CN110234044A - A kind of voice awakening method, voice Rouser and earphone - Google Patents
A kind of voice awakening method, voice Rouser and earphone Download PDFInfo
- Publication number
- CN110234044A CN110234044A CN201910390724.4A CN201910390724A CN110234044A CN 110234044 A CN110234044 A CN 110234044A CN 201910390724 A CN201910390724 A CN 201910390724A CN 110234044 A CN110234044 A CN 110234044A
- Authority
- CN
- China
- Prior art keywords
- wake
- voice messaging
- voice
- vibration information
- earphone
- 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- Withdrawn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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1083—Reduction of ambient noise
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2201/00—Details of transducers, loudspeakers or microphones covered by H04R1/00 but not provided for in any of its subgroups
- H04R2201/10—Details of earpieces, attachments therefor, earphones or monophonic headphones covered by H04R1/10 but not provided for in any of its subgroups
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Telephone Function (AREA)
Abstract
The present embodiments relate to voice awakening technology field more particularly to a kind of voice awakening methods, voice Rouser and earphone.Voice awakening method, voice Rouser and earphone provided in an embodiment of the present invention wake up vibration information caused by voice messaging and the detection earphone wearer sounding by obtaining;When the wake-up voice messaging is matched with the default voice messaging that wakes up, and the vibration information meets preset condition, wake up instruction is generated.When this method only has while meeting the two conditions of vibration information caused by wake-up voice messaging and earphone wearer sounding, the earphone just generates wake up instruction and carries out wake actions, the False Rate that the voice messaging of user other than can reduce because of wearer generates improves the accuracy rate of voice wake-up.
Description
Technical field
The present embodiments relate to voice awakening technology fields more particularly to a kind of voice awakening method, voice to wake up dress
It sets and earphone.
Background technique
Earphone (Earphones;Headphones;Head-sets;It Earpieces) is a pair of of converting unit, it receives matchmaker
The electric signal that body player or receiver are issued converts it into the sound wave that can be heard using the loudspeaker close to ear.
Earphone can be connect by modes such as plug, bluetooths with media player, and benefit can be listened alone in the case where not influencing other people
Listen sound equipment;Also the sound that ambient enviroment can be separated, very to the people used under noisy environment of making an uproar in recording studio, DJ, journey, movement etc.
It is helpful.Earphone original is used on phone and radio, but prevailing with portable electronic devices, and earphone is chiefly used in hand
Machine, walkman, radio, portable electronic game sum digit reproducing apparatus for phonotape etc..
With the development of ear phone technology, earphone is also commonly used for the function that voice wakes up terminal.In the prior art, earphone is realized
Voice arousal function, it will usually the voice of the user other than earphone wearer is collected, to cause to judge by accident.
Summary of the invention
One purpose of the embodiment of the present invention is to provide a kind of voice awakening method, language that can be reduced voice and wake up False Rate
Sound Rouser and earphone.
In a first aspect, being applied to earphone the embodiment of the invention provides a kind of voice awakening method, which comprises
It obtains and wakes up vibration information caused by voice messaging and the detection earphone wearer sounding;
When the wake-up voice messaging is matched with the default voice messaging that wakes up, and the vibration information meets preset condition
When, generate wake up instruction.
Optionally, it under the voice detection mode, obtains and wakes up voice messaging and the detection earphone wearer sounding
Before generated vibration information, further includes:
Triggering voice messaging is obtained in real time, is determined whether to trigger voice detection mode according to the triggering voice messaging.
Optionally, the real-time acquisition triggers voice messaging, is determined whether to trigger voice according to the triggering voice messaging
Detection pattern, comprising:
Extract the energy of the triggering voice messaging;
Judge whether the energy is greater than preset energy threshold;
If so, triggering voice detection mode success, jumps acquisition and wakes up voice messaging and the detection earphone wearer
The step of vibration information caused by sounding;
If it is not, then triggering voice detection mode failure.
Optionally, the wake-up voice messaging is matched with the default voice messaging that wakes up, comprising:
Judge whether the wake-up voice messaging matches default wake-up voice messaging.
Optionally, the default wake-up voice messaging is default wake-up keyword;
It is described to judge whether the wake-up voice messaging matches default wake-up voice messaging, including;
Detect whether the wake-up voice messaging includes and preset the word for waking up Keywords matching;
If so, determining the wake-up voice messaging and default wake-up information matches;
If it is not, then waking up termination.
Optionally, the vibration information meets preset condition, comprising:
Judge whether the vibration information meets preset condition.
Optionally, the preset condition is that the frequency of vibration information is greater than default vibration frequency threshold;
It is described to judge whether the vibration information meets preset condition, comprising:
If the frequency of the vibration information is greater than predeterminated frequency threshold value, it is determined that the vibration information meets default item
Part;
If the vibration information frequency threshold is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for
Preset condition.
Optionally, it is matched when the wake-up voice messaging with wake-up voice messaging is preset described, and the vibration information
When meeting preset condition, before generating wake up instruction, the method also includes:
Verify whether the wake-up voice messaging matches with vibration information;
If so, it is described when the wake-ups voice messaging is matched with default wake-up voice messaging jumping, and vibration letter
When breath meets preset condition, the wake up instruction step is generated;
It is terminated if it is not, waking up.
Optionally, whether the verifying wake-up voice messaging matches with vibration information, comprising:
Extract the waveform for waking up voice messaging and vibration information;
Judge whether the wake-up voice messaging matches with the waveform of vibration information;
If so, determining that the wake-up voice messaging is matched with vibration information;
If not, it is determined that the wake-up voice messaging and vibration information mismatch.
Optionally, the method also includes:
Vibration information caused by the earphone wearer sounding is obtained in real time;Alternatively,
Under the voice detection mode, vibration information caused by the earphone wearer sounding is obtained.
Second aspect, the embodiment of the invention also provides a kind of voice Rousers, are applied to earphone, described device packet
It includes:
Module is obtained, wakes up vibration letter caused by voice messaging and the detection earphone wearer sounding for obtaining
Breath;
Generation module, for being matched when the wake-up voice messaging with the default voice messaging that wakes up, and the vibration information
When meeting preset condition, wake up instruction is generated.
Optionally, described device further include:
Determining module triggers voice messaging for obtaining in real time, is determined whether to trigger language according to the triggering voice messaging
Sound detection pattern;
The determining module is specifically used for extracting the energy of the triggering voice messaging;It is pre- to judge whether the energy is greater than
If energy threshold;If so, triggering voice detection mode success, jumps acquisition wake-up voice messaging and the detection earphone is worn
The step of vibration information caused by wearer's sounding;If it is not, then triggering voice detection mode failure.
Optionally, described device further include:
First judgment module, for judging whether the wake-up voice messaging matches default wake-up voice messaging;
The first judgment module be specifically used for detecting the wake-up voice messaging whether include and default wake-up keyword
Matched word;If so, determining the wake-up voice messaging and default wake-up information matches;If it is not, then waking up termination;
Second judgment module, for judging whether the vibration information meets preset condition;
If the frequency that second judgment module is specifically used for the vibration information is greater than default vibration frequency threshold, really
The fixed vibration information meets preset condition;
If the vibration information is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for default item
Part.
Optionally, described device further include:
Whether authentication module matches for verifying the wake-up voice messaging with vibration information;If so, jumping described work as
The wake-up voice messaging match with the default voice messaging that wakes up, and when the vibration information meets preset condition, generates wake-up
Instruct the step;It is terminated if it is not, waking up;
The authentication module is specifically used for extracting the waveform for waking up voice messaging and vibration information;Judge the wake-up
Whether voice messaging matches with the waveform of vibration information;If so, determining that the wake-up voice messaging is matched with vibration information;If
It is no, it is determined that the wake-up voice messaging and vibration information mismatch.
Optionally, described device further include:
Second obtains module, for obtaining vibration information caused by the earphone wearer sounding in real time;Alternatively, institute
It states under voice detection mode, obtains vibration information caused by the earphone wearer sounding.
The third aspect, the embodiment of the invention also provides a kind of earphones, comprising:
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
A processor executes, so that at least one described processor is able to carry out above-mentioned voice awakening method.
Fourth aspect, the embodiment of the present invention provide a kind of storage medium, and the storage medium is stored with executable instruction, institute
When stating executable instruction and being executed by intelligent terminal, the intelligent terminal is made to execute voice awakening method as described above.
5th aspect, the embodiment of the invention also provides a kind of program product, the machine program product includes being stored in
Program on storage media, described program include program instruction, when described program instruction is executed by intelligent terminal, make the intelligence
Terminal executes voice awakening method as described above.
Voice awakening method, voice Rouser and earphone provided in an embodiment of the present invention wake up voice letter by obtaining
Cease and detect vibration information caused by the earphone wearer sounding;When the wake-up voice messaging and the default voice that wakes up are believed
Breath matching, and when the vibration information meets preset condition, generate wake up instruction.This method, which only has while meeting, wakes up voice letter
When breath is with the two conditions of vibration information caused by earphone wearer sounding, the earphone just generates wake up instruction and is waken up
Movement, the False Rate that the voice messaging of the user other than can reduce because of wearer generates, improves the accuracy rate of voice wake-up.
Detailed description of the invention
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the application scenarios schematic diagram of voice awakening method and voice Rouser of the present invention;
Fig. 2 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 3 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 4 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 5 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 6 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 7 is the flow chart of one embodiment of voice awakening method of the present invention;
Fig. 8 is the structural schematic diagram of one embodiment of voice Rouser of the present invention;
Fig. 9 is the structural schematic diagram of one embodiment of voice Rouser of the present invention;
Figure 10 is the hardware structural diagram of earphone provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Voice awakening method and voice Rouser provided in an embodiment of the present invention are suitable for application scenarios shown in FIG. 1.
In application scenarios shown in Fig. 1, including earphone 100.Wherein, earphone 100 includes microphone array 101, vibrating sensor 102
And controller 103.The microphone array 100 includes at least one microphone in the open state, the microphone array
Column 100 are used to obtain the voice messaging of user.For obtaining user generated vibration letter occurs for the vibrating sensor 102
Breath.The voice messaging and vibration that the controller 103 is used to obtain the microphone array 101 with vibrating sensor 102 are believed
Breath is analyzed and is handled, and judges whether to generate wake-up information.
Wherein, earphone 100 can be connect with terminal, and the wake-up information is sent to terminal after generating wake-up information,
So that the terminal carries out corresponding to the movement for waking up information.For example, the terminal is mobile phone, and the earphone 100 and institute
Terminal connection is stated, the earphone 100 generates the wake-up information for waking up voice assistant, and the wake-up information is sent to the hand
Machine after the mobile phone receives the wake-up information, opens wake-up assistant's software on mobile phone.
Based on this, the embodiment of the invention provides a kind of voice awakening method, voice Rouser and earphones.
Wherein, the present invention apply example offer be applied to voice awakening method be it is a kind of can be improved voice wake up accuracy rate
Voice awakening method, specifically: it is vibrated caused by voice messaging and the detection earphone wearer sounding by obtaining to wake up
Information;It is raw when the wake-up voice messaging is matched with the default voice messaging that wakes up, and the vibration information meets preset condition
At wake up instruction.This method only meet simultaneously wake up vibration information caused by voice messaging and earphone wearer sounding this two
When a condition, the earphone just generates wake up instruction and carries out wake actions, the voice of the user other than can reduce because of wearer
The False Rate that information generates improves the accuracy rate of voice wake-up.
Wherein, a kind of voice Rouser provided in an embodiment of the present invention for running on earphone is made of software program
It can be realized the virtual bench provided in an embodiment of the present invention applied to earphone, be applied to ear with provided in an embodiment of the present invention
A kind of voice awakening method of machine is based on identical inventive concept, technical characteristic having the same and beneficial effect.
Wherein, earphone provided in an embodiment of the present invention is able to carry out voice awakening method provided in an embodiment of the present invention, or
Person runs voice Rouser provided in an embodiment of the present invention.
It should be noted that it is above it is merely exemplary show a kind of form of application scenarios, the embodiment of the present invention provides
Voice awakening method can also further be extended in other suitable application environments, and be not limited to answer shown in Fig. 1
Use environment.
Fig. 2 is the flow chart of one embodiment of voice awakening method provided in an embodiment of the present invention, and the voice wakes up
Method can be executed by the earphone 100 in Fig. 1, as shown in Fig. 2, the voice awakening method includes:
S210: it obtains and wakes up vibration information caused by voice messaging and the detection earphone wearer sounding;
In the present embodiment, the earphone 100 is preset with a voice detection mode, only in the voice detection mode
Under, the earphone 100 to the wake-up voice messaging and vibration information could obtain and be handled with analysis.The wake-up voice
Information can be a Duan Yuyin, for example, it is described wake up voice messaging can for voice " wake up voice assistant " that user issues this is short
Sentence, described " wake-up " this word that wakes up voice messaging and can also issue for user, specifically waking up voice messaging can be according to user
The setting of demand self-defining.The vibration information refers to that the vibrating sensor is produced when speaking by the earphone wearer
The electric signal that is converted into of vibration, which is vibration signal.
Wherein, it when the voice detection mode starts, carries out waking up obtaining for voice messaging by the microphone array 101
It takes, meanwhile, trigger the acquisition that the vibrating sensor 102 carries out vibration information.Alternatively, when the voice detection mode is opened,
The acquisition for wake up by the microphone array 101 voice messaging, in the microphone array 101 to the wake-up language
During message breath is obtained, by the vibrating sensor 102 to vibration information caused by earphone wearer's sounding
It is obtained.Or the vibration microphone is constantly in open state, obtains the vibration information in real time.In other words,
The acquisition time of the vibration information can be later than the acquisition time point for waking up voice messaging slightly, and because of the vibration information
It is to be generated according to the wake-up voice messaging, therefore obtaining for vibration information need to be in the mistake of the wake-up voice messaging acquisition
It is obtained in journey.
Preferably, described to obtain the start-up time for waking up voice messaging and detect caused by the earphone wearer sounding
Vibration information start-up time is identical.
In some embodiments, for the opening time of the voice detection mode to can be preset.For example, user is preparatory
Opening time provided with the voice detection mode is 1 minute, when the earphone 100 opens voice detection mode one minute
Later, the earphone 100 is automatically closed the voice detection mode, stops described waking up obtaining for voice messaging and vibration information
It takes.The setting of the opening time of the voice detection mode can shift to an earlier date and carry out in the terminal communicated to connect with the earphone 100
Setting, enters the Setting pattern of the earphone 100 in the terminal, and the voice detection mode of earphone 100 described in self-setting is opened
Open duration.Certainly, the opening time of the voice detection mode is not restricted by, and user can self-defining.
S220: when the wake-up voice messaging match with the default voice messaging that wakes up, and the vibration information meets and presets
When condition, wake up instruction is generated.
Wherein, the earphone is when getting the wake-up voice messaging and vibration information, to the wake-up voice messaging
It is analyzed and processed with vibration information, when the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.Specifically, the default wake-up voice messaging refers to that user is pre-set and calls out
Awake voice messaging, when the earphone 100 gets wake-up voice messaging under voice detection mode, by the wake-up voice messaging
It is matched with default wake-up voice messaging.For example, the pre-set default wake-up voice messaging of the earphone 100 is
" waking up voice assistant " corresponding voice messaging of this short sentence, getting under voice detection mode and waking up voice messaging is also " to call out
When the corresponding wake-up voice messaging of awake voice assistant ", that is, illustrate that the wake-up voice messaging is matched with the default voice messaging that wakes up.
The vibration information meets preset condition, refers to that the vibration information that the earphone 100 is got meets pre-set default item
Part.The pre-set condition can be for the presence or absence of vibration information.For example, the vibrating sensor is detecting the wearing
The vibration information of earphone person has been more than default vibration information threshold value, then there are vibration informations for explanation, and then proves the vibration letter
Breath meets preset condition.
Specifically, when the wake-up voice messaging and default wake-up voice messaging mismatch, and the vibration information meets
When preset condition, the earphone 100 does not generate wake up instruction;When the wake-up voice messaging and default wake-up voice messaging
Match, and when the vibration information is unsatisfactory for preset condition, the earphone 100 does not generate wake up instruction;When the wake-up voice is believed
Breath is mismatched with the default voice messaging that wakes up, and when the vibration information is unsatisfactory for preset condition, the earphone 100, which does not generate, is called out
It wakes up and instructs.It is only matched when the wake-up voice messaging with wake-up voice messaging is preset, and the vibration information meets default item
When part, the earphone 100 just generates wake up instruction.
It should be noted that when the earphone 100 is connect with the terminal, the wake up instruction for controlling terminal into
Row respective action.For example, the wake up instruction respective action is to open voice assistant, then the earphone 100 sends the wake-up and refers to
When order to the terminal, the terminal carries out opening voice assistant This move.
It should be noted that the acquisition modes of the vibration information, it can are as follows: obtain earphone wearer sounding institute in real time
The vibration information of generation;Alternatively, obtaining vibration letter caused by the earphone wearer sounding under the voice detection mode
Breath.In other words, the vibration information can be acquisition in real time, or when entering the voice detection mode, just be vibrated
The acquisition of information.In other words, the application scenarios of respective figure 1 are parsed, and are that the vibrating sensor can be always
(being constantly in the acquisition state of vibration information) in the open state is also possible to enter speech detection in the earphone 100
When mode, the vibrating sensor, which is just opened, (i.e. under the voice detection mode, to be obtained the earphone wearer sounding and is produced
Raw vibration information).
Voice awakening method provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.
Fig. 3 is the flow chart of one embodiment of voice awakening method provided in an embodiment of the present invention, and the voice wakes up
Method can be executed by the earphone 100 in Fig. 1.As shown in Fig. 3, the voice awakening method includes: S310: obtaining triggering in real time
Voice messaging determines whether to trigger voice detection mode according to the triggering voice messaging;S320: obtain wake up voice messaging and
Detect vibration information caused by the earphone wearer sounding;S330: when the wake-up voice messaging and default wake-up voice
Information matches, and when the vibration information meets preset condition, generate wake up instruction.Compared with above-described embodiment, the present embodiment
Difference be, under the voice detection mode, obtain and wake up voice messaging and the detection earphone wearer sounding is produced
Before raw vibration information, the method also includes:
S310: obtaining triggering voice messaging in real time, is determined whether to trigger speech detection mould according to the triggering voice messaging
Formula.
In the present embodiment, the microphone array of the earphone 100 is in real-time open state, described in obtaining in real time
Trigger voice messaging.The triggering voice messaging that the microphone array of the earphone 100 obtains in real time, and the triggering voice is believed
Breath carries out analysis in real time and processing, and according to the result of analysis and processing, it is determined whether triggering voice detection mode.
Specifically, the earphone 100 is the trigger condition for pre-setting the voice detection mode, the earphone 100
Microphone array be listed in and obtain the triggering voice messaging in real time, when the triggering voice messaging meets the voice detection mode
Trigger condition when, the earphone 100 then enter the voice detection mode.The trigger condition can be according to the triggering
The signal energy of voice messaging is set
Specifically, the real-time acquisition triggers voice messaging, is determined whether to trigger voice according to the triggering voice messaging
Detection pattern, comprising:
Extract the energy of the triggering voice messaging;
Judge whether the energy is greater than preset energy threshold;
If so, triggering voice detection mode success;
If it is not, then triggering voice detection mode failure.
Wherein, the earphone 100 obtains the triggering voice messaging in real time, and carries out energy to the triggering voice messaging
Extraction, extracting for the energy can be according to the triggering voice messaging within the unit time when number of particle vibration, unit
Between wave propagation distance and wavelength obtained.The earphone 100 is previously provided with energy threshold, is getting the triggering language
After the energy of message breath, the energy is compared with preset energy threshold.If the energy is greater than preset energy cut-off
Value then triggers voice detection mode success;If the energy is less than or equal to preset energy threshold, speech detection mould is triggered
Formula failure.
Specifically, the energy threshold can be configured in the terminal connecting with earphone 100 in advance.For example, with institute
The Setting pattern for entering the earphone 100 on the mobile phone of the connection of earphone 100 is stated, into the input interface of energy threshold, clicks energy
Threshold value typing button is measured, the voice for meeting itself desired energy is then issued to the microphone array, typing is clicked and completes.
It should be noted that the earphone 100 is before the energy for obtaining the triggering voice messaging, meeting is first to the touching
It sends out voice messaging and carries out noise reduction process, noise present in the triggering voice messaging is filtered, to prevent noise to the triggering
Voice detection mode impacts, to reduce False Rate.
Specifically, when triggering voice detection mode failure, the real-time acquisition triggering voice messaging is jumped, according to described
Triggering voice messaging determines whether triggering voice detection mode step, and continuation real-time detection, which whether there is, can trigger institute's predicate
The triggering voice messaging of sound detection pattern.When triggering voice detection mode success, jump acquisitions wake-up voice messaging and
Detect vibration information step caused by the earphone wearer sounding.
It should be noted that the triggering keyword needs of the earphone 100 are preset.The triggering of the earphone 100 is closed
Keyword can be by being preset in terminal connected to it.For example, when the earphone 100 is connect with the mobile phone, touching
" Setting pattern " of the earphone 100 is introduced into control mobile phone, clicking trigger is crucial in " Setting pattern " of the earphone 100
The admission of word, the triggering keyword voice prepared in advance by the microphone array typing to the earphone 100 carry out identification or
Person directly keys in the triggering keyword, clicks typing and completes, realizes the typing of triggering keyword.
Voice awakening method provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.Also, by obtaining in real time
Voice messaging is triggered, triggering voice detection mode is determined whether according to the triggering voice messaging, so that the earphone will not one
Directly under voice detection mode, unnecessary power wastage is avoided.
Fig. 4 is the flow chart of one embodiment of voice awakening method provided in an embodiment of the present invention, and the voice wakes up
Method can be executed by the earphone 100 in Fig. 1.As shown in Fig. 4, the voice awakening method includes: S410: obtaining and wakes up voice
Vibration information caused by information and the detection earphone wearer sounding;S420: judge the wake-up voice messaging whether
With default wake-up voice messaging;S430: when the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.
Wherein, the earphone 100 is previously provided with default wake-up voice messaging, is getting the wake-up voice messaging
Afterwards, judge whether the wake-up voice messaging matches the default wake-up voice messaging.The default wake-up voice messaging can be
The corresponding voice messaging of keyword.For example, the default wake-up voice messaging is that " waking up voice assistant " this keyword is corresponding
Voice messaging.
It should be noted that the earphone 100 then opens the wake-up voice after entering the voice detection mode
The acquisition of information, and calculating is compared with the default voice messaging that wakes up in the wake-up voice messaging that will acquire, and is to judge institute
It states and wakes up whether voice messaging matches default wake-up voice messaging.
Specifically, the default wake-up voice messaging is default wake-up keyword;
It is described to judge whether the wake-up voice messaging matches default wake-up voice messaging, comprising:
Detect whether the wake-up voice messaging includes and preset the word for waking up Keywords matching;
If so, determining the wake-up voice messaging and default wake-up information matches;
If it is not, then waking up termination.
Wherein, the wake-up voice messaging is the corresponding voice messaging of at least one word, for example, the wake-up voice is believed
Breath can be word " voice assistant " corresponding voice messaging, alternatively, the wake-up voice messaging " can also wake up voice to help for word
The corresponding voice messaging of hand ".Presetting in the earphone 100 and waking up voice messaging is default wake-up keyword, when the earphone 100
When getting the wake-up voice messaging, detect whether the wake-up voice messaging matches default wake-up voice messaging, if described
Wake up that voice messaging matching is default to wake up voice messaging, by determination the wake-ups voice messaging with to preset wake-up information be to match
, if the wake-up voice messaging mismatches default wake-up voice messaging, this wake-up is terminated, and jump to the real-time acquisition
Voice messaging is triggered, is determined whether to trigger the voice detection mode step according to the triggering voice messaging.
It, can be it should be noted that the corresponding default wake-up voice messaging needs of the wake-up voice messaging are preset
The default setting for waking up voice messaging is carried out in the terminal connecting with the earphone 100.For example, the earphone 100 and hand
Machine connection, user on the mobile phone enter the earphone Setting pattern, into it is default wake up voice messaging set interface,
The default typing for waking up voice messaging is clicked, can be carried out by the default voice messaging that wakes up of the microphone array typing of earphone 100
Identification, or the corresponding keyword of the default wake-up voice messaging is directly keyed on the mobile phone.Alternatively, described preset is called out
Awake voice messaging be it is preset in production firm in advance, user wakes up voice messaging without presetting described in self-setting,
And the default wake-up voice messaging can be known by specification or other feasible patterns, for example, by browsing explanation
Book sends a telegraph the oral acquisition of earphone manufacturer customer service progress.
Specifically, refering to attached drawing 5, the voice awakening method includes: S510: obtaining and wakes up described in voice messaging and detection
Vibration information caused by earphone wearer's sounding;S520: judge whether the vibration information meets preset condition;S530: when
The wake-up voice messaging match with the default voice messaging that wakes up, and when the vibration information meets preset condition, generates wake-up
Instruction.The difference of the present embodiment and above-described embodiment is that the vibration information meets preset condition, comprising:
S520: judge whether the vibration information meets preset condition.
Wherein, the earphone 100 is previously provided with the preset condition for the vibration information.The earphone 100 is obtaining
After getting the vibration information, judge whether the vibration information meets the preset condition.The preset condition can be default
Vibration information threshold value, when the earphone 100 gets vibration information, by the vibration information of the acquisition and default vibration information
Threshold value is compared, so that it is determined that the vibration information whether southerner preset condition.Or it is super for defining the vibration information
The vibration information of default vibration frequency is crossed, the preset condition then can be for the presence or absence of the vibration information.When the earphone 100
When not getting the vibration information, determine that the vibration information is unsatisfactory for preset condition, when the earphone 100 gets institute
When stating vibration information, determine that the vibration information meets preset condition.
Specifically, the preset condition is that the frequency of vibration information is greater than predeterminated frequency threshold value;
It is described to judge whether the vibration information meets preset condition, comprising:
If the frequency of the vibration information is greater than predeterminated frequency threshold value, it is determined that the vibration information meets default item
Part;
If the vibration information frequency threshold is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for
Preset condition.
Wherein, the preset preset condition of the earphone 100 is that the frequency of vibration information is greater than predeterminated frequency threshold value, when described
After earphone 100 gets the vibration information, the signal frequency of the vibration information is calculated, according to the signal frequency and in advance
If the comparison result of frequency threshold, determine whether the vibration information meets preset condition.It should be noted that user is not having
Carry out speech act when, because user limb action behavior or other external factors caused by body vibration, the earphone 100
And vibration information can be got.And because the frequency of the corresponding vibration signal of speech act is caused by being far longer than other movements
Vibration signal frequency, then by the default predeterminated frequency threshold value of preset condition and the vibration information of sounding movement
Frequency is compared, and can be improved the accuracy rate of judgement.
It should be noted that obtaining the vibration information while obtaining the wake-up voice messaging, then judging institute
It states and wakes up whether voice messaging matches default wake-up voice messaging and judge whether accessed vibration information meets default item
Part, at this point, judging whether the wake-up voice messaging matches default wake-up voice messaging and judge whether the vibration information is full
Sufficient preset condition is synchronous carries out.Alternatively, the vibration information is obtained during obtaining the wake-up voice messaging,
Then judge whether the wake-up voice messaging match vibration information accessed by default wake-up voice messaging and judgement
Meet preset condition, at this point, judging whether the vibration information meets preset condition is to be later than to judge the default wake-up slightly
Whether voice messaging matches the default wake-up voice messaging.But the opening time point of the judgement vibration information must
Be it is described judge whether the default wake-up voice messaging matches the default wake-up voice messaging during.
Preferably, judge at the beginning of whether the wake-up voice messaging matches the default wake-up voice messaging point with
Judge to put at the beginning of whether the vibration information meets preset condition identical.
It should be noted that it is described it is " described to judge whether the vibration information meets preset condition " with described " judge institute
State and wake up whether voice messaging matches default wake-up voice messaging " it carries out independently of each other, but the time that the two brings into operation
Point is identical, alternatively, point is in " the judgement at the beginning of " described to judge whether the vibration information meets preset condition "
It is described wake up voice messaging and whether match default wake up voice messaging " operational process in.For example, the earphone 100 is judging
Whether the wake-up voice messaging, which matches the default voice messaging that wakes up, is terminated since the 1st second, and at the 8th second, then " the institute
State and judge whether the vibration information meets preset condition " at the beginning of point can be the 1st second, or the 1st second and the 8th second it
Between.
In some other embodiment, the preset condition whether can be matched for the vibration information it is described preset it is pre-
If vibration information.The default vibration information can be to carry out typing in advance in the terminal connecting with the earphone in advance.For example,
Earphone is worn in advance, and enters default vibration information typing circle of the earphone 100 on the mobile phone connecting with the earphone 100
Default vibration information button is clicked in face, carries out the sounding of default voice messaging, for example, preset language information is that phrase " wakes up language
The corresponding voice messaging of sound assistant ", user then carry out reading aloud for phrase " waking up voice assistant " against the microphone array of earphone,
So that earphone can typing correspond to the vibration information of preset language information, finally click admission and complete.It is obtained in the earphone 100
To after the vibration information, the vibration information is matched with default vibration information, judge the vibration information whether
With default vibration information, so that it is determined that whether the vibration information meets preset condition.
Voice awakening method provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.Also, it prejudges described
Wake up whether voice messaging matches default wake-up voice messaging and/or judge whether the vibration information meets preset condition, with
Make the judging nicety rate for improving voice awakening method.
Fig. 6 is the flow chart of one embodiment of voice awakening method provided in an embodiment of the present invention, and the voice wakes up
Method can be executed by the earphone 100 in Fig. 1.As shown in Fig. 6, the voice awakening method includes: S610: obtaining and wakes up voice
Vibration information caused by information and the detection earphone wearer sounding;S620: the verifying wake-up voice messaging and vibration
Whether information matches;S630: when the wake-up voice messaging match with the default voice messaging that wakes up, and vibration information satisfaction
When preset condition, wake up instruction is generated.The difference of the present embodiment and above-described embodiment is that the vibration information meets default item
Part, comprising:
S620: whether the verifying wake-up voice messaging matches with vibration information;
If so, being matched when the wake-up voice messaging with wake-up voice messaging is preset described in jumping, and the vibration is believed
When breath meets preset condition, the wake up instruction step is generated;
It is terminated if it is not, waking up.
Wherein, the earphone 100 also judges the wake-up after getting the wake-up voice messaging and vibration information
Whether voice messaging matches with vibration information.The wake-up voice messaging is matched with vibration information to be referred to, whether the vibration information
Wake-up voice messaging generation is issued for user.It for example, is only that user oneself says the default wake-up voice letter
In breath when corresponding keyword " hello ", the corresponding voice messaging of " hello " word is generated, while it is corresponding to generate " hello " word
Vibration information, then the corresponding voice messaging of " hello " word is that vibration information corresponding with " hello " word is matched.
And other people other than the user say the keyword " hello " for waking up voice messaging, and user says not keyword at this time
When, earphone can also get the corresponding wake-up voice messaging of keyword " hello ", and the corresponding vibration information of non-key word at this time,
But the corresponding vibration information of non-key word is that wake-up voice messaging not corresponding with keyword " hello " is matched at this time, Ye Jiguan
Keyword " hello " is not when wearing earphone person to issue, and vibration information is not matched with voice messaging.
Specifically, it when the wake-up voice messaging is matched with vibration information, then jumps described when the wake-up voice is believed
Breath is matched with the default voice messaging that wakes up, and when the vibration information meets preset condition, generation wake up instruction step;If institute
When stating wake-up voice messaging and vibration information mismatch, then this wake-up is terminated, jumps to obtain in real time and trigger voice messaging, according to
The triggering voice messaging determines whether to trigger the voice detection mode step.
Specifically, refering to attached drawing 7, whether the verifying wake-up voice messaging matches with vibration information, comprising:
S710: the waveform for waking up voice messaging and vibration information is extracted;
Wherein, the earphone 100 extracts the wake-up language after getting the wake-up voice messaging and vibration information
Message ceases waveform corresponding with vibration information.When the wake-up voice messaging and vibration information, which are all from, wears earphone person, institute
It is similar for stating and waking up the waveform of voice messaging and vibration information.For example, waking up voice messaging is " hello, wakes up voice assistant "
When, the vibration information of total wavelength of wake-up this section of waveform of voice messaging of corresponding word " hello " and corresponding word " hello " this
Total wavelength of one section of waveform is equal, total wave of wake-up this section of waveform of voice messaging of corresponding word " waking up voice assistant "
Long total wavelength with this section of waveform of vibration information of corresponding word " waking up voice assistant " is equal.
S720: judge whether the wake-up voice messaging matches with the waveform of vibration information;
Wherein, judge whether the wake-up voice messaging matches with the waveform of vibration information, it can be according to the vibration information
In total wavelength of at least a bit of waveform whether in the wake-up voice messaging can find the total wavelength to match.Example
Such as, when wake-up voice messaging is " hello, wakes up voice assistant ", this section of waveform of wake-up voice messaging of corresponding word " hello "
Total wavelength with total wavelength of this section of waveform of vibration information of corresponding word " hello " be it is equal, corresponding word " wakes up language
The vibration information of total wavelength of wake-up this section of waveform of voice messaging of sound assistant " and corresponding word " wake up voice assistant " this
Total wavelength of section waveform is equal." hello " vibration information corresponding with " waking up voice assistant " two words can then be passed through
Total wavelength carries out lookup correspondence in the entire waveform for waking up voice messaging, judges whether there is the one of identical total wavelength
Segment wavelength, and if it exists, then determine that the wake-up voice messaging is matched with vibration information, if it does not exist, it is determined that the wake-up
Voice messaging and vibration information mismatch.
S730: if so, determining that the wake-up voice messaging is matched with vibration information;
Wherein, if the wake-up voice messaging with the waveform of vibration information is to jump when matching when the wake-up voice
Information match with the default voice messaging that wakes up, and when the vibration information meets preset condition, generation wake up instruction step.
S740: if not, it is determined that the wake-up voice messaging and vibration information mismatch.
Wherein, if the voice messaging and the waveform of vibration information of waking up is when mismatching, to terminate this wake-up, jump
Triggering voice messaging is obtained in real time, is determined whether to trigger the voice detection mode step according to the triggering voice messaging.
Voice awakening method provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.Also, refer to generating to wake up
It also verifies whether the wake-up voice messaging matches with vibration information in advance before enabling, improves the accuracy rate that voice wakes up.
Correspondingly, the voice Rouser is used for Fig. 1 institute the embodiment of the invention also provides a kind of voice Rouser
The earphone 100 shown, as shown in figure 8, the voice Rouser 800 includes:
Module 801 is obtained, wakes up vibration caused by voice messaging and the detection earphone wearer sounding for obtaining
Information;
Generation module 802, for matching when the wake-up voice messaging with the default voice messaging that wakes up, and the vibration is believed
When breath meets preset condition, wake up instruction is generated.
Voice Rouser provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.
Specifically, refering to attached drawing 9, described device 900 includes:
First obtains module 901, wakes up caused by voice messaging and the detection earphone wearer sounding for obtaining
Vibration information;
Generation module 902, for matching when the wake-up voice messaging with the default voice messaging that wakes up, and the vibration is believed
When breath meets preset condition, wake up instruction is generated.
Described device 900 further include:
Determining module 903 triggers voice messaging for obtaining in real time, determines whether to trigger according to the triggering voice messaging
Voice detection mode;
The determining module 903 be specifically used for detecting the triggering voice messaging whether include and preset triggering keyword
The word to match;If so, triggering voice detection mode success;If it is not, then triggering voice detection mode failure.
First judgment module 904, for judging whether the wake-up voice messaging matches default wake-up voice messaging;
The first judgment module 904 is specifically used for detecting whether the wake-up voice messaging includes crucial with default wake-up
The matched word of word;If so, determining the wake-up voice messaging and default wake-up information matches;If it is not, then waking up termination;
Second judgment module 905, for judging whether the vibration information meets preset condition;
If the frequency that second judgment module 905 is specifically used for the vibration information is greater than default vibration frequency threshold,
Then determine that the vibration information meets preset condition;
If the vibration information is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for default item
Part.
Whether authentication module 906 matches for verifying the wake-up voice messaging with vibration information;If so, jumping
It states when the wake-up voice messaging is matched with the default voice messaging that wakes up, and the vibration information meets preset condition, generates
The wake up instruction step;It is terminated if it is not, waking up;
The authentication module 906 is specifically used for extracting the waveform for waking up voice messaging and vibration information;Described in judgement
Wake up whether voice messaging matches with the waveform of vibration information;If so, determining the wake-up voice messaging and vibration information
Match;If not, it is determined that the wake-up voice messaging and vibration information mismatch.
Second obtains module 907, for obtaining vibration information caused by the earphone wearer sounding in real time;Alternatively,
Under the voice detection mode, vibration information caused by the earphone wearer sounding is obtained.
Voice Rouser provided in an embodiment of the present invention wakes up voice messaging and the detection earphone wearing by obtaining
Vibration information caused by person's sounding;When the wake-up voice messaging match with the default voice messaging that wakes up, and vibration letter
When breath meets preset condition, wake up instruction is generated.This method, which only has while meeting, wakes up voice messaging and earphone wearer sounding
When the two conditions of generated vibration information, the earphone just generates wake up instruction and carries out wake actions, can reduce Yin Pei
The False Rate that the voice messaging of user other than wearer generates improves the accuracy rate of voice wake-up.
Figure 10 is the hardware structural diagram of earphone 10 provided in an embodiment of the present invention, as shown in Figure 10, the earphone 10 packet
It includes:
One or more processors 11 and memory 12, in Fig. 6 by taking a processor 11 as an example.
Processor 11 can be connected with memory 12 by bus or other modes, to be connected as by bus in Fig. 6
Example.
Memory 12 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, such as the corresponding program of voice awakening method in the embodiment of the present invention
Instruction/module (for example, attached acquisition module shown in Fig. 8 801 and generation module 802).Processor 11 is stored in by operation
Non-volatile software program, instruction and module in reservoir 12, thereby executing the various function application and data of server
The voice awakening method of above method embodiment is realized in processing.
Memory 12 may include storing program area and storage data area, wherein storing program area can storage program area,
Application program required at least one function;Storage data area, which can be stored, uses created number according to voice Rouser
According to etc..In addition, memory 12 may include high-speed random access memory, it can also include nonvolatile memory, such as extremely
A few disk memory, flush memory device or other non-volatile solid state memory parts.In some embodiments, memory
12 it is optional include the memory remotely located relative to processor 11, these remote memories can pass through network connection to voice
Rouser.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and its group
It closes.
One or more of modules are stored in the memory 12, when by one or more of processors 11
When execution, the voice awakening method in above-mentioned any means embodiment is executed, for example, executing the method in Fig. 2 described above
Method and step S310 to step S330 in step S210 to step S220, Fig. 3;Realize module S410-S430, Fig. 5 in Fig. 4
Module S610-S630 submodule in middle module S510-S540, Fig. 6, module S710-S740, Fig. 8 Neutron module 801- in Fig. 7
The function of 802 and Fig. 9 Neutron module 901-906.
Method provided by the embodiment of the present invention can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present invention.
The embodiment of the invention provides a kind of non-volatile computer readable storage medium storing program for executing, the computer-readable storage mediums
Matter is stored with computer executable instructions, which is executed by one or more processors, such as in Figure 10
A processor 11, may make said one or multiple processors that voice in above-mentioned any means embodiment can be performed and wake up
Method, for example, the method and step S210 to step S220 in Fig. 2 described above is executed, the method and step S310 in Fig. 3 to step
Rapid S330;Realize in module S410-S430, Fig. 5 in Fig. 4 module S610-S630 submodule in module S510-S540, Fig. 6,
Module S710-S740, Fig. 8 Neutron module 801-802 and Fig. 9 Neutron module 901-906 in Fig. 7.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment
The mode of general hardware platform can be added to realize by software, naturally it is also possible to pass through hardware.Those of ordinary skill in the art can
With understand all or part of the process realized in above-described embodiment method be can be instructed by computer program it is relevant hard
Part is completed, and the program can be stored in a computer-readable storage medium, the program is when being executed, it may include as above
State the process of the embodiment of each method.Wherein, the storage medium can be magnetic disk, CD, read-only memory (Read-
Only Memory, ROM) or random access memory (RandomAccessMemory, RAM) etc..
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;At this
It under the thinking of invention, can also be combined between the technical characteristic in above embodiments or different embodiment, step can be with
It is realized with random order, and there are many other variations of different aspect present invention as described above, for simplicity, they do not have
Have and is provided in details;Although the present invention is described in detail referring to the foregoing embodiments, the ordinary skill people of this field
Member is it is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, or to part of skill
Art feature is equivalently replaced;And these are modified or replaceed, each reality of the present invention that it does not separate the essence of the corresponding technical solution
Apply the range of a technical solution.
Claims (16)
1. a kind of voice awakening method is applied to earphone, which is characterized in that the described method includes:
It obtains and wakes up vibration information caused by voice messaging and the detection earphone wearer sounding;
It is raw when the wake-up voice messaging is matched with the default voice messaging that wakes up, and the vibration information meets preset condition
At wake up instruction.
2. voice awakening method according to claim 1, which is characterized in that obtain and wake up voice messaging and the detection ear
Before vibration information caused by machine wearer's sounding, further includes:
Triggering voice messaging is obtained in real time, is determined whether to trigger voice detection mode according to the triggering voice messaging.
3. voice awakening method according to claim 2, which is characterized in that the real-time acquisition triggers voice messaging, root
Determine whether to trigger voice detection mode according to the triggering voice messaging, comprising:
Extract the energy of the triggering voice messaging;
Judge whether the energy is greater than preset energy threshold;
If so, triggering voice detection mode success, jumps acquisition and wakes up voice messaging and the detection earphone wearer sounding
The generated vibration information step;
If it is not, then triggering voice detection mode failure.
4. voice awakening method according to claim 1, which is characterized in that the wake-up voice messaging and default wake-up language
Sound information matches, comprising:
Judge whether the wake-up voice messaging matches default wake-up voice messaging.
5. voice awakening method according to claim 4, which is characterized in that the default wake-up voice messaging is default calls out
Awake keyword;
It is described to judge whether the wake-up voice messaging matches default wake-up voice messaging, comprising:
Detect whether the wake-up voice messaging includes and preset the word for waking up Keywords matching;
If so, determining the wake-up voice messaging and default wake-up information matches;
If it is not, then waking up termination.
6. voice awakening method according to claim 1, which is characterized in that the vibration information meets preset condition, packet
It includes:
Judge whether the vibration information meets preset condition.
7. voice awakening method according to claim 6, which is characterized in that the preset condition is the frequency of vibration information
Greater than predeterminated frequency threshold value;
It is described to judge whether the vibration information meets preset condition, comprising:
If the frequency of the vibration information is greater than predeterminated frequency threshold value, it is determined that the vibration information meets preset condition;
If the vibration information frequency threshold is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for presetting
Condition.
8. voice awakening method according to claim 1, which is characterized in that described when the wake-up voice messaging and pre-
If waking up voice messaging matching, and when the vibration information meets preset condition, before generating wake up instruction, the method is also wrapped
It includes:
Verify whether the wake-up voice messaging matches with vibration information;
If so, being matched when the wake-up voice messaging with wake-up voice messaging is preset described in jumping, and the vibration information is full
When sufficient preset condition, the wake up instruction step is generated;
It is terminated if it is not, waking up.
9. voice awakening method according to claim 8, which is characterized in that the verifying wake-up voice messaging and vibration
Whether dynamic information matches, comprising:
Extract the waveform for waking up voice messaging and vibration information;
Judge whether the wake-up voice messaging matches with the waveform of vibration information;
If so, determining that the wake-up voice messaging is matched with vibration information;
If not, it is determined that the wake-up voice messaging and vibration information mismatch.
10. -9 described in any item voice awakening methods according to claim 1, which is characterized in that the method also includes:
Vibration information caused by the earphone wearer sounding is obtained in real time;Alternatively,
Under the voice detection mode, vibration information caused by the earphone wearer sounding is obtained.
11. a kind of voice Rouser, it is applied to earphone, which is characterized in that described device includes:
First obtains module, wakes up vibration letter caused by voice messaging and the detection earphone wearer sounding for obtaining
Breath;
Generation module, for matching when the wake-up voice messaging with the default voice messaging that wakes up, and the vibration information meets
When preset condition, wake up instruction is generated.
12. voice Rouser according to claim 11, which is characterized in that described device further include:
Determining module triggers voice messaging for obtaining in real time, is determined whether to trigger voice inspection according to the triggering voice messaging
Survey mode;
The determining module is specifically used for extracting the energy of the triggering voice messaging, and it is preset to judge whether the energy is greater than
Energy threshold;If so, triggering voice detection mode success, jumps acquisition and wakes up voice messaging and the detection earphone wearer
The step of vibration information caused by sounding;If it is not, then triggering voice detection mode failure.
13. voice Rouser according to claim 11, which is characterized in that described device further include:
First judgment module, for judging whether the wake-up voice messaging matches default wake-up voice messaging;
The first judgment module be specifically used for detecting the wake-up voice messaging whether include and default wake-up Keywords matching
Word;If so, determining the wake-up voice messaging and default wake-up information matches;If it is not, then waking up termination;
Second judgment module, for judging whether the vibration information meets preset condition;
If the frequency that second judgment module is specifically used for the vibration information is greater than predeterminated frequency threshold value, it is determined that described
Vibration information meets preset condition;
If the vibration information frequency threshold is less than or equal to predeterminated frequency threshold value, it is determined that the vibration information is unsatisfactory for presetting
Condition.
14. voice Rouser according to claim 11, which is characterized in that described device further include:
Whether authentication module matches for verifying the wake-up voice messaging with vibration information;If so, described when described jumping
It wakes up voice messaging to match with the default voice messaging that wakes up, and when the vibration information meets preset condition, generation wake up instruction
The step;It is terminated if it is not, waking up;
The authentication module is specifically used for extracting the waveform for waking up voice messaging and vibration information;Judge the wake-up voice
Whether information matches with the waveform of vibration information;If so, determining that the wake-up voice messaging is matched with vibration information;If it is not,
Then determine that the wake-up voice messaging and vibration information mismatch.
15. voice Rouser according to claim 11, which is characterized in that described device further include:
Second obtains module, for obtaining vibration information caused by the earphone wearer sounding in real time;Alternatively, in institute's predicate
Under sound detection pattern, vibration information caused by the earphone wearer sounding is obtained.
16. a kind of earphone, which is characterized in that the earphone includes:
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
It manages device to execute, so that at least one described processor is able to carry out the described in any item voice awakening methods of claim 1-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910390724.4A CN110234044A (en) | 2019-05-10 | 2019-05-10 | A kind of voice awakening method, voice Rouser and earphone |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910390724.4A CN110234044A (en) | 2019-05-10 | 2019-05-10 | A kind of voice awakening method, voice Rouser and earphone |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110234044A true CN110234044A (en) | 2019-09-13 |
Family
ID=67860509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910390724.4A Withdrawn CN110234044A (en) | 2019-05-10 | 2019-05-10 | A kind of voice awakening method, voice Rouser and earphone |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110234044A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110611524A (en) * | 2019-09-26 | 2019-12-24 | 联想(北京)有限公司 | Bluetooth data information transmission method and device |
CN110896511A (en) * | 2019-12-10 | 2020-03-20 | 深圳市沃特沃德股份有限公司 | Earphone control method and device, storage medium and computer equipment |
CN112509567A (en) * | 2020-12-25 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, device, equipment, storage medium and program product for processing voice data |
CN113225662A (en) * | 2021-05-28 | 2021-08-06 | 杭州国芯科技股份有限公司 | TWS earphone awakening test method with G-sensor |
CN114615729A (en) * | 2022-04-07 | 2022-06-10 | 重庆物奇微电子有限公司 | Data interaction method, earphone device and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105575395A (en) * | 2014-10-14 | 2016-05-11 | 中兴通讯股份有限公司 | Voice wake-up method and apparatus, terminal, and processing method thereof |
CN108712566A (en) * | 2018-04-27 | 2018-10-26 | 维沃移动通信有限公司 | A kind of voice assistant awakening method and mobile terminal |
CN108766468A (en) * | 2018-06-12 | 2018-11-06 | 歌尔科技有限公司 | A kind of intelligent sound detection method, wireless headset, TWS earphones and terminal |
CN108806679A (en) * | 2018-05-18 | 2018-11-13 | 出门问问信息科技有限公司 | voice awakening method and device |
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 |
US20190108839A1 (en) * | 2016-07-15 | 2019-04-11 | Sonos, Inc. | Voice Detection By Multiple Devices |
-
2019
- 2019-05-10 CN CN201910390724.4A patent/CN110234044A/en not_active Withdrawn
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105575395A (en) * | 2014-10-14 | 2016-05-11 | 中兴通讯股份有限公司 | Voice wake-up method and apparatus, terminal, and processing method thereof |
US20190108839A1 (en) * | 2016-07-15 | 2019-04-11 | Sonos, Inc. | Voice Detection By Multiple Devices |
CN108712566A (en) * | 2018-04-27 | 2018-10-26 | 维沃移动通信有限公司 | A kind of voice assistant awakening method and mobile terminal |
CN108806679A (en) * | 2018-05-18 | 2018-11-13 | 出门问问信息科技有限公司 | voice awakening method and device |
CN108766468A (en) * | 2018-06-12 | 2018-11-06 | 歌尔科技有限公司 | A kind of intelligent sound detection method, wireless headset, TWS earphones and terminal |
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 (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110611524A (en) * | 2019-09-26 | 2019-12-24 | 联想(北京)有限公司 | Bluetooth data information transmission method and device |
CN110896511A (en) * | 2019-12-10 | 2020-03-20 | 深圳市沃特沃德股份有限公司 | Earphone control method and device, storage medium and computer equipment |
CN112509567A (en) * | 2020-12-25 | 2021-03-16 | 北京百度网讯科技有限公司 | Method, device, equipment, storage medium and program product for processing voice data |
CN112509567B (en) * | 2020-12-25 | 2024-05-10 | 阿波罗智联(北京)科技有限公司 | Method, apparatus, device, storage medium and program product for processing voice data |
CN113225662A (en) * | 2021-05-28 | 2021-08-06 | 杭州国芯科技股份有限公司 | TWS earphone awakening test method with G-sensor |
CN113225662B (en) * | 2021-05-28 | 2022-04-29 | 杭州国芯科技股份有限公司 | TWS earphone awakening test method with G-sensor |
CN114615729A (en) * | 2022-04-07 | 2022-06-10 | 重庆物奇微电子有限公司 | Data interaction method, earphone device and computer readable storage medium |
CN114615729B (en) * | 2022-04-07 | 2023-08-29 | 重庆物奇微电子有限公司 | Data interaction method, earphone device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110234044A (en) | A kind of voice awakening method, voice Rouser and earphone | |
CN106714023B (en) | Bone conduction earphone-based voice awakening method and system and bone conduction earphone | |
KR102525294B1 (en) | Voice control method, wearable device and terminal | |
US10460095B2 (en) | Earpiece with biometric identifiers | |
CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
CN110288997A (en) | Equipment awakening method and system for acoustics networking | |
CN109120790A (en) | Call control method, device, storage medium and wearable device | |
CN108470034A (en) | A kind of smart machine service providing method and system | |
CN108766438A (en) | Man-machine interaction method, device, storage medium and intelligent terminal | |
CN110708625A (en) | Intelligent terminal-based environment sound suppression and enhancement adjustable earphone system and method | |
CN109243445A (en) | Sound control method, device, electronic equipment and storage medium | |
CN109656511A (en) | A kind of audio frequency playing method, terminal and computer readable storage medium | |
CN107564523A (en) | A kind of earphone receiving method, apparatus and earphone | |
CN105677004A (en) | Terminal processing method and terminal | |
US20230377602A1 (en) | Health-related information generation and storage | |
CN110223711A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
CN109412544B (en) | Voice acquisition method and device of intelligent wearable device and related components | |
CN109240639A (en) | Acquisition methods, device, storage medium and the terminal of audio data | |
CN111491236A (en) | Active noise reduction earphone, awakening method and device thereof and readable storage medium | |
US11170790B2 (en) | User authentication with audio reply | |
CN110428806A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
CN107863110A (en) | Safety prompt function method, intelligent earphone and storage medium based on intelligent earphone | |
CN110111776A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
CN109639908A (en) | A kind of bluetooth headset, anti-eavesdrop method, apparatus, equipment and 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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190913 |