CN107277672A - A kind of method and apparatus for supporting awakening mode to automatically switch - Google Patents
A kind of method and apparatus for supporting awakening mode to automatically switch Download PDFInfo
- Publication number
- CN107277672A CN107277672A CN201710422108.3A CN201710422108A CN107277672A CN 107277672 A CN107277672 A CN 107277672A CN 201710422108 A CN201710422108 A CN 201710422108A CN 107277672 A CN107277672 A CN 107277672A
- Authority
- CN
- China
- Prior art keywords
- unit
- algorithm
- awakening mode
- function module
- microphone
- 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 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 169
- 230000006870 function Effects 0.000 claims description 97
- 238000012545 processing Methods 0.000 claims description 47
- 230000001629 suppression Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 9
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000005611 electricity Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
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
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4418—Suspend and resume; Hibernate and awake
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Telephone Function (AREA)
- Power Sources (AREA)
Abstract
The invention provides a kind of method and apparatus for supporting awakening mode to automatically switch, methods described detects whether present apparatus powers by power detecting unit first, to allow the corresponding awakening mode of pattern determining unit determining device.When device is in power supply awakening mode, power consumption is not the factor of overriding concern, thus device is waken up using the first preset strategy, and the algoritic module function in the first preset strategy is more, algorithm is comprehensive, performance is high, so as to meet user's request to greatest extent；When device is in battery awakening mode, the power consumption of device becomes overriding concern factor, thus device is waken up using the second preset strategy, the algoritic module function in the second preset strategy is relatively fewer, algorithm amount of calculation is low, small power consumption, and power consumption can be saved to greatest extent.So, different patterns is in for device, using different interactive modes, effectively improves Consumer's Experience.
Description
Technical field
The present invention relates to electronic device field, more particularly to a kind of method and apparatus for supporting awakening mode to automatically switch.
Background technology
With the development and the progress of society of science and technology, the life of people has obtained very big improvement, the requirement to electronic product
Also more and more higher.Intelligent sound interaction is exactly wherein important one, is known by inserting pickup module and voice in the electronic device
Other module, user can be controlled by sound to electronic equipment, so as to lift Consumer's Experience.Intelligent sound interaction is near several
Year much-talked-about topic, the international major company such as Amazon, Google is all successively proposed intelligent sound box as promoting respective artificial intelligence
The entry of development.
At present, the most of portable intelligent audio amplifiers of in the market all use key wakeup pattern, and it needs user to be manually pressed by
Associated button on intelligent sound box, just can be achieved the wake-up to intelligent sound box, bad sensory experience is brought to user.And prop up
The audio amplifier of speech identifying function is held, its pattern worked is usually that power supply is directly powered awakening mode, due to the algorithm of use
Because amount of calculation is larger, power consumption is often higher.Once audio amplifier is under battery operated mode, battery electric quantity will be drained unnecessarily quickly.
The content of the invention
For this reason, it may be necessary to a kind of technical scheme for supporting awakening mode to automatically switch be provided, for solving intelligent sound electronics
Power consumption that equipment is present is big, poor user experience the problems such as.
To achieve the above object, the device for supporting that awakening mode automatically switches is inventor provided, described device includes electricity
Source detection unit, microphone, pattern determining unit, low-power consumption pickup unit, high-performance pickup unit, voice recognition unit, calculation
Method functional module, memory cell and wakeup unit, the power detecting unit are connected with pattern determining unit, the microphone point
It is not connected with low-power consumption pickup unit, high-performance pickup unit；The high-performance pickup unit includes the first microphone and enables list
Member, the first algorithm function module enabling unit and the first algorithm enabling unit；The low-power consumption pickup unit includes the second Mike
Wind enabling unit, the second algorithm function module enabling unit and the second algorithm enabling unit；The memory cell is respectively with first
Algorithm enabling unit, the connection of the second algorithm enabling unit；
The power detecting unit is used to detect whether present apparatus powers；
The pattern determining unit is used for the corresponding awakening mode of electric power thus supplied determining device according to present apparatus, described
Awakening mode includes power supply awakening mode and battery awakening mode；
When device is in power supply awakening mode, the first microphone enabling unit is used to be made according to the first preset strategy
The energy microphone, the first algorithm function module enabling unit is used to enable algorithm function mould according to the first preset strategy
Block, the first algorithm enabling unit is used to enable algorithm function module correspondence determined by the first preset strategy in memory cell
The first algorithm and perform, handled so that the audio-frequency information that is caught to microphone performs first；
When device is in battery awakening mode, the second microphone enabling unit is used to be made according to the second preset strategy
The energy microphone, the second algorithm function module enabling unit is used to enable algorithm function mould according to the second preset strategy
Block, the second algorithm enabling unit is used to enable algorithm function module correspondence determined by the second preset strategy in memory cell
The second algorithm and perform, so that the audio-frequency information that is caught to microphone performs second processing；
Audio-frequency information and preset audio letter that the voice recognition unit is used to perform after the first processing or second processing
Breath is compared, and wakeup unit is used to wake up described device if matching；Otherwise wakeup unit is not entered to described device
Row wakes up.
Further, the memory cell be additionally operable to storage the first speech recognition algorithm and the second speech recognition algorithm and its
Corresponding matching template；It is described " audio-frequency information that voice recognition unit is used to perform after the first processing or second processing with it is pre-
If audio-frequency information is compared " include：When device is in power supply awakening mode, the voice recognition unit is used to use first
The audio-frequency information performed after the first processing is compared speech recognition algorithm with preset audio information；When device is called out in battery
Wake up pattern when, the voice recognition unit be used for using the second speech recognition algorithm will perform second processing after audio-frequency information with
Preset audio information is compared.
Further, described device also includes key wakeup unit；The key wakeup unit is connected with wakeup unit；Institute
Stating key wakeup unit is used to receive key wakeup instruction, and described device is waken up.
Further, the algorithm function module includes sound source positioning function module, Wave beam forming functional module, noise suppression
Functional module processed, removal obscure the one or more in functional module, echo cancellation performance module, long-range pickup functional module.
Inventor additionally provides a kind of method for supporting awakening mode to automatically switch, and methods described is applied to support to wake up mould
Formula automatically switch device, described device include power detecting unit, microphone, pattern determining unit, low-power consumption pickup unit,
High-performance pickup unit, voice recognition unit, algorithm function module, memory cell and wakeup unit, the power detecting unit
It is connected with pattern determining unit, the microphone is connected with low-power consumption pickup unit, high-performance pickup unit respectively；The high property
Energy pickup unit includes the first microphone enabling unit, the first algorithm function module enabling unit and the first algorithm enabling unit；
The low-power consumption pickup unit, which includes second microphone enabling unit, the second algorithm function module enabling unit and the second algorithm, to be made
Can unit；The memory cell is connected with the first algorithm enabling unit, the second algorithm enabling unit respectively；Methods described includes：
Whether power detecting unit detection present apparatus powers；
Pattern determining unit is according to the corresponding awakening mode of electric power thus supplied determining device of present apparatus, the awakening mode
Including power supply awakening mode and battery awakening mode；
When device is in power supply awakening mode, methods described includes：First microphone enabling unit is default according to first
The policy enabled microphone, the first algorithm function module enabling unit enables algorithm function module according to the first preset strategy,
First algorithm enabling unit enables corresponding first algorithm of algorithm function module determined by the first preset strategy in memory cell
And perform, handled so that the audio-frequency information caught to microphone performs first；
When device is in battery awakening mode, methods described includes：Second microphone enabling unit is default according to second
The policy enabled microphone, the second algorithm function module enabling unit enables algorithm function module according to the second preset strategy,
Second algorithm enabling unit enables corresponding second algorithm of algorithm function module determined by the second preset strategy in memory cell
And perform, so that the audio-frequency information caught to microphone performs second processing；
After the audio-frequency information caught to microphone performs the first processing or second processing, methods described also includes：Language
The audio-frequency information performed after the first processing or second processing is compared sound recognition unit with preset audio information, if matching
Wakeup unit wakes up to described device；Otherwise wakeup unit does not wake up to described device.
Further, the memory cell is additionally operable to the first speech recognition algorithm of storage and the second speech recognition algorithm；Institute
State step " audio-frequency information and the progress of preset audio information that voice recognition unit is used to perform after the first processing or second processing
Compare " include：
When device is in power supply awakening mode, voice recognition unit will be performed at first using the first speech recognition algorithm
Audio-frequency information after reason is compared with preset audio information；
Or, when device is in battery awakening mode, voice recognition unit will be performed using the second speech recognition algorithm
Audio-frequency information after second processing is compared with preset audio information.
Further, described device also includes key wakeup unit；The key wakeup unit is connected with wakeup unit；Institute
The method of stating includes：
Key wakeup unit receives key wakeup instruction, and described device is waken up.
Further, the algorithm function module includes sound source positioning function module, Wave beam forming functional module, noise suppression
Functional module processed, removal obscure the one or more in functional module, echo cancellation performance module, long-range pickup functional module.
The present invention has advantages below：Detect whether present apparatus powers by power detecting unit, to allow pattern to determine
The corresponding awakening mode of unit determining device.When device is in power supply awakening mode, power consumption is not the factor of overriding concern, because
And device is waken up using the first preset strategy, the algoritic module function in the first preset strategy is more, algorithm comprehensive, performance
Height, so as to meet user's request to greatest extent；When device is in battery awakening mode, the power consumption of device, which becomes, primarily to be examined
Worry factor, thus device is waken up using the second preset strategy, the algoritic module function in the second preset strategy is relatively
Less, algorithm amount of calculation is low, small power consumption, and power consumption can be saved to greatest extent.So, different patterns is in for device, adopted
With different interactive modes, Consumer's Experience is effectively improved.
Brief description of the drawings
Fig. 1 is the schematic diagram for the device that the support awakening mode that an embodiment of the present invention is related to automatically switches；
Fig. 2 is the flow chart for the method that the support awakening mode that an embodiment of the present invention is related to automatically switches；
Description of reference numerals：
101st, power detecting unit；
102nd, microphone；
103rd, pattern determining unit；
104th, high-performance pickup unit；114th, microphone enabling unit；124th, the first algorithm function module enabling unit；
134th, the first algorithm enabling unit；
105th, low-power consumption pickup unit；115th, second microphone enabling unit；125th, the second algorithm function module enables single
Member；135th, the second algorithm enabling unit；
106th, voice recognition unit；
107th, algorithm function module；
108th, memory cell；
109th, wakeup unit.
Embodiment
To describe the technology contents of technical scheme in detail, feature, the objects and the effects being constructed, below in conjunction with specific reality
Apply example and coordinate accompanying drawing to be explained in detail.
Referring to Fig. 1, the schematic diagram of the device automatically switched for the support awakening mode that an embodiment of the present invention is related to.
Described device is the electronic equipment with speech processes and speech identifying function, such as intelligent sound box, intelligent sound terminal.It is described
Device includes power detecting unit 101, microphone 102, pattern determining unit 103, low-power consumption pickup unit 104, high-performance and picked up
Sound unit 105, voice recognition unit 106, algorithm function module 107, memory cell 108 and wakeup unit 109, the power supply inspection
Survey unit 101 to be connected with pattern determining unit 103, the microphone 102 is picked up with low-power consumption pickup unit 104, high-performance respectively
Sound unit 105 is connected；The high-performance pickup unit 104 includes the first microphone enabling unit 114, the first algorithm function module
The algorithm enabling unit 134 of enabling unit 124 and first；The low-power consumption pickup unit 105 includes second microphone enabling unit
115th, the second algorithm function module enabling unit 125 and the second algorithm enabling unit 135；The memory cell 108 is respectively with
One algorithm enabling unit 134, the second algorithm enabling unit 135 are connected；
The power detecting unit 101 is used to detect whether present apparatus powers, and the pattern determining unit 103 is used for root
According to the corresponding awakening mode of electric power thus supplied determining device of present apparatus.The awakening mode includes power supply awakening mode and battery
Awakening mode.The power detecting unit can be realized with power sense circuit, when device is connected with external power supply, then table
It is power supply state to show present apparatus, and pattern determining unit determines that the power supply awakening mode of present apparatus is power supply awakening mode；When
When device disconnects with external power supply, then it represents that present apparatus is non-powered state, pattern determining unit determines the confession of present apparatus
Electric awakening mode is battery awakening mode.External power supply can be dc source, AC power etc., or mobile external electricity
Source device, such as charger baby.Pattern determining unit can be realized by register, and the value of register such as is entered as into " 1 ", table
It is power supply awakening mode to show the power supply awakening mode of present apparatus；The value of register is entered as " 0 ", the confession of present apparatus is represented
Electric awakening mode is battery awakening mode.
When device is in power supply awakening mode, the first microphone enabling unit is used to be made according to the first preset strategy
The energy microphone, the first algorithm function module enabling unit is used to enable algorithm function mould according to the first preset strategy
Block.The first algorithm enabling unit is used to enable algorithm function module correspondence determined by the first preset strategy in memory cell
The first algorithm and perform, handled so that the audio-frequency information that is caught to microphone performs first.First preset strategy is
Include determination of number of microphone, the quantity of algorithm function module and each corresponding algorithm of algorithm function module etc..The
For one preset strategy is compared to the second preset strategy, number of microphone that it is included is more, algorithm function module quantity more
The performance of many, determination algorithm to be run is also higher.When device is in power supply awakening mode, power consumption is not overriding concern
Factor, is calculated using the high algorithm of performance, effectively the audio user collected can be handled and recognized, it is ensured that language
Sound recognition success rate, so as to meet user's request to greatest extent.
When device is in battery awakening mode, the second microphone enabling unit is used to be made according to the second preset strategy
The energy microphone, the second algorithm function module enabling unit is used to enable algorithm function mould according to the second preset strategy
Block, the second algorithm enabling unit is used to enable algorithm function module correspondence determined by the second preset strategy in memory cell
The second algorithm and perform, so that the audio-frequency information that is caught to microphone performs second processing.When device wakes up in battery
During pattern, the power consumption of device becomes overriding concern factor, thus device is waken up using the second preset strategy, and second is pre-
If algoritic module function in strategy is relatively fewer, algorithm amount of calculation is low, small power consumption, and power consumption can be saved to greatest extent.The
One preset strategy and the second preset strategy can be adjusted setting according to being actually needed for user.
In certain embodiments, the algorithm function module include sound source positioning function module, Wave beam forming functional module,
Noise suppression function module, removal obscure functional module, echo cancellation performance module, one kind in long-range pickup functional module or
It is a variety of.
Exemplified by including the intelligent sound box of 6 microphones, when intelligent sound box is in power supply awakening mode, the first Mike
Wind enabling unit all enables 6 microphones, so that Mike's wind energy more delicately captures audio-frequency information.Meanwhile, first
Algorithm function module enabling unit can by sound source positioning function module, Wave beam forming functional module, noise suppression function module,
Removal is obscured functional module, echo cancellation performance module, long-range pickup functional module and all enabled, so as to incoming to microphone
Audio-frequency information carry out auditory localization, Wave beam forming, noise suppression, removal obscure, the processing such as echo cancellor, long-range pickup so that
Most crucial audio signal (sound that user is sent) is extracted, transmits to voice recognition unit and is compared.In addition, storage
Be stored with each corresponding algorithm of algorithm function module, by taking sound source positioning function module as an example, auditory localization algorithm in unit
Quantity is multiple, and the amount of calculation of each algorithm is also different.Under normal circumstances, its performance of the larger algorithm of amount of calculation is relatively
Height, but its power consumption is also of a relatively high.When device is in power supply awakening mode, power consumption is not the factor of overriding concern, for each
The corresponding algorithm of individual algorithm function module, can use the high algorithm of performance in memory cell be calculated.
When intelligent sound box is in battery awakening mode, second microphone enabling unit enables mi-crophone part (as only
Enable 2 microphones), handle, only needed without using all algorithm functions for the audio-frequency information that microphone is caught
Using which part algorithm function module, for example only carry out noise suppression, remove obscure, echo cancellor, without carrying out sound
Source positioning, Wave beam forming, long-range pickup.Accordingly, the second algorithm function module enabling unit enable noise suppression function module,
Functional module, echo cancellation performance module are obscured in removal, to reach the purpose for saving power consumption.For each algorithm function module pair
On the algorithms selection answered, it can use in memory cell the relatively low amount of calculation that is stored, small power consumption algorithm performs and to sound
Frequency information carries out second processing.
The voice recognition unit 106 is used to that audio-frequency information and preset audio after the first processing or second processing will to be performed
Information is compared, and wakeup unit 109 is used to wake up described device if matching；Otherwise wakeup unit 109 is not to institute
Device is stated to be waken up.In the present embodiment, the memory cell 108 is additionally operable to store the first speech recognition algorithm and second
Speech recognition algorithm；It is described that " audio-frequency information that voice recognition unit is used to perform after the first processing or second processing is with presetting
Audio-frequency information is compared " include：When device is in power supply awakening mode, the voice recognition unit 106 is used to use the
The audio-frequency information performed after the first processing is compared one speech recognition algorithm with preset audio information；When device is in battery
During awakening mode, the voice recognition unit 106 is used to that the audio after second processing will to be performed using the second speech recognition algorithm
Information is compared with preset audio information.
In short, the different speech recognition algorithms that are stored with memory cell, can when device is in power supply awakening mode
To carry out speech recognition using the speech recognition algorithm of performance higher (power consumption is also of a relatively high), to improve speech recognition success
Rate；And when device is in battery awakening mode, can be entered using the speech recognition algorithm of power consumption relatively low (performance is relatively low)
Row speech recognition, to reach the purpose for saving power consumption.
In certain embodiments, described device also includes key wakeup unit；The key wakeup unit and wakeup unit
Connection；The key wakeup unit is used to receive key wakeup instruction, and described device is waken up.In other embodiments
In, described device also includes Bluetooth unit or wifi wakeup units, and user can pass through the bluetooth module of terminal and this hair
The Bluetooth unit of bright device is docked, and realizes the wake-up to device；Can certainly be by the wifi module of terminal
Docked with the wifi wakeup units of the device of the present invention, the signal transmitted by wifi connections realizes the wake-up to device.
In short, the mode waken up to device is not only limited to the mode of voice wake-up, other wake-up modes can also be included, used
Family can be waken up according to itself hobby using corresponding wake-up mode to device, lift Consumer's Experience.
Referring to Fig. 2, the flow chart of the method automatically switched for the support awakening mode that an embodiment of the present invention is related to.
Methods described is applied to support the device that awakening mode automatically switches, and described device includes power detecting unit, microphone, pattern
Determining unit, low-power consumption pickup unit, high-performance pickup unit, voice recognition unit, algorithm function module, memory cell and call out
Wake up unit, the power detecting unit is connected with pattern determining unit, the microphone respectively with low-power consumption pickup unit, Gao Xing
Can pickup unit connection；The high-performance pickup unit includes the first microphone enabling unit, the first algorithm function module and enabled
Unit and the first algorithm enabling unit；The low-power consumption pickup unit includes second microphone enabling unit, the second algorithm function
Module enabling unit and the second algorithm enabling unit；The memory cell makes with the first algorithm enabling unit, the second algorithm respectively
Can unit connection；Methods described includes：
Initially enter whether step S201 power detecting units detection present apparatus powers, if it is true then to enter step S202
It is power supply awakening mode to determine the corresponding awakening mode of device, and it is electricity otherwise to enter the corresponding awakening mode of step S203 determining devices
Pond awakening mode.
When device is in power supply awakening mode, step S203 the first microphone enabling units can be entered after step S202
The microphone is enabled according to the first preset strategy, the first algorithm function module enabling unit is enabled according to the first preset strategy and calculated
Method functional module；And enter in step the first algorithms of S204 enabling unit enable memory cell determined by the first preset strategy
Corresponding first algorithm of algorithm function module is simultaneously performed, and is handled so that the audio-frequency information caught to microphone performs first；
When device is in battery awakening mode, step S206 second microphone enabling units can be entered after step S205
The microphone is enabled according to the second preset strategy, the second algorithm function module enabling unit is enabled according to the second preset strategy and calculated
Method functional module；And enter in step the second algorithms of S207 enabling unit enable memory cell determined by the second preset strategy
Corresponding second algorithm of algorithm function module is simultaneously performed, so that the audio-frequency information caught to microphone performs second processing；
After step S206 or step S207, methods described also includes：Step S208 voice recognition units will be performed at first
Audio-frequency information after reason or second processing is compared with preset audio information, and step S209 wakeup units pair are entered if matching
Described device is waken up；Otherwise described device is not waken up into step S10 wakeup units.
In certain embodiments, the memory cell is additionally operable to the first speech recognition algorithm of storage and the second speech recognition is calculated
Method；Step " audio-frequency information and preset audio letter that voice recognition unit is used to perform after the first processing or second processing
Breath is compared " include：When device is in power supply awakening mode, voice recognition unit will be held using the first speech recognition algorithm
Audio-frequency information after the processing of row first is compared with preset audio information；Or, when device is in battery awakening mode, language
Sound recognition unit is compared the audio-frequency information performed after second processing with preset audio information using the second speech recognition algorithm
It is right.The preset audio information can be the voice match template being stored in memory cell, and the voice match template can be with
It is the prompting audio-frequency information that system is carried, can also be set according to the hobby of user is self-defined.
In certain embodiments, described device also includes key wakeup unit；The key wakeup unit and wakeup unit
Connection；Methods described includes：Key wakeup unit receives key wakeup instruction, and described device is waken up.In other realities
Apply in example, described device also includes Bluetooth unit or wifi wakeup units, user can by the bluetooth module of terminal with
The Bluetooth unit of the device of the present invention is docked, and realizes the wake-up to device；Can certainly be by the wifi of terminal
Module is docked with the wifi wakeup units of the device of the present invention, and the signal transmitted by wifi connections is realized and device is called out
Wake up.In short, the mode waken up to device is not only limited to the mode of voice wake-up, other wake-up sides can also be included
Formula, user can be waken up according to itself hobby using corresponding wake-up mode to device, lift Consumer's Experience.
In certain embodiments, the algorithm function module include sound source positioning function module, Wave beam forming functional module,
Noise suppression function module, removal obscure functional module, echo cancellation performance module, one kind in long-range pickup functional module or
It is a variety of.In preferred embodiment, when device is in power supply awakening mode, algorithm function module enabling unit enables above-mentioned all
Algorithm function module, meets user's request, lifts Consumer's Experience.When device is in battery awakening mode, algorithm function module
Enabling unit enables above-mentioned some algorithm functional module, to reach the purpose for saving power consumption.
The present invention has advantages below：Detect whether present apparatus powers by power detecting unit, to allow pattern to determine
The corresponding awakening mode of unit determining device.When device is in power supply awakening mode, power consumption is not the factor of overriding concern, because
And device is waken up using the first preset strategy, the algoritic module function in the first preset strategy is more, algorithm comprehensive, performance
Height, so as to meet user's request to greatest extent；When device is in battery awakening mode, the power consumption of device, which becomes, primarily to be examined
Worry factor, thus device is waken up using the second preset strategy, the algoritic module function in the second preset strategy is relatively
Less, algorithm amount of calculation is low, small power consumption, and power consumption can be saved to greatest extent.So, different patterns is in for device, adopted
With different interactive modes, Consumer's Experience is effectively improved.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposited between operating
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that process, method, article or terminal device including a series of key elements not only include those
Key element, but also other key elements including being not expressly set out, or also include being this process, method, article or end
The intrinsic key element of end equipment.In the absence of more restrictions, limited by sentence " including ... " or " including ... "
Key element, it is not excluded that also there is other key element in the process including the key element, method, article or terminal device.This
Outside, herein, " being more than ", " being less than ", " exceeding " etc. are interpreted as not including this number；" more than ", " following ", " within " etc. understand
It is to include this number.
It should be understood by those skilled in the art that, the various embodiments described above can be provided as method, device or computer program production
Product.These embodiments can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.All or part of step in the method that the various embodiments described above are related to can be instructed by program correlation hardware come
Complete, described program can be stored in the storage medium that computer equipment can be read, for performing the various embodiments described above side
All or part of step described in method.The computer equipment, includes but is not limited to：Personal computer, server, general-purpose computations
Machine, special-purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, intelligent home device, Wearable
Smart machine, vehicle intelligent equipment etc.；Described storage medium, includes but is not limited to：RAM, ROM, magnetic disc, tape, CD, sudden strain of a muscle
Deposit, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage etc..
The various embodiments described above are with reference to method, equipment (system) and the computer program product according to embodiment
Flow chart and/or block diagram are described.It should be understood that can be by every in computer program instructions implementation process figure and/or block diagram
One flow and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computers can be provided
Programmed instruction is to the processor of computer equipment to produce a machine so that pass through the finger of the computing device of computer equipment
Order, which is produced, to be used to realize what is specified in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
The device of function.
These computer program instructions may be alternatively stored in the computer that computer equipment can be guided to work in a specific way and set
In standby readable memory so that the instruction being stored in the computer equipment readable memory, which is produced, includes the manufacture of command device
Product, the command device is realized to be referred in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
Fixed function.
These computer program instructions can be also loaded into computer equipment so that performed on a computing device a series of
Operating procedure is to produce computer implemented processing, so that the instruction performed on a computing device is provided for realizing in flow
The step of function of being specified in one flow of figure or multiple flows and/or one square frame of block diagram or multiple square frames.
Although the various embodiments described above are described, those skilled in the art once know basic wound
The property made concept, then can make other change and modification to these embodiments, so embodiments of the invention are the foregoing is only,
Not thereby the scope of patent protection of the present invention, the equivalent structure that every utilization description of the invention and accompanying drawing content are made are limited
Or equivalent flow conversion, or other related technical fields are directly or indirectly used in, similarly it is included in the patent of the present invention
Within protection domain.
Claims (8)
1. a kind of device for supporting awakening mode to automatically switch, it is characterised in that described device includes power detecting unit, Mike
Wind, pattern determining unit, low-power consumption pickup unit, high-performance pickup unit, voice recognition unit, algorithm function module, storage
Unit and wakeup unit, the power detecting unit are connected with pattern determining unit, the microphone respectively with low-power consumption pickup
Unit, the connection of high-performance pickup unit；The high-performance pickup unit includes the first microphone enabling unit, the first algorithm function
Module enabling unit and the first algorithm enabling unit；The low-power consumption pickup unit includes second microphone enabling unit, second
Algorithm function module enabling unit and the second algorithm enabling unit；The memory cell respectively with the first algorithm enabling unit,
Two algorithm enabling units are connected；
The power detecting unit is used to detect whether present apparatus powers；
The pattern determining unit is used for the corresponding awakening mode of electric power thus supplied determining device according to present apparatus, the wake-up
Pattern includes power supply awakening mode and battery awakening mode；
When device is in power supply awakening mode, the first microphone enabling unit is used to enable institute according to the first preset strategy
Microphone is stated, the first algorithm function module enabling unit is used to enable algorithm function module, institute according to the first preset strategy
Stating the first algorithm enabling unit is used to enable algorithm function module determined by the first preset strategy in memory cell corresponding the
One algorithm is simultaneously performed, and is handled so that the audio-frequency information caught to microphone performs first；
When device is in battery awakening mode, the second microphone enabling unit is used to enable institute according to the second preset strategy
Microphone is stated, the second algorithm function module enabling unit is used to enable algorithm function module, institute according to the second preset strategy
Stating the second algorithm enabling unit is used to enable algorithm function module determined by the second preset strategy in memory cell corresponding the
Two algorithms are simultaneously performed, so that the audio-frequency information caught to microphone performs second processing；
The voice recognition unit is used to enter the audio-frequency information performed after the first processing or second processing with preset audio information
Row is compared, and wakeup unit is used to wake up described device if matching；Otherwise wakeup unit is not called out described device
Wake up.
2. the device for supporting awakening mode to automatically switch as claimed in claim 1, it is characterised in that the memory cell is also used
In the first speech recognition algorithm of storage and the second speech recognition algorithm；It is described that " voice recognition unit is used to that the first processing will to be performed
Or the audio-frequency information after second processing is compared with preset audio information " include：When device is in power supply awakening mode, institute
Stating voice recognition unit is used to by the audio-frequency information after the first processing is performed with preset audio believe using the first speech recognition algorithm
Breath is compared；When device is in battery awakening mode, the voice recognition unit is used to use the second speech recognition algorithm
The audio-frequency information performed after second processing is compared with preset audio information.
3. the device for supporting awakening mode to automatically switch as claimed in claim 1, it is characterised in that described device also includes pressing
Key wakeup unit；The key wakeup unit is connected with wakeup unit；The key wakeup unit refers to for receiving key wakeup
Order, wakes up to described device.
4. the device for supporting awakening mode to automatically switch as claimed in claim 1, it is characterised in that the algorithm function module
Obscure functional module, echo including sound source positioning function module, Wave beam forming functional module, noise suppression function module, removal
Eliminate the one or more in functional module, long-range pickup functional module.
5. a kind of method for supporting awakening mode to automatically switch, it is characterised in that methods described is applied to support awakening mode certainly
The device of dynamic switching, described device includes power detecting unit, microphone, pattern determining unit, low-power consumption pickup unit, Gao Xing
Can pickup unit, voice recognition unit, algorithm function module, memory cell and wakeup unit, the power detecting unit and mould
Formula determining unit is connected, and the microphone is connected with low-power consumption pickup unit, high-performance pickup unit respectively；The high-performance is picked up
Sound unit includes the first microphone enabling unit, the first algorithm function module enabling unit and the first algorithm enabling unit；It is described
Low-power consumption pickup unit includes second microphone enabling unit, the second algorithm function module enabling unit and the second algorithm and enables list
Member；The memory cell is connected with the first algorithm enabling unit, the second algorithm enabling unit respectively；Methods described includes：
Whether power detecting unit detection present apparatus powers；
Pattern determining unit includes according to the corresponding awakening mode of electric power thus supplied determining device of present apparatus, the awakening mode
Power supply awakening mode and battery awakening mode；
When device is in power supply awakening mode, methods described includes：First microphone enabling unit is according to the first preset strategy
The microphone is enabled, the first algorithm function module enabling unit enables algorithm function module, first according to the first preset strategy
Algorithm enabling unit is enabled corresponding first algorithm of algorithm function module determined by the first preset strategy and to be held in memory cell
OK, handled so that the audio-frequency information caught to microphone performs first；
When device is in battery awakening mode, methods described includes：Second microphone enabling unit is according to the second preset strategy
The microphone is enabled, the second algorithm function module enabling unit enables algorithm function module, second according to the second preset strategy
Algorithm enabling unit is used to enable corresponding second algorithm of algorithm function module determined by the second preset strategy in memory cell
And perform, so that the audio-frequency information caught to microphone performs second processing；
After the audio-frequency information caught to microphone performs the first processing or second processing, methods described also includes：Voice is known
The audio-frequency information performed after the first processing or second processing is compared other unit with preset audio information, is waken up if matching
Unit is used to wake up described device；Otherwise wakeup unit does not wake up to described device.
6. the method for supporting awakening mode to automatically switch as claimed in claim 5, it is characterised in that the memory cell is also used
In the first speech recognition algorithm of storage and the second speech recognition algorithm；" voice recognition unit is used to that first will to be performed the step
Audio-frequency information after processing or second processing is compared with preset audio information " include：
When device is in power supply awakening mode, voice recognition unit will be performed after the first processing using the first speech recognition algorithm
Audio-frequency information be compared with preset audio information；
Or, when device is in battery awakening mode, voice recognition unit will perform second using the second speech recognition algorithm
Audio-frequency information after processing is compared with preset audio information.
7. the method for supporting awakening mode to automatically switch as claimed in claim 5, it is characterised in that described device also includes pressing
Key wakeup unit；The key wakeup unit is connected with wakeup unit；Methods described includes：
Key wakeup unit receives key wakeup instruction, and described device is waken up.
8. the device for supporting awakening mode to automatically switch as claimed in claim 5, it is characterised in that the algorithm function module
Obscure functional module, echo including sound source positioning function module, Wave beam forming functional module, noise suppression function module, removal
Eliminate the one or more in functional module, long-range pickup functional module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710422108.3A CN107277672B (en) | 2017-06-07 | 2017-06-07 | Method and device for supporting automatic switching of wake-up mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710422108.3A CN107277672B (en) | 2017-06-07 | 2017-06-07 | Method and device for supporting automatic switching of wake-up mode |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107277672A true CN107277672A (en) | 2017-10-20 |
| CN107277672B CN107277672B (en) | 2020-01-10 |
Family
ID=60065914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710422108.3A Active CN107277672B (en) | 2017-06-07 | 2017-06-07 | Method and device for supporting automatic switching of wake-up mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107277672B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108093340A (en) * | 2017-12-25 | 2018-05-29 | 广州市尊浪电器有限公司 | A kind of speaker with intelligent switch machine |
| CN108182942A (en) * | 2017-12-28 | 2018-06-19 | 福州瑞芯微电子股份有限公司 | A kind of method and apparatus for supporting different virtual role interactions |
| CN108376059A (en) * | 2018-02-12 | 2018-08-07 | 山东师范大学 | A kind of all-purpose computer voice booting Rouser |
| CN108600898A (en) * | 2018-03-28 | 2018-09-28 | 深圳市冠旭电子股份有限公司 | A kind of method, wireless sound box and the terminal device of configuration wireless sound box |
| CN109036411A (en) * | 2018-09-05 | 2018-12-18 | 深圳市友杰智新科技有限公司 | A kind of intelligent terminal interactive voice control method and device |
| CN110738983A (en) * | 2018-07-02 | 2020-01-31 | 成都启英泰伦科技有限公司 | Multi-neural-network model voice recognition method based on equipment working state switching |
| CN111263312A (en) * | 2018-12-03 | 2020-06-09 | 深圳市广和通无线股份有限公司 | Tracker and tracking method thereof |
| CN111369999A (en) * | 2020-03-12 | 2020-07-03 | 北京百度网讯科技有限公司 | Signal processing method and device and electronic equipment |
| CN112581945A (en) * | 2019-09-29 | 2021-03-30 | 百度在线网络技术（北京）有限公司 | Voice control method and device, electronic equipment and readable storage medium |
| CN112820283A (en) * | 2019-11-18 | 2021-05-18 | 阿里巴巴集团控股有限公司 | Voice processing method, device and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202512508U (en) * | 2012-02-17 | 2012-10-31 | 安徽科大讯飞信息科技股份有限公司 | Voice awakening device |
| CN105376389A (en) * | 2014-08-19 | 2016-03-02 | 中兴通讯股份有限公司 | Voice wake-up method and device |
| US20160293168A1 (en) * | 2015-03-30 | 2016-10-06 | Opah Intelligence Ltd. | Method of setting personal wake-up word by text for voice control |
| CN106131302A (en) * | 2016-06-15 | 2016-11-16 | 乐视控股（北京）有限公司 | Audio play control method |
| 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 |
-
2017
- 2017-06-07 CN CN201710422108.3A patent/CN107277672B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202512508U (en) * | 2012-02-17 | 2012-10-31 | 安徽科大讯飞信息科技股份有限公司 | Voice awakening device |
| CN105376389A (en) * | 2014-08-19 | 2016-03-02 | 中兴通讯股份有限公司 | Voice wake-up method and device |
| US20160293168A1 (en) * | 2015-03-30 | 2016-10-06 | Opah Intelligence Ltd. | Method of setting personal wake-up word by text for voice control |
| CN106131302A (en) * | 2016-06-15 | 2016-11-16 | 乐视控股（北京）有限公司 | Audio play control method |
| 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 |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108093340A (en) * | 2017-12-25 | 2018-05-29 | 广州市尊浪电器有限公司 | A kind of speaker with intelligent switch machine |
| CN108182942A (en) * | 2017-12-28 | 2018-06-19 | 福州瑞芯微电子股份有限公司 | A kind of method and apparatus for supporting different virtual role interactions |
| CN108182942B (en) * | 2017-12-28 | 2021-11-26 | 瑞芯微电子股份有限公司 | Method and device for supporting interaction of different virtual roles |
| CN108376059A (en) * | 2018-02-12 | 2018-08-07 | 山东师范大学 | A kind of all-purpose computer voice booting Rouser |
| CN108376059B (en) * | 2018-02-12 | 2021-06-25 | 山东师范大学 | Universal computer voice starting awakening device |
| CN108600898B (en) * | 2018-03-28 | 2020-03-31 | 深圳市冠旭电子股份有限公司 | Method for configuring wireless sound box, wireless sound box and terminal equipment |
| CN108600898A (en) * | 2018-03-28 | 2018-09-28 | 深圳市冠旭电子股份有限公司 | A kind of method, wireless sound box and the terminal device of configuration wireless sound box |
| CN110738983A (en) * | 2018-07-02 | 2020-01-31 | 成都启英泰伦科技有限公司 | Multi-neural-network model voice recognition method based on equipment working state switching |
| CN109036411A (en) * | 2018-09-05 | 2018-12-18 | 深圳市友杰智新科技有限公司 | A kind of intelligent terminal interactive voice control method and device |
| CN111263312A (en) * | 2018-12-03 | 2020-06-09 | 深圳市广和通无线股份有限公司 | Tracker and tracking method thereof |
| CN112581945A (en) * | 2019-09-29 | 2021-03-30 | 百度在线网络技术（北京）有限公司 | Voice control method and device, electronic equipment and readable storage medium |
| CN112820283A (en) * | 2019-11-18 | 2021-05-18 | 阿里巴巴集团控股有限公司 | Voice processing method, device and system |
| CN111369999A (en) * | 2020-03-12 | 2020-07-03 | 北京百度网讯科技有限公司 | Signal processing method and device and electronic equipment |
| CN111369999B (en) * | 2020-03-12 | 2024-05-14 | 北京百度网讯科技有限公司 | Signal processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107277672B (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107277672A (en) | A kind of method and apparatus for supporting awakening mode to automatically switch | |
| KR102354275B1 (en) | Speech recognition method and apparatus, and storage medium | |
| CN104716750B (en) | A kind of low power consuming wireless power method and relevant apparatus, system | |
| CN107105359A (en) | One kind switching earphone mode of operation method and a kind of earphone | |
| CN108810280A (en) | Processing method, device, storage medium and the electronic equipment of voice collecting frequency | |
| CN205788350U (en) | A kind of intelligent sound electronic lock | |
| CN105808108A (en) | Unlocking control method and mobile terminal | |
| US20160286489A1 (en) | Terminal Energy-Saving Method, Terminal, And System | |
| CN103701981B (en) | A kind of method and device of realizing speech identifying function | |
| CN107317916A (en) | Application control method and related product | |
| CN111083678A (en) | Playing control method and system of Bluetooth sound box and intelligent device | |
| CN107147809A (en) | A kind of convenient call method of mobile terminal and system | |
| CN108845667A (en) | A kind of awakening method and its system of intelligence penny bank | |
| CN107797643A (en) | Reduce method, terminal and the computer-readable recording medium of terminal operating power consumption | |
| CN106612367A (en) | Speech wake method based on microphone and mobile terminal | |
| CN107256334A (en) | recipe matching method and related product | |
| CN110517677B (en) | Speech processing system, method, apparatus, speech recognition system, and storage medium | |
| CN204156936U (en) | A kind of acoustic control speech-sound intelligent mobile phone | |
| CN105529025A (en) | Voice operation input method and electronic device | |
| CN104133654B (en) | A kind of electronic equipment and information processing method | |
| CN109656719A (en) | Algorithm process method, apparatus, storage medium and terminal device | |
| CN108388842A (en) | Intelligent prompt method and Related product | |
| CN109215656A (en) | Speech remote controller device and method, storage medium, electronic device | |
| CN209606794U (en) | A kind of wearable device, sound-box device and intelligent home control system | |
| CN111078181A (en) | Method and system for playing intelligent music, storage medium and terminal equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 350003 building, No. 89, software Avenue, Gulou District, Fujian, Fuzhou 18, China Patentee after: Ruixin Microelectronics Co., Ltd Address before: 350003 building, No. 89, software Avenue, Gulou District, Fujian, Fuzhou 18, China Patentee before: Fuzhou Rockchips Electronics Co.,Ltd. |