CN106155621A - The key word voice of recognizable sound source position wakes up system and method and mobile terminal up - Google Patents
The key word voice of recognizable sound source position wakes up system and method and mobile terminal up Download PDFInfo
- Publication number
- CN106155621A CN106155621A CN201510192268.4A CN201510192268A CN106155621A CN 106155621 A CN106155621 A CN 106155621A CN 201510192268 A CN201510192268 A CN 201510192268A CN 106155621 A CN106155621 A CN 106155621A
- Authority
- CN
- China
- Prior art keywords
- signal
- key word
- wakes
- mobile terminal
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000003111 delayed effect Effects 0.000 claims abstract description 17
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 9
- 238000004020 luminiscence type Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000001133 acceleration Effects 0.000 description 7
- 230000002618 waking effect Effects 0.000 description 4
- 230000003213 activating effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000006854 communication Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000001260 vocal cord Anatomy 0.000 description 1
Landscapes
- Telephone Function (AREA)
Abstract
The present invention relates to a kind of voice process technology field, the key word voice particularly relating to a kind of recognizable sound source position wakes up system and method and mobile terminal up.Including: collecting unit, including the first harvester and the second harvester, a predetermined gap is set between the first harvester and the second harvester;Delay unit, arranges a predetermined time delay, in order to receive the first collection signal, and the first collection signal does delay process formation the first delay signal output;Computing unit, in order to receive the second collection signal and the first time delayed signal respectively, gathers signal and the first time delayed signal carries out calculating formation one result of calculation output second;Control unit, in order to receive the result of calculation of computing unit output, gathers under the state that the predetermined key word of Signal Matching one wakes up instruction up in second, forms a control signal output in conjunction with result of calculation;Wakeup unit, is used under the effect of control signal wake up mobile terminal up.
Description
Technical field
The present invention relates to a kind of voice process technology field, particularly relate to a kind of recognizable sound source position
Key word voice wake up system and method and mobile terminal up.
Background technology
Word employed in human speech communication process is typically the vowel that vocal cord vibration produces and arranges in pairs or groups this vibration
Larynx, tongue, lip, jaw, intraoral air-flow formed consonant combine formed, i.e. vowel can produce
Energy, consonant is only gas sound, and major part has the word of essence implication all first to start with consonant, and opens with vowel
Begin word be mostly auxiliary words of mood, as " ", " " " uh " ... wait word all to start with vowel
Word.
In existing mobile terminal, the system that wakes up up mainly has and manually wakes up system up, i.e. conventional by starting
Start push button exciting mobile terminal;This kind of mode, life-time service, easily cause the malfunctioning of button, simultaneously
Power consumption is bigger;Action wakes up system up, is i.e. provided with acceleration transducer in mobile terminal, and acceleration passes
Sensor detects whether that there are acceleration (such as moves the mobile terminal placed that lies low and i.e. there is an acceleration
Degree) produce, when acceleration meets predetermined condition, activate mobile terminal, this kind of mode needs to arrange in pairs or groups one
Individual acceleration transducer, relatively costly, and acceleration transducer power consumption is bigger;Such as brandish mobile terminal
Mobile terminal can be activated;Voice wakes up system up, and voice wakes up the activity of system detection human speech up, i.e.
As long as any vowel or consonant being detected, the mobile terminal being in holding state can be activated, adopt
Waking up system up with voice, power consumption is relatively low, and cost is relatively low, but this kind of voice wakes up system up and only hearing
Human speech information can activate, and maloperation easily occurs, can activate mobile terminal the most per capita, people
The occasion that number is more, mobile terminal is constantly in duty, and power consumption is relatively big, activates accuracy rate low.Existing
Some voices wake up up and there is also a defect, i.e. mobile terminal and be in left-hand thread state (i.e. screen light emission direction does not has
Have barrier), because user is not intended to the phonetic order that sends, it is possible to cause mobile terminal to be waken up, and this kind
Waking up up under state does not has substantial meaning, causes electric energy or power consumption to be wasted.
Summary of the invention
For the deficiencies in the prior art, the present invention provide a kind of low in energy consumption, activate that accuracy rate is high, maloperation
The key word voice of low a kind of recognizable sound source position wakes up system and method and mobile terminal up.
The key word voice of a kind of recognizable sound source position wakes up system up, wherein: including:
One collecting unit, including the first harvester and the second harvester, described first harvester and described second
Arrange a predetermined gap, described first harvester and described second harvester between harvester to be used to currently
Gather described acoustical signal when acoustical signal in local environment reaches predetermined amplitude respectively, and formed respectively
First gathers signal and second gathers signal output;
One delay unit, arranges a predetermined time delay, gathers signal in order to receive described first, and to described the
One gathers signal does delay process formation the first delay signal output;
One computing unit, gathers signal and described first time delayed signal, to institute in order to receive described second respectively
State the second collection signal and described first time delayed signal carries out calculating formation one result of calculation output;
One control unit, in order to receive the described result of calculation of described computing unit output, adopts in described second
Collect under the state that the predetermined key word of Signal Matching one wakes up instruction up, form a control in conjunction with described result of calculation
Signal processed exports;
One wakeup unit, is used under the effect of described control signal wake up up described mobile terminal.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: described control unit includes one
Judging unit, in order to receive described result of calculation,
In the state that described result of calculation is not zero, it is judged that described sound source is positioned at sending out of described mobile terminal screen
Light direction;
It is the state of zero in described result of calculation, it is judged that described sound source is positioned at the described luminescence of described mobile terminal
Any side in direction or the back side;
Under the state of the light emission direction that described control unit is positioned at described mobile terminal screen in described sound source, send out
Go out the control signal allowing to activate described mobile terminal.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: institute is mated in described predetermined time delay
State the preset space length between the first harvester and described second harvester.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: also include a non-volatile storage
Unit, connects described control unit, wakes up instruction up in order to store predetermined described key word.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: also include a training unit,
It is connected between described collecting unit and described nonvolatile memory cell, is used to described running of mobile terminal
Under a training mode, a plurality of voices that described collecting unit sends in order to receive user wake up instruction up,
And wake up instruction up according to a plurality of described voices and form the described key word preset and wake up instruction up, and export extremely
Described nonvolatile memory cell stores.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: described training unit includes
One integral unit, connects described second harvester, in order to default described key word is waken up up instruct into
The described key word that row integral and calculating is preset wakes up the standard energy information of instruction, standard amplitude information up;
One timing unit, connects described collecting unit, wakes up instruction up in order to calculate default described key word
Standard time information.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: described default key word is called out
Awake instruction at least includes standard energy information, standard amplitude information, standard time information,
Described judging unit at least mates described standard energy information and described standard width in described collection signal
Described judged result is exported for allowing to activate described mobile terminal when value information and described standard time information.
Above-mentioned recognizable sound source position key word voice wakes up system up, wherein: described training mode is by described
The control unit of mobile terminal controls to be formed.
The key word voice awakening method of a kind of recognizable sound source position, is applied to mobile terminal, wherein: bag
Include following steps,
Step S1, control the first harvester and the second harvester gathers the sound being presently in environment respectively
Signal, and form the first collection signal and the second collection signal output respectively;
Step S2, control delay unit receive described first and gather signal, and gather signal to described first
Do delay process and form the first delay signal output;
Step S3, control computing unit receive described second respectively and gather signal and described first time delayed signal,
Gather signal to described second and described first time delayed signal carries out calculating formation one result of calculation output;
Step S4, control unit receive the described result of calculation of described computing unit output, in described second
Gather under the state that the predetermined key word of Signal Matching one wakes up instruction up, form one in conjunction with described result of calculation
Control signal exports;
Step S5, wakeup unit wake up described mobile terminal under the effect of described control signal up.
A kind of mobile terminal, wherein: include that the key word voice described in any of the above-described item wakes up system up, described
Key word voice wakes up system up and is arranged in described mobile terminal, be used to receive one include predetermined
After the voice signal of described key word, the operational mode of described mobile terminal is switched to work from standby mode
Operation mode.
Compared with prior art, the invention have the advantage that
The present invention is preset with key word and wakes up instruction up, and key word wakes up instruction up and can set voluntarily according to the hobby of user
Putting, the time delay being combined collecting unit by sound amplitude judges sound source position, and control unit is according to sound source position
Put output control signal to activate mobile terminal.Effectively prevent user at the shape that cannot use mobile terminal
Activate mobile terminal under state by mistake, reduce further the power consumption of mobile terminal.
Accompanying drawing explanation
Fig. 1 is the structural representation that key word voice of the present invention wakes up system up;
Fig. 2 is the schematic flow sheet of key word voice awakening method of the present invention.
Detailed description of the invention
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as the present invention's
Limit.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out
Clearly and completely describe, it is clear that described embodiment is only a part of embodiment of the present invention, and
It is not all, of embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained on the premise of going out creative work, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the embodiment in the present invention and the spy in embodiment
Levy and can be mutually combined.
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as the present invention's
Limit.
As it is shown in figure 1, the key word voice of a kind of recognizable sound source position wakes up system up, wherein: including:
One collecting unit, including the first harvester and the second harvester, described first harvester and described second
Arrange a predetermined gap, described first harvester and described second harvester between harvester to be used to currently
Gather described acoustical signal when acoustical signal in local environment reaches predetermined amplitude respectively, and formed respectively
First gathers signal and second gathers signal output;When this predetermined amplitude is usually user just to mobile terminal
Sound amplitude because when the screen back of mobile terminal is to user, though activate mobile terminal, user
Also cannot use.
One delay unit, arranges a predetermined time delay, gathers signal in order to receive described first, and to described the
One gathers signal does delay process formation the first delay signal output;
One computing unit, gathers signal and described first time delayed signal, to institute in order to receive described second respectively
State the second collection signal and described first time delayed signal carries out calculating formation one result of calculation output;
One control unit, in order to receive the described result of calculation of described computing unit output, adopts in described second
Collect under the state that the predetermined key word of Signal Matching one wakes up instruction up, form a control in conjunction with described result of calculation
Signal processed exports;
One wakeup unit, is used under the effect of described control signal wake up up described mobile terminal.
A kind of key word voice wakes up the operation principle of system up: described first harvester collection is presently in environment
In acoustical signal form the first collection signal output to described time delay elements, described second harvester collection
The acoustical signal being presently in environment forms the second collection signal output to described computing unit;Time described
Prolong unit and described first collection signal is done delay process formation the first delay signal output to the most described calculating list
Unit, described second collection signal and described first time delayed signal are counted by described computing unit according to described
Calculate and form a result of calculation output;Control unit receives the described result of calculation of described computing unit output,
Gather under the state that the predetermined key word of Signal Matching one wakes up instruction up in described second, in conjunction with described calculating
Result forms a control signal output, and wakeup unit wakes up described movement under the effect of described control signal up
Terminal, wherein, result of calculation includes two states, and one is zero state, the i.e. first time delayed signal and
Two collection signals are identical, the most now may determine that the side being positioned at described mobile terminal for described sound source,
(underline, it is also possible to the second harvester is connected delay unit herein, gather signal to second and prolong more
Time process, principle is ibid.), mate the first harvester and second because of the predetermined time delay of delay unit and gather
Predetermined gap between device, predetermined time delay is typically set at the ratio of predetermined gap and sound propagation velocity.
It is assumed that the first harvester first collects acoustical signal forms the first signal, the second harvester after adopt
Collection forms secondary signal to acoustical signal, now has one between the first signal waveform and secondary signal waveform
Individual actual time delay, carries out the time delay processing of a predetermined instant by time delay elements to the first signal, through being somebody's turn to do
The first time delayed signal that time delay processing is formed is identical with secondary signal waveform, and the first time delay is believed by computing unit
Number with secondary signal do subtraction process.When result of calculation is zero, then the first signal and the reality of secondary signal
Border time delay is equal to the scheduled time, then explanation sound source position is the side near the first harvester, and not the
In the middle of one harvester and the second harvester.When result of calculation is not zero, then the first signal and secondary signal
Actual time delay be not equal to the scheduled time, then explanation sound source position is near being positioned at the first harvester and second
In the middle of harvester.
It addition, predetermined amplitude generally can be by user's sets itself, it is also possible to the basic volume of human speech is made
For predetermined amplitude, do not limit.The collection of signal is carried out when acoustical signal reaches predetermined amplitude,
The mistake collection of the collection being prevented effectively from, such as acoustical signal too low or too high in the case of, gather
Unit does not gather this signal, under the too low state of usual sound, the screen of mobile terminal be likely to be at back to
Family, mobile terminal can not be activated.If but user can not normally send under voice status and (such as open
During Hui), can exciting mobile terminal by other means, such as conventional push button exciting moves end
End, or fingerprint activated mobile terminal.I.e. mobile terminal can use multiple Starting mode cooperate with
Activate mobile terminal.
Using said method, the time delay being combined collecting unit by sound amplitude judges sound source position, controls
Unit exports control signal to activate mobile terminal according to sound source position.Effectively prevent user cannot make
With activating mobile terminal under the state of mobile terminal by mistake, reduce further the power consumption of mobile terminal.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, described control unit includes a judging unit, in order to receive described result of calculation, calculates knot in described
The state that fruit is not zero, it is judged that described sound source is positioned at the light emission direction of described mobile terminal screen;In described
Result of calculation is the state of zero, it is judged that described sound source is positioned at appointing of the described light emission direction of described mobile terminal
Meaning side or the back side;Described control unit is positioned at the light emission direction of described mobile terminal screen in described sound source
Under state, send the control signal allowing to activate described mobile terminal.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, wherein: also include a nonvolatile memory cell, connects described judging unit, default in order to store
Described key word wakes up instruction up.Nonvolatile memory cell is i.e. when power down, and key word wakes up instruction up
It is difficult to lose.Nonvolatile memory cell can be MTP memory element (can repeatedly programmed logic memory element),
OTP memory cell (One Time Programming, One Time Programmable), EEPROM (Electrically
Erasable Programmable Read-Only Memory band EEPROM) storage
Unit, Flash (Flash Memory flash memory).The present invention is preset with key word and wakes up instruction up, crucial
Word wakes up instruction up and can arrange voluntarily according to the hobby of user, such as, arrange one " Xiao Ming ", single when gathering
When the signal that unit gathers is " obviously ", " little red ", mobile terminal all can not be activated, only only have
Can be activated when collecting " Xiao Ming ".Using this kind of mode, mobile terminal is only capable of specifically being closed
Keyword activates, and is in standby mode when not being activated, and power consumption is relatively low, and is effectively increased
The accuracy rate of mobile terminal activating, greatly reduces misuse rate.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, wherein: also include a training unit, is connected to described collecting unit and described nonvolatile memory cell
Between, it is used to described running of mobile terminal under a training mode, in order to receive the plural number that user sends
Individual voice wakes up instruction up, and the described key word waking up instruction formation up default according to a plurality of described voices is called out
Wake up and instruct, and export to the storage of described nonvolatile memory cell.Training unit is mainly in order to arrange key word
Waking up instruction up, user in training mode, sends ten times " Xiao Ming ", training unit receive ten times " little
Bright ", according to the voice messaging of ten times " Xiao Ming ", key word is modified, calls out forming key word
Wake up and instruct.Because the amplitude of each voice messaging of the mankind, time, the energy of pronunciation are different from, so
Increasing a training unit, wake up instruction up in order to form key word, it is to user that this key word wakes up instruction up
The key word sent is trained and revises, it is allowed to user occurs in that part deviation at the key word sent
Under state, still can activate mobile terminal.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, wherein: described training unit includes
One integral unit, connects described second harvester, in order to default described key word is waken up up instruct into
The described key word that row integral and calculating is preset wakes up the standard energy information of instruction, standard amplitude information up;Enter
One step ground, described integral unit is Fourier transform unit, in order to default described key word is waken up up finger
The described key word that order carries out Fourier transformation acquisition default wakes up the standard energy information of instruction, standard width up
Value information.First voice signal is carried out segmentation, every section of interior signal is carried out frequency domain transform, frequency domain is become
Change interior energy information to carry out frequency-domain calculations and obtain energy information and the standard amplitude information of its standard.
One timing unit, connects described collecting unit, wakes up instruction up in order to calculate default described key word
Standard time information.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, wherein: described default key word wakes up instruction up and at least includes that standard energy information, standard amplitude are believed
Breath, standard time information, described judging unit at least mates described standard energy letter in described collection signal
When breath and described standard amplitude information and described standard time information, the described judged result of output is fair
Permitted to activate described mobile terminal.Described judging unit can comprise several comparators, in order to respectively the
Two gather the energy information of signal, amplitude information, temporal information.
As further preferred embodiment, the key word voice of above-mentioned recognizable sound source position wakes up up and is
System, wherein: described training mode is controlled to be formed by the control unit of described mobile terminal.Training mode is led to
The control unit often having mobile terminal controls, and when being under training mode, collecting unit is only single with training
Unit connects, i.e. the voice signal of collecting unit collection only transmits to training unit.
As in figure 2 it is shown, the key word voice awakening method of a kind of recognizable sound source position, it is applied to mobile whole
End, wherein, including,
Step S1, control the first harvester and the second harvester reaches in the acoustical signal being presently in environment
Signal output is gathered to gathering and formed the first collection signal and second during predetermined amplitude respectively;
Step S2, control delay unit receive described first and gather signal, and gather signal to described first
Do delay process and form the first delay signal output;
Step S3, control computing unit receive described second respectively and gather signal and described first time delayed signal,
Gather signal to described second and described first time delayed signal carries out calculating formation one result of calculation output;
Step S4, control unit receive the described result of calculation of described computing unit output, in described second
Gather under the state that the predetermined key word of Signal Matching one wakes up instruction up, form one in conjunction with described result of calculation
Control signal exports;
Step S5, wakeup unit wake up described mobile terminal under the effect of described control signal up.
The key word voice awakening method of a kind of recognizable sound source position, its operation principle and recognizable sound source position
The operation principle that the key word voice put wakes up system up is identical, does not repeats.
A kind of mobile terminal, wherein: include the key words of recognizable sound source position described in any of the above-described item
Sound wakes up system up, and described key word voice wakes up system up and is arranged in described mobile terminal, is used to receive
After a voice signal including predetermined described key word, by the operational mode of described mobile terminal from
Standby mode switches to mode of operation.
The application can also include the mobile end of a key word awakening method implementing recognizable sound source position
End.
The foregoing is only preferred embodiment of the present invention, not thereby limit embodiments of the present invention and guarantor
Protect scope, to those skilled in the art, it should can appreciate that all utilization description of the invention and
Equivalent done by diagramatic content and the scheme obtained by obvious change, all should be included in
In protection scope of the present invention.
Claims (10)
1. the key word voice of a recognizable sound source position wakes up system up, it is characterised in that: including:
One collecting unit, including the first harvester and the second harvester, described first harvester and described second
Arrange a predetermined gap, described first harvester and described second harvester between harvester to be used to currently
Gather described acoustical signal when acoustical signal in local environment reaches predetermined amplitude respectively, and formed respectively
First gathers signal and second gathers signal output;
One delay unit, arranges a predetermined time delay, gathers signal in order to receive described first, and to described the
One gathers signal does delay process formation the first delay signal output;
One computing unit, gathers signal and described first time delayed signal, to institute in order to receive described second respectively
State the second collection signal and described first time delayed signal carries out calculating formation one result of calculation output;
One control unit, in order to receive the described result of calculation of described computing unit output, adopts in described second
Collect under the state that the predetermined key word of Signal Matching one wakes up instruction up, form a control in conjunction with described result of calculation
Signal processed exports;
One wakeup unit, is used under the effect of described control signal wake up up described mobile terminal.
Recognizable sound source position key word voice the most according to claim 1 wakes up system up, its feature
It is: described control unit includes a judging unit, in order to receive described result of calculation,
In the state that described result of calculation is not zero, it is judged that described sound source is positioned at sending out of described mobile terminal screen
Light direction;
It is the state of zero in described result of calculation, it is judged that described sound source is positioned at the described luminescence of described mobile terminal
Any side in direction or the back side;
Under the state of the light emission direction that described control unit is positioned at described mobile terminal screen in described sound source, send out
Go out the control signal allowing to activate described mobile terminal.
Recognizable sound source position key word voice the most according to claim 1 wakes up system up, it is characterised in that:
The preset space length between described first harvester and described second harvester is mated in described predetermined time delay.
Recognizable sound source position key word voice the most according to claim 1 wakes up system up, it is characterised in that:
Also include a nonvolatile memory cell, connect described control unit, in order to store predetermined described key word
Wake up instruction up.
Recognizable sound source position key word voice the most according to claim 4 wakes up system up, it is characterised in that:
Also include a training unit, be connected between described collecting unit and described nonvolatile memory cell, in order to
In described running of mobile terminal under a training mode, described collecting unit is in order to answering of receiving that user sends
Several voices wake up instruction up, and wake up, according to a plurality of described voices, the described key word that instruction formation is preset up
Wake up instruction up, and export to the storage of described nonvolatile memory cell.
Recognizable sound source position key word voice the most according to claim 5 wakes up system up, it is characterised in that:
Described training unit includes
One integral unit, connects described second harvester, in order to default described key word is waken up up instruct into
The described key word that row integral and calculating is preset wakes up the standard energy information of instruction, standard amplitude information up;
One timing unit, connects described collecting unit, wakes up instruction up in order to calculate default described key word
Standard time information.
Recognizable sound source position key word voice the most according to claim 1 wakes up system up, it is characterised in that:
Described default key word wakes up instruction up when at least including standard energy information, standard amplitude information, standard
Between information,
Described judging unit at least mates described standard energy information and described standard width in described collection signal
Described judged result is exported for allowing to activate described mobile terminal when value information and described standard time information.
Recognizable sound source position key word voice the most according to claim 5 wakes up system up, it is characterised in that:
Described training mode is controlled to be formed by the control unit of described mobile terminal.
9. a key word voice awakening method for recognizable sound source position, is applied to mobile terminal, and its feature exists
In: comprise the steps,
Step S1, control the first harvester and the second harvester gathers the sound being presently in environment respectively
Signal, and form the first collection signal and the second collection signal output respectively;
Step S2, control delay unit receive described first and gather signal, and gather signal to described first
Do delay process and form the first delay signal output;
Step S3, control computing unit receive described second respectively and gather signal and described first time delayed signal,
Gather signal to described second and described first time delayed signal carries out calculating formation one result of calculation output;
Step S4, control unit receive the described result of calculation of described computing unit output, in described second
Gather under the state that the predetermined key word of Signal Matching one wakes up instruction up, form one in conjunction with described result of calculation
Control signal exports;
Step S5, wakeup unit wake up described mobile terminal under the effect of described control signal up.
10. a mobile terminal, it is characterised in that: include knowing described in any one of the claims 1~8
The key word voice of other sound source position wakes up system up, and described key word voice wakes up system up and is arranged at described shifting
In dynamic terminal, after being used to receive a voice signal including predetermined described key word, by described
The operational mode of mobile terminal switches to mode of operation from standby mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510192268.4A CN106155621B (en) | 2015-04-20 | 2015-04-20 | Keyword voice awakening system and method capable of identifying sound source position and mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510192268.4A CN106155621B (en) | 2015-04-20 | 2015-04-20 | Keyword voice awakening system and method capable of identifying sound source position and mobile terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106155621A true CN106155621A (en) | 2016-11-23 |
CN106155621B CN106155621B (en) | 2024-04-16 |
Family
ID=58059049
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510192268.4A Active CN106155621B (en) | 2015-04-20 | 2015-04-20 | Keyword voice awakening system and method capable of identifying sound source position and mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106155621B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106782585A (en) * | 2017-01-26 | 2017-05-31 | 芋头科技(杭州)有限公司 | A kind of sound pick-up method and system based on microphone array |
CN107145329A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | Apparatus control method, device and smart machine |
CN108429999A (en) * | 2018-04-06 | 2018-08-21 | 东莞市华睿电子科技有限公司 | The standby controlling method of intelligent sound box |
CN108744498A (en) * | 2018-05-17 | 2018-11-06 | 东莞市华睿电子科技有限公司 | A kind of virtual game quick start method based on double VR equipment |
CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
CN109598188A (en) * | 2018-10-16 | 2019-04-09 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
WO2020151580A1 (en) * | 2019-01-25 | 2020-07-30 | 华为技术有限公司 | Screen control and voice control method and electronic device |
CN112673422A (en) * | 2018-09-11 | 2021-04-16 | 日本电信电话株式会社 | Continuous speech estimation device, continuous speech estimation method, and program |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
CN103292437A (en) * | 2013-06-17 | 2013-09-11 | 广东美的制冷设备有限公司 | Voice interactive air conditioner and control method thereof |
US20140281628A1 (en) * | 2013-03-15 | 2014-09-18 | Maxim Integrated Products, Inc. | Always-On Low-Power Keyword spotting |
CN204856459U (en) * | 2015-04-20 | 2015-12-09 | 钰太芯微电子科技(上海)有限公司 | Keyword pronunciation of distinguishable sound source position awaken system and mobile terminal up |
-
2015
- 2015-04-20 CN CN201510192268.4A patent/CN106155621B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599270A (en) * | 2008-06-02 | 2009-12-09 | 海尔集团公司 | Voice server and voice control method |
US20140281628A1 (en) * | 2013-03-15 | 2014-09-18 | Maxim Integrated Products, Inc. | Always-On Low-Power Keyword spotting |
CN103292437A (en) * | 2013-06-17 | 2013-09-11 | 广东美的制冷设备有限公司 | Voice interactive air conditioner and control method thereof |
CN204856459U (en) * | 2015-04-20 | 2015-12-09 | 钰太芯微电子科技(上海)有限公司 | Keyword pronunciation of distinguishable sound source position awaken system and mobile terminal up |
Non-Patent Citations (1)
Title |
---|
赵吉清;易灵芝;王根平;: "无线触发唤醒的无线数据采集系统设计" * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106782585A (en) * | 2017-01-26 | 2017-05-31 | 芋头科技(杭州)有限公司 | A kind of sound pick-up method and system based on microphone array |
WO2018137704A1 (en) * | 2017-01-26 | 2018-08-02 | 芋头科技(杭州)有限公司 | Microphone array-based pick-up method and system |
CN106782585B (en) * | 2017-01-26 | 2020-03-20 | 芋头科技(杭州)有限公司 | Pickup method and system based on microphone array |
US11302341B2 (en) | 2017-01-26 | 2022-04-12 | Yutou Technology (Hangzhou) Co., Ltd. | Microphone array based pickup method and system |
CN107145329A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | Apparatus control method, device and smart machine |
CN108429999A (en) * | 2018-04-06 | 2018-08-21 | 东莞市华睿电子科技有限公司 | The standby controlling method of intelligent sound box |
CN108744498A (en) * | 2018-05-17 | 2018-11-06 | 东莞市华睿电子科技有限公司 | A kind of virtual game quick start method based on double VR equipment |
CN108744498B (en) * | 2018-05-17 | 2021-05-07 | 武汉微派网络科技有限公司 | Virtual game quick starting method based on double VR equipment |
CN112673422A (en) * | 2018-09-11 | 2021-04-16 | 日本电信电话株式会社 | Continuous speech estimation device, continuous speech estimation method, and program |
CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
CN109598188A (en) * | 2018-10-16 | 2019-04-09 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
WO2020151580A1 (en) * | 2019-01-25 | 2020-07-30 | 华为技术有限公司 | Screen control and voice control method and electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN106155621B (en) | 2024-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106155621A (en) | The key word voice of recognizable sound source position wakes up system and method and mobile terminal up | |
CN106161755A (en) | A kind of key word voice wakes up system and awakening method and mobile terminal up | |
CN108320733B (en) | Voice data processing method and device, storage medium and electronic equipment | |
CN105009204B (en) | Speech recognition power management | |
CN110428810B (en) | Voice wake-up recognition method and device and electronic equipment | |
CN107564518A (en) | Smart machine control method, device and computer equipment | |
CN110364143B (en) | Voice awakening method and device and intelligent electronic equipment | |
US20200027462A1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
CN106714023A (en) | Voice wake-up method and system based on bone conduction earphone, and bone conduction earphone | |
CN109493849A (en) | Voice awakening method, device and electronic equipment | |
CN111105796A (en) | Wireless earphone control device and control method, and voice control setting method and system | |
CN109036393A (en) | Wake-up word training method, device and the household appliance of household appliance | |
CN109243446A (en) | A kind of voice awakening method based on RNN network | |
CN110473536A (en) | A kind of awakening method, device and smart machine | |
JPWO2003015076A1 (en) | Dog emotion discrimination device and method based on voice feature analysis | |
CN102635999B (en) | Method for managing refrigerators through voices | |
CN110349579B (en) | Voice wake-up processing method and device, electronic equipment and storage medium | |
CN204856459U (en) | Keyword pronunciation of distinguishable sound source position awaken system and mobile terminal up | |
CN103077721A (en) | Voice memorandum method of mobile terminal and mobile terminal | |
CN109036395A (en) | Personalized speaker control method, system, intelligent sound box and storage medium | |
CN106971719A (en) | A kind of offline changeable nonspecific sound speech recognition awakening method for waking up word | |
CN108052195A (en) | The control method and terminal device of a kind of microphone apparatus | |
CN109166571A (en) | Wake-up word training method, device and the household appliance of household appliance | |
CN111429901A (en) | IoT chip-oriented multi-stage voice intelligent awakening method and system | |
CN110500721A (en) | A kind of air-conditioning sound control method, device and air conditioner |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |