CN110445931A - Speech recognition open method and electronic equipment - Google Patents
Speech recognition open method and electronic equipment Download PDFInfo
- Publication number
- CN110445931A CN110445931A CN201910706931.6A CN201910706931A CN110445931A CN 110445931 A CN110445931 A CN 110445931A CN 201910706931 A CN201910706931 A CN 201910706931A CN 110445931 A CN110445931 A CN 110445931A
- Authority
- CN
- China
- Prior art keywords
- electronic equipment
- speech recognition
- signal
- sounding
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/12—Details of telephonic subscriber devices including a sensor for measuring a physical value, e.g. temperature or motion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/22—Details of telephonic subscriber devices including a touch pad, a touch sensor or a touch detector
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/74—Details of telephonic subscriber devices with voice recognition means
Abstract
This application provides a kind of speech recognition open method and electronic equipments.The speech recognition open method includes: first when detecting that the electronic equipment meets the first preset condition, and the electronic equipment enters speech recognition triggering state.Secondly, obtaining signal associated with wearer's sounding of the electronic equipment, and detects and whether there is voice in acquired signal.Finally, if detecting in acquired signal, there are voice, the electronic equipment enters speech recognition open state by speech recognition triggering state.Herein described technical solution can make the electronic equipment enter speech recognition triggering state by speech recognition closed state first, subsequently into speech recognition open state.The speech recognition open method is more intelligent, and operation can be completed in wearer's one hand, can be used in any scene, has and use portable, intelligent advantage.
Description
Technical field
This application involves speech ciphering equipment technical fields, more particularly to speech recognition open method and electronic equipment.
Background technique
With the development of technology, intelligent wearable device can have speech identifying function.Speech identifying function is opened
It is vital for opening to the experience of entire speech recognition, while good open mode is also very big to avoiding noise jamming from playing
It helps.
In existing intelligent wearable device there are mainly two types of speech recognition open methods: one is open after touch operation
Speech recognition.For example, by releasing the button on screen, or the operations such as screen sliding are defined to open.Another is to pass through physics
Speech recognition is opened later by key pressing.
But in the open method of speech recognition in the prior art, both methods requires both hands operation, not enough just
Victory, intelligence are such as driven, hand seems inconvenient by coffee or when carrying weight in some occasions.
Summary of the invention
Based on this, it is necessary to need both hands to operate for the speech recognition open method of electronic equipment in the prior art, In
Some occasion (when taking coffee such as driving, hand or carry weight) inconvenient problems with use, provide a kind of speech recognition opening square
Method and electronic equipment.
A kind of speech recognition open method is applied to electronic equipment, comprising:
When detecting that the electronic equipment meets the first preset condition, the electronic equipment enters speech recognition triggering shape
State；
Signal associated with wearer's sounding of the electronic equipment is obtained, and detects and whether is deposited in acquired signal
In voice；
If detecting in acquired signal, there are voice, the electronic equipment enters language by speech recognition triggering state
Sound identifies open state.
First preset condition includes that the screen of the electronic equipment is in illuminating state in one of the embodiments,
And/or detect hand raising action.
The acquisition signal associated with wearer's sounding of the electronic equipment in one of the embodiments, and
Include: with the presence or absence of the step of voice in the acquired signal of detection
It is acquired by the sounding coherent signal acquisition module in the electronic equipment and is set with the electronics within a preset time
The standby associated signal of wearer's sounding, and by whether there is language in the acquired signal of Voice activity detection module detection
Sound.
The sounding coherent signal acquisition module includes: acceleration transducer and/or Mike in one of the embodiments,
Wind, the acceleration transducer is for detecting vibration caused by wearer's sounding, and the microphone is for acquiring sound letter
Number.
The acquisition signal associated with wearer's sounding of the electronic equipment in one of the embodiments, and
After the step of whether there is voice in the acquired signal of detection, the method also includes:
If detecting, there is no the voices in acquired signal, and the electronic equipment detects within a preset time
The screen is without operation, then the electronic equipment keeps the speech recognition triggering state.
The acquisition signal associated with wearer's sounding of the electronic equipment in one of the embodiments, and
After the step of whether there is voice in the acquired signal of detection, the method also includes:
If detecting, there is no the voices in acquired signal, and the electronic equipment detects within a preset time
The screen has click and/or touch operation and/or the electronic equipment to detect that screen side physical button has key
Operation, then the electronic equipment enters speech recognition closed state by the speech recognition triggering state.
If detecting in one of the embodiments, there are voices in acquired signal, and the electronic equipment is by language
After the step of sound identification triggering state enters speech recognition open state, the method also includes:
The screen of the electronic equipment shows speech animation interface, and wearer's speech identifying function is prompted to have been switched on.
A kind of electronic equipment, comprising:
Speech recognition trigger module, for when detect electronic equipment meet the first preset condition when, the electronic equipment
Into speech recognition triggering state；
Speech recognition opening module is electrically connected with the speech recognition trigger module, for obtaining and the electronic equipment
The associated signal of wearer's sounding, and detect and whether there is voice in acquired signal, if detecting acquired letter
There are voices in number, then the electronic equipment enters speech recognition open state by speech recognition triggering state.
The speech recognition opening module includes: in one of the embodiments,
Sounding coherent signal acquisition module, for acquiring signal associated with wearer's sounding of the electronic equipment；
Voice activity detection module is electrically connected with the sounding coherent signal acquisition module, for detecting acquired letter
It whether there is voice in number, the electronic equipment is triggered by speech recognition there are voice if detecting in acquired signal
State enters speech recognition open state.
The sounding coherent signal acquisition module includes: acceleration transducer and/or Mike in one of the embodiments,
Wind, the acceleration transducer are electrically connected with the Voice activity detection module, and are caused for detecting wearer's sounding
Vibration, the microphone is electrically connected with the Voice activity detection module, and is used for collected sound signal.
Compared with prior art, above-mentioned speech recognition open method and electronic equipment, first when detecting that the electronics sets
When the first preset condition of standby satisfaction, the electronic equipment enters speech recognition triggering state.Secondly, obtaining and the electronic equipment
The associated signal of wearer's sounding, and detect and whether there is voice in acquired signal.Finally, if detecting acquired
Signal in there are voices, then the electronic equipment enters speech recognition open state by speech recognition triggering state.Using upper
Technical solution is stated, the electronic equipment enters speech recognition triggering state by speech recognition closed state first, subsequently into language
Sound identifies open state, and the speech recognition open method of the electronic equipment is more intelligent, and operation can be completed in wearer's one hand,
It can be used in any scene, have and use portable, intelligent advantage.
Detailed description of the invention
Fig. 1 is the flow chart for the speech recognition open method that one embodiment of the application provides；
Fig. 2 is the structural block diagram for the electronic equipment that one embodiment of the application provides.
10 electronic equipments
100 speech recognition trigger modules
200 speech recognition opening modules
210 sounding coherent signal acquisition modules
211 acceleration transducers
212 microphones
220 Voice activity detection modules
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing to the application
Specific embodiment be described in detail.Many details are explained in the following description in order to fully understand this Shen
Please.But the application can be implemented with being much different from other way described herein, those skilled in the art can be not
Similar improvement is done in the case where violating the application intension, therefore the application is not limited by following public specific implementation.
It should be noted that it can directly on the other element when element is referred to as " being fixed on " another element
Or there may also be elements placed in the middle.When an element is considered as " connection " another element, it, which can be, is directly connected to
To another element or it may be simultaneously present centering elements.
Unless otherwise defined, all technical and scientific terms used herein and the technical field for belonging to the application
The normally understood meaning of technical staff is identical.The term used in the description of the present application is intended merely to description tool herein
The purpose of the embodiment of body, it is not intended that in limitation the application.Term " and or " used herein includes one or more phases
Any and all combinations of the listed item of pass.
Referring to Figure 1, one embodiment of the application provides a kind of speech recognition open method, is applied to electronic equipment 10, packet
It includes:
S102: when detecting that the electronic equipment 10 meets the first preset condition, the electronic equipment 10 enters voice
Identify triggering state.
In one embodiment, the electronic equipment 10 can be intelligent terminal, such as smart phone, tablet computer or
Other intelligent terminals for having speech identifying function.In one embodiment, the electronic equipment 10 can also be intelligence wearing
Equipment, such as Intelligent bracelet, smartwatch or other intelligent wearable devices for having speech identifying function.The speech recognition
Triggering state is that the electronic equipment 10 is entered a mistake during speech recognition open state by speech recognition closed state
Cross state.In the speech recognition triggering state, the electronic equipment 10 can't trigger speech identifying function.
When detecting that the electronic equipment 10 meets the first preset condition, the electronic equipment 10 is known by current voice
Other closed state enters the speech recognition triggering state.In one embodiment, first preset condition can be described
The screen of electronic equipment 10 is in illuminating state and/or detects hand raising action.Detect the screen of the electronic equipment 10
When in illuminating state and/or detecting hand raising action, the electronic equipment 10 enters speech recognition triggering state.
In one embodiment, whether can be in by the detection screen of the processor in the electronic equipment 10 and light shape
State.In one embodiment, can be by the hand raising action of the sensor senses user in the electronic equipment 10, such as can lead to
Cross the hand raising action of six axle sensors detection user.When the screen for detecting the electronic equipment 10 be in illuminating state and/or
When detecting hand raising action, the electronic equipment 10 is sent out automatically into speech recognition triggering state or the electronic equipment 10
Enter speech recognition triggering state out to prompt, wearer is reminded to carry out subsequent operation instruction according to prompt, and according to receiving
Operation instruction enters speech recognition triggering state.
S104: signal associated with wearer's sounding of the electronic equipment 10 is obtained, and detects acquired signal
In whether there is voice.
Signal associated with wearer's sounding of the electronic equipment 10 refers to: can reflect (characterization) described electronics and sets
The signal of standby 10 wearer's sounding.It is noted that the song behavior of wearer not necessarily occurs in the period of the signal.And
It is that, if the song behavior of wearer has occurred in the period of the signal, which may include the sounding of wearer, and
It further detects in the signal with the presence or absence of voice.
In some embodiments, signal associated with wearer's sounding of the electronic equipment 10 may include vibration letter
Number, at least one of voice signal and electrical signal.It in some embodiments, is vibration signal in the associated signal
In the case where, can be detected by the sensor with vibration detection function, as acceleration transducer, displacement sensor,
Any one of velocity sensor is several.In some embodiments, in the feelings that the associated signal is voice signal
Under condition, voice signal can be acquired by microphone.In one embodiment, vibrating sensor and Mike can be passed through
Wind cooperation, is respectively acquired vibration signal and voice signal.
In one embodiment, the associated signal of acquisition (obtaining) can be sent to Voice activity detection device
(Voice activity detection, VAD) carries out VAD inspection to the associated signal by Voice activity detection device
It surveys, and determines and whether there is voice in acquired signal.If detecting, there are voices in acquired signal, are thened follow the steps
S106.If detecting not there is no voice in acquired signal, return step S104 is reacquired and the electronic equipment 10
The associated signal of wearer's sounding.
S106: if detecting in acquired signal, there are voice, the electronic equipment 10 triggers shape by speech recognition
State enters speech recognition open state.
In one embodiment, if detecting in acquired signal there are voice, the electronic equipment 10 automatically by
The speech recognition triggering state enters the speech recognition open state；It can also be that the electronic equipment 10 issues and enter language
Sound identifies open state prompt, reminds wearer to carry out subsequent operation instruction according to prompt, and according to the operational order received
Into the speech recognition open state.When the electronic equipment 10 is in speech recognition open state, the electronic equipment
10 can identify voice.Wearer can carry out voice operating at this time, such as make a phone call, look into weather.
In the present embodiment, when detecting that the electronic equipment 10 meets the first preset condition, the electronic equipment 10 into
Enter speech recognition triggering state.Then, signal associated with wearer's sounding of the electronic equipment 10 is obtained, and detects institute
It whether there is voice in the signal of acquisition.If detecting in acquired signal there are voice, the electronic equipment 10 is by language
Sound identification triggering state enters speech recognition open state.By adopting the above technical scheme, the electronic equipment 10 is first by voice
Identification closed state enters speech recognition triggering state, subsequently into speech recognition open state, the language of the electronic equipment 10
Sound identifies that open method is more intelligent, and operation can be completed in wearer's one hand, can be used, has using just in any scene
It takes, intelligent advantage.
In one embodiment, described to obtain signal associated with wearer's sounding of the electronic equipment 10, and examine
Surveying in acquired signal the step of whether there is voice includes: within a preset time by the sounding phase in the electronic equipment
OFF signal acquisition module 210 acquires signal associated with wearer's sounding of the electronic equipment, and is examined by voice activity
Module 220 is surveyed to detect in acquired signal with the presence or absence of voice.
In one embodiment, the specific value of the preset time can be set according to actual needs, as 30ms,
40ms etc..In one embodiment, the sounding coherent signal acquisition module 210 may include acceleration transducer, displacement sensing
Any one of device, velocity sensor are several.In one embodiment, the sounding coherent signal acquisition module can also wrap
Include microphone.It is acquired by the sounding coherent signal acquisition module 210 related to wearer's sounding of the electronic equipment 10
The signal of connection, and transmit the signal to the Voice activity detection module 220.
VAD detection is carried out to the signal by the Voice activity detection module 220, and is in determining acquired signal
It is no that there are voices.If detecting, there are voices in acquired signal, then follow the steps S106.If detecting acquired signal
In not there is no voice, then return step S104 reacquires signal associated with wearer's sounding of the electronic equipment 10.
In one embodiment, described to obtain signal associated with wearer's sounding of the electronic equipment 10, and examine
It surveys in acquired signal after the step of whether there is voice, the method also includes: if detecting in acquired signal
There is no the voices, and the electronic equipment 10 detects the screen without operation within a preset time, then the electronics is set
Standby 10 keep the speech recognition triggering state.In one embodiment, the specific value of the preset time can be according to reality
Demand is set, such as 30ms, 40ms.
In one embodiment, the electronic equipment 10 detects that the screen refers to without operation: in the preset time
Interior, wearer does not click or touches screen, does not also carry out button operation to screen side physical button.Wearer simultaneously
It does not lift hand or puts down the movement of hand, then the electronic equipment 10 keeps the speech recognition triggering state at this time.If described
In preset time, the electronic equipment 10 detects the screen without operation, but wearer has the movement for putting down hand (can be by six
Axle sensor is detected), then at this time the electronic equipment 10 by the speech recognition triggering state enter speech recognition close
State.
In one embodiment, described to obtain signal associated with wearer's sounding of the electronic equipment 10, and examine
It surveys in acquired signal after the step of whether there is voice, the method also includes: if detecting in acquired signal
There is no the voices, and the electronic equipment 10 detects that the screen has click and/or touch in the preset time
Operation and/or the electronic equipment 10 detect that screen side physical button has button operation, then the electronic equipment 10
Speech recognition closed state is entered by the speech recognition triggering state.
In one embodiment, the preset time can be used mode described in above-described embodiment and be set.At one
In embodiment, in the preset time, the electronic equipment detects that the screen has click and/or touch operation, and/or
Detect that screen side physical button has button operation, then the electronic equipment 10 triggers shape by the speech recognition automatically
State enters speech recognition closed state.
In one embodiment, if detecting in acquired signal there are voice, the electronic equipment 10 is by voice
After the step of identification triggering state enters speech recognition open state, the method also includes: the screen of the electronic equipment 10
Curtain display speech animation interface, prompts wearer's speech identifying function to have been switched on.
In one embodiment, when the electronic equipment 10 enters speech recognition open state by speech recognition triggering state
Later, the speech identifying function of the electronic equipment 10 is triggered, and the speech identifying function of the electronic equipment 10 can be at this time
Normal use.The screen of the electronic equipment 10 can remind user speech to identify function by way of showing speech animation interface
It can have been switched on, remind user that speech identifying function can be used.In one embodiment, the electronic equipment 10 can pass through
Built-in speech input device receives phonetic order in the electronic equipment 10.For example, by built-in in the electronic equipment 10
Microphone receive the phonetic order that user issues, and corresponding operating is executed for example, when receiving according to the phonetic order that receives
To " Cha Tianqi " phonetic order when, the electronic equipment 10 executes the operation for looking into weather.
Fig. 2 is referred to, one embodiment of the application provides a kind of electronic equipment 10, comprising: 100 He of speech recognition trigger module
Speech recognition opening module 200.The speech recognition trigger module 100, which is used to work as, detects that electronic equipment 10 meets first and presets
When condition, the electronic equipment 10 enters speech recognition triggering state.The speech recognition opening module 200 is known with the voice
Other trigger module 100 is electrically connected.The speech recognition opening module 200 is sent out for obtaining with the wearer of the electronic equipment 10
The signal of acoustic correlation connection, and detect and whether there is voice in acquired signal.If detecting, there are languages in acquired signal
Sound, then the electronic equipment 10 enters speech recognition open state by speech recognition triggering state.
In one embodiment, first preset condition can be in illuminating state for the screen of the electronic equipment 10
And/or detect hand raising action.Detect that the screen of the electronic equipment 10 is in illuminating state and/or detects that lift is manual
When making, the electronic equipment 10 enters speech recognition triggering state.
Signal associated with wearer's sounding of the electronic equipment 10 refers to: can reflect (characterization) described electronics and sets
The signal of standby 10 wearer's sounding.It is noted that the song behavior of wearer not necessarily occurs in the period of the signal.And
It is that, if the song behavior of wearer has occurred in the period of the signal, which may include the sounding of wearer, and
It further detects in the signal with the presence or absence of voice.
In one embodiment, the speech recognition opening module 200 includes: 210 He of sounding coherent signal acquisition module
Voice activity detection module 220.The sounding coherent signal acquisition module 210 is for acquiring and the wearer of the electronic equipment
The associated signal of sounding.The Voice activity detection module 220 is electrically connected with the sounding coherent signal acquisition module 210.
The Voice activity detection module 220 is used to detect in acquired signal with the presence or absence of voice.If detecting acquired letter
There are voices in number, then the electronic equipment 10 enters speech recognition open state by speech recognition triggering state.
In one embodiment, the specific structure of the sounding coherent signal acquisition module 210 does not limit, and adopts as long as having
Collect the function of signal associated with wearer's sounding of the electronic equipment.In one embodiment, the sounding phase
OFF signal acquisition module 210 can be made of acceleration transducer 211 and/or microphone 212.The acceleration transducer 211 with
The Voice activity detection module 220 is electrically connected, and for detecting vibration caused by wearer's sounding.The microphone
212 are electrically connected with the Voice activity detection module 220, and are used for collected sound signal.
In one embodiment, the Voice activity detection module 220 receives the acceleration transducer 211 and/or institute
The signal of the acquisition of microphone 212 is stated, and VAD detection is carried out to the signal, so that it is determined that whether there is voice in the signal.If inspection
There are voices in signal acquired in measuring, then the electronic equipment 10 enters speech recognition by speech recognition triggering state and opens
State.To which wearer can carry out voice operating.
In conclusion the application is when detecting that the electronic equipment 10 meets the first preset condition, the electronic equipment
10 enter speech recognition triggering state.Then, signal associated with wearer's sounding of the electronic equipment 10 is obtained, and is examined
It surveys and whether there is voice in acquired signal.If detecting, there are voice, the electronic equipments 10 in acquired signal
Speech recognition open state is entered by speech recognition triggering state.The application by adopting the above technical scheme, the electronic equipment 10
Speech recognition triggering state is entered by speech recognition closed state first, subsequently into speech recognition open state, the electronics
The speech recognition open method of equipment 10 is more intelligent, and operation can be completed in wearer's one hand, can be used in any scene, tool
Have and uses portable, intelligent advantage.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of speech recognition open method is applied to electronic equipment characterized by comprising
When detecting that the electronic equipment meets the first preset condition, the electronic equipment enters speech recognition triggering state；
Signal associated with wearer's sounding of the electronic equipment is obtained, and detects and whether there is language in acquired signal
Sound；
If detecting there are voice in acquired signal, the electronic equipment, which enters voice by speech recognition triggering state, to be known
Other open state.
2. speech recognition open method as described in claim 1, which is characterized in that first preset condition includes the electricity
The screen of sub- equipment is in illuminating state and/or detects hand raising action.
3. speech recognition open method as described in claim 1, which is characterized in that the pendant of the acquisition and the electronic equipment
The associated signal of wearer's sounding, and detect the step of whether there is voice in acquired signal and include:
It is acquired and the electronic equipment by the sounding coherent signal acquisition module in the electronic equipment within a preset time
The associated signal of wearer's sounding, and by whether there is voice in the acquired signal of Voice activity detection module detection.
4. speech recognition open method as claimed in claim 3, which is characterized in that the sounding coherent signal acquisition module packet
Include: acceleration transducer and/or microphone, the acceleration transducer vibrate caused by wearer's sounding for detecting,
The microphone is used for collected sound signal.
5. speech recognition open method as described in claim 1, which is characterized in that the pendant of the acquisition and the electronic equipment
The associated signal of wearer's sounding, and after the step of detecting in acquired signal with the presence or absence of voice, the method is also wrapped
It includes:
If detecting, there is no the voices in acquired signal, and within a preset time the electronic equipment detect it is described
Screen is without operation, then the electronic equipment keeps the speech recognition triggering state.
6. speech recognition open method as claimed in claim 5, which is characterized in that the pendant of the acquisition and the electronic equipment
The associated signal of wearer's sounding, and after the step of detecting in acquired signal with the presence or absence of voice, the method is also wrapped
It includes:
If detecting, there is no the voices in acquired signal, and the electronic equipment detects in the preset time
The screen has click and/or touch operation and/or the electronic equipment to detect that screen side physical button has key
Operation, then the electronic equipment enters speech recognition closed state by the speech recognition triggering state.
7. speech recognition open method as described in claim 1, which is characterized in that exist in acquired signal if detecting
After the step of voice, the then electronic equipment enters speech recognition open state by speech recognition triggering state, the method
Further include:
The screen of the electronic equipment shows speech animation interface, and wearer's speech identifying function is prompted to have been switched on.
8. a kind of electronic equipment characterized by comprising
Speech recognition trigger module (100), for when detect electronic equipment (10) meet the first preset condition when, the electronics
Equipment (10) enters speech recognition triggering state；
Speech recognition opening module (200) is electrically connected with the speech recognition trigger module (100), for obtaining and the electricity
The associated signal of wearer's sounding of sub- equipment (10), and detect and whether there is voice in acquired signal, if detecting
There are voices in acquired signal, then the electronic equipment (10) enters speech recognition opening state by speech recognition triggering state
State.
9. electronic equipment as claimed in claim 8, which is characterized in that the speech recognition opening module (200) includes:
Sounding coherent signal acquisition module (210), for acquiring signal associated with wearer's sounding of the electronic equipment；
Voice activity detection module (220) is electrically connected with the sounding coherent signal acquisition module (210), is obtained for detecting
It whether there is voice in the signal taken, there are voices in acquired signal if detecting, the electronic equipment (10) is by language
Sound identification triggering state enters speech recognition open state.
10. electronic equipment as claimed in claim 9, which is characterized in that sounding coherent signal acquisition module (210) packet
It includes: acceleration transducer (211) and/or microphone (212), the acceleration transducer (211) and the Voice activity detection
Module (220) electrical connection, and for detecting vibration, the microphone (212) and the voice caused by wearer's sounding
Activity determination module (220) electrical connection, and it is used for collected sound signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910706931.6A CN110445931A (en) | 2019-08-01 | 2019-08-01 | Speech recognition open method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910706931.6A CN110445931A (en) | 2019-08-01 | 2019-08-01 | Speech recognition open method and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110445931A true CN110445931A (en) | 2019-11-12 |
Family
ID=68432847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910706931.6A Pending CN110445931A (en) | 2019-08-01 | 2019-08-01 | Speech recognition open method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110445931A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432303A (en) * | 2020-03-19 | 2020-07-17 | 清华大学 | Monaural headset, intelligent electronic device, method, and computer-readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383644A (en) * | 2016-09-19 | 2017-02-08 | 广东小天才科技有限公司 | Voice recognition enabling method and apparatus for electronic device |
| CN107886944A (en) * | 2017-11-16 | 2018-04-06 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
| WO2018124355A1 (en) * | 2016-12-28 | 2018-07-05 | 엘지전자 주식회사 | Audio device and control method therefor |
| CN108492825A (en) * | 2018-03-12 | 2018-09-04 | 陈火 | A kind of startup method, headset equipment and the speech recognition system of speech recognition |
| CN109308900A (en) * | 2018-10-29 | 2019-02-05 | 恒玄科技（上海）有限公司 | Headphone device, speech processing system and method for speech processing |
-
2019
- 2019-08-01 CN CN201910706931.6A patent/CN110445931A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383644A (en) * | 2016-09-19 | 2017-02-08 | 广东小天才科技有限公司 | Voice recognition enabling method and apparatus for electronic device |
| WO2018124355A1 (en) * | 2016-12-28 | 2018-07-05 | 엘지전자 주식회사 | Audio device and control method therefor |
| CN107886944A (en) * | 2017-11-16 | 2018-04-06 | 出门问问信息科技有限公司 | A kind of audio recognition method, device, equipment and storage medium |
| CN108492825A (en) * | 2018-03-12 | 2018-09-04 | 陈火 | A kind of startup method, headset equipment and the speech recognition system of speech recognition |
| CN109308900A (en) * | 2018-10-29 | 2019-02-05 | 恒玄科技（上海）有限公司 | Headphone device, speech processing system and method for speech processing |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432303A (en) * | 2020-03-19 | 2020-07-17 | 清华大学 | Monaural headset, intelligent electronic device, method, and computer-readable medium |
| CN111432303B (en) * | 2020-03-19 | 2023-01-10 | 交互未来(北京)科技有限公司 | Monaural headset, intelligent electronic device, method, and computer-readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104700832B (en) | Voiced keyword detecting system and method | |
| CN108511002A (en) | The recognition methods of hazard event voice signal, terminal and computer readable storage medium | |
| CN109982228A (en) | A kind of microphone fault detection method and mobile terminal | |
| US10430896B2 (en) | Information processing apparatus and method that receives identification and interaction information via near-field communication link | |
| CN106851026A (en) | Inactive phone number is recognized and method for cleaning, device and mobile terminal | |
| KR20160024630A (en) | Electronic device and method for displaying call information thereof | |
| CN104660817B (en) | The switching method and device of a kind of operating mode | |
| CN110097875A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN109994111A (en) | A kind of exchange method, device and mobile terminal | |
| CN106878390A (en) | Electronic pet interaction control method, device and wearable device | |
| CN109754823A (en) | A kind of voice activity detection method, mobile terminal | |
| CN109144454A (en) | double-sided screen display control method and related product | |
| CN106383644A (en) | Voice recognition enabling method and apparatus for electronic device | |
| CN107491254A (en) | A kind of gesture operation method, device and mobile terminal | |
| CN111107219B (en) | Control method and electronic equipment | |
| CN109218538A (en) | Mobile terminal screen control method, mobile terminal and computer readable storage medium | |
| CN109145088A (en) | A kind of searching method and private tutor's machine based on private tutor's machine | |
| CN108494970A (en) | Processing method, device, storage medium and the terminal of terminal's status information | |
| CN106095203B (en) | Sensing touches the calculating device and method that sound is inputted as user gesture | |
| CN110995921A (en) | Call processing method, electronic device and computer readable storage medium | |
| CN110944056A (en) | Interaction method, mobile terminal and readable storage medium | |
| CN103152481B (en) | Mobile terminal sound timing system and mobile terminal sound reporting method | |
| CN111081275A (en) | Terminal processing method and device based on sound analysis, storage medium and terminal | |
| CN110445931A (en) | Speech recognition open method and electronic equipment | |
| Diaconita et al. | Do you hear what i hear? using acoustic probing to detect smartphone locations |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191112 |
|
| RJ01 | Rejection of invention patent application after publication |