and device, storage medium and mobile terminal | |
| EP3820168B1 (en) | Microphone hole blockage detection method and related product | |
| CN105848225B (en) | Wireless connection switching method and device in audio frequency broadcast system | |
| CN108449502B (en) | Voice call data processing method and device, storage medium and mobile terminal | |
| CN108712778B (en) | Channel selection method and related product | |
| CN106422325A (en) | Data interaction method and mobile terminals | |
| CN111093259A (en) | Bluetooth power adjustment method, device, storage medium and terminal | |
| CN106851014A (en) | Adjust method, device and the terminal of broadcast message queue | |
| CN108111698A (en) | A kind of incoming call reminding method and smart machine | |
| CN103995506A (en) | Background-music control method, terminals and system | |
| CN108449499B (en) | Voice call data processing method and device, storage medium and mobile terminal | |
| CN108172237A (en) | Voice communication data processing method, device, storage medium and mobile terminal | |
| CN109150675A (en) | Interaction method and device for household appliances | |
| CN105679350A (en) | Audio playing method and device | |
| CN108566706A (en) | flash lamp control method, device, terminal device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180911 |
|
| WW01 | Invention patent application withdrawn after publication |