CN107102713A - It is a kind of to reduce the method and device of power consumption - Google Patents
It is a kind of to reduce the method and device of power consumption Download PDFInfo
- Publication number
- CN107102713A CN107102713A CN201610094626.2A CN201610094626A CN107102713A CN 107102713 A CN107102713 A CN 107102713A CN 201610094626 A CN201610094626 A CN 201610094626A CN 107102713 A CN107102713 A CN 107102713A
- Authority
- CN
- China
- Prior art keywords
- signal
- threshold value
- predetermined threshold
- voice signal
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000009467 reduction Effects 0.000 abstract description 10
- 230000037007 arousal Effects 0.000 abstract description 4
- 230000005059 dormancy Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004880 explosion Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 1
- 235000015110 jellies Nutrition 0.000 description 1
- 239000008274 jelly Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001314 paroxysmal effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/3287—Power saving characterised by the action undertaken by switching off individual functional units in the computer system
-
- 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)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Selective Calling Equipment (AREA)
Abstract
The present invention relates to communication electronics field, more particularly to a kind of method and device of reduction power consumption.For solving the problem of smart machine power consumption with speech identifying function is high in the prior art.Sound identification module judges whether the signal received is voice signal, if it is, triggering software identifying system is analyzed the voice signal；Corresponding operating is realized to smart machine according to analysis result.When no matter the method that the present invention is provided only having sound identification module in running order, and software identifying system may be at dormancy or halted state, and the sound identification module can be directly realized by by hardware, and because the frequency of voice signal is very low, so the power consumption of sound identification module can accomplish very low, therefore power consumption when most of voice arousal function is enabled is saved, the stand-by time of smart machine is greatly extended, while also reducing the power consumption of smart machine.
Description
Technical field
The present invention relates to communication electronics field, more particularly to a kind of method and device of reduction power consumption.
Background technology
At present on the smart machines such as intelligent electric appliance, intelligent robot, intelligent sound control skill is mostly employed
Art.Intelligent sound control technology refers to as people, or specific people say one it is specific if when, make
Obtain intelligent electric appliance or intelligent robot performs default corresponding program.Typically realized in following two modes：
The first, as shown in figure 1, when using simulation microphone (Microphone, MIC) module,
Audio codec modules can gather the data that MIC modules are received, and Audio codec modules are by DAB
Signal sends software processing system (Software Process System) to and carries out processing parsing, smart machine
Corresponding operation is completed according to analysis result；
Second, as shown in Fig. 2 when use digital microphone module (Digital Microphone,
When DMIC), the data convert that digital microphone controller (DMIC Controller) exports DMIC
Into audio digital signals, it is then sent to software processing system (Software Process System) and is located
Understand analysis, smart machine completes corresponding operation according to analysis result.
But the inventors discovered that, in intelligent sound control technology of the prior art, before speaking,
The module such as MIC (DMIC), Audio codec (DMIC Controller), CPU, Memory all in
Working condition, can cause very high power consumption.But in actual use, smart machine is not connect when most of
Voice signal is received, when being not received by voice signal, the said equipment is still in working condition, because
This can produce many unnecessary power consumptions.For example in our low-power consumption environment, software processing system for
Minimum power consumption expense needed for identification is more than 10mW.In fact MIC (DMIC) power consumption of itself in fact only
There is 1mW or so.
The content of the invention
The embodiments of the invention provide a kind of method and apparatus for reducing power consumption, for solving band in the prior art
There is the problem of smart machine power consumption of speech identifying function is high.
A kind of method for reducing power consumption, methods described includes：
Sound identification module judges whether the signal received is voice signal, if it is, triggering software identification
System is analyzed the voice signal；
Corresponding operating is realized to smart machine according to analysis result.
It can be seen that, using method provided in an embodiment of the present invention, only sound identification module is constantly in work shape
State, i.e., detect whether to receive voice signal in real time, just triggers soft after sound identification module determines and receives signal
Part identifying system is analyzed voice signal and completes corresponding operation.The present embodiments relate to software
Identifying system, which includes CPU, RAM, FLASH flash memory etc., to be needed to know voice signal in the prior art
The module of the operations such as other and processing, it is seen then that when no matter the method that the present invention is provided only having voice knowledge
Other module is in running order, and software identifying system may be at dormancy or halted state, and the voice
Identification module can be directly realized by by hardware, and because the frequency of voice signal is very low, so speech recognition mould
The power consumption of block can accomplish very low, therefore save power consumption when most of voice arousal function is enabled, pole
The earth extends the stand-by time of smart machine, while also reducing the power consumption of smart machine.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of technical scheme of the invention or of the prior art
There is the accompanying drawing used required in technology description to be briefly described.
Fig. 1 for this first Voice command smart machine in the prior art structure chart；
Fig. 2 for this second of Voice command smart machine in the prior art structure chart；
Fig. 3 is a kind of method flow diagram of reduction power consumption provided in an embodiment of the present invention；
Fig. 4 is explosion sound oscillogram provided in an embodiment of the present invention；
Fig. 5 is knock oscillogram provided in an embodiment of the present invention；
Fig. 6 is specific a kind of method flow diagram of reduction power consumption provided in an embodiment of the present invention；
Fig. 7 is specific a kind of structure drawing of device of reduction power consumption provided in an embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understand the technical scheme in the embodiment of the present invention, and make this
Above-mentioned purpose, the feature and advantage of invention can be more obvious understandable, below in conjunction with the accompanying drawings to skill in the present invention
Art scheme is described in further detail.
Using method provided in an embodiment of the present invention, only sound identification module is constantly in working condition, i.e.,
Detect whether to receive voice signal in real time, software identification is just triggered after sound identification module determines and receives signal
System is analyzed voice signal and completes corresponding operation.The present embodiments relate to software recognize system
System includes CPU, RAM, FLASH flash memory etc. needs that voice signal is identified and locates in the prior art
The module of the operations such as reason, it is seen then that when no matter the method that the present invention is provided only having sound identification module
It is in running order, and software identifying system may be at dormancy or halted state, and the speech recognition mould
Block can be directly realized by by hardware, and because the frequency of voice signal is very low, so the work(of sound identification module
Consumption can accomplish very low, therefore save power consumption when most of voice arousal function is enabled, and greatly prolong
The stand-by time of smart machine is grown, while also reducing the power consumption of smart machine.As shown in figure 3, specific
Process is as follows：
Step 31, sound identification module judges whether the signal received is voice signal, if it is, touching
Part identifying system of feeling like jelly is analyzed the voice signal；
Step 32, corresponding operating is realized to smart machine according to analysis result.
Specifically, sound identification module judges whether the signal received is that voice signal includes：
Judge whether the signal is higher than default first predetermined threshold value；
When the signal is higher than the first predetermined threshold value, the signal is voice signal.
Specifically, the sound identification module judges whether the signal received is that voice signal includes：
Judge the signal whether between default first predetermined threshold value and the second predetermined threshold value；
When the signal is between the first predetermined threshold value and the second predetermined threshold value, the signal is believed for voice
Number.
Specifically, it is determined that the signal be higher than the first predetermined threshold value after, and it is determined that the signal be language
Before message number, further comprise：
Judge whether the signal duration exceedes preset time, it is voice if it is to determine the signal
Signal.
Specifically, it is determined that the signal be higher than the first predetermined threshold value after, and it is determined that the signal be language
Before message number, further comprise：
Judge whether the number of times that the signal occurs, and duration are respectively greater than preset times and default
Time, if it is, determining that the signal is voice signal.
Specifically, sound identification module judges whether the signal received is that voice signal includes：
Judge the signal whether outside default first predetermined threshold value and the second predetermined threshold value；
If it is, judge the number of times that the signal occurs, and whether duration is respectively greater than default time
Number and preset time, if it is, determining that the signal is voice signal.
Specifically, the number of times for judging that signal occurs includes：
Number of times is used as using the number of the crest value of the signal.
Specifically, the number of times for judging that signal occurs includes：When the signal is higher than the described first default threshold
During value, the beginning of this signal is used as；When the signal is less than into second predetermined threshold value, this is used as
The end of signal；The frequency of the signal is determined according to the beginning of the signal and end.
First predetermined threshold value is between noise signal peak value and voice signal peak value.
It is introduced below with specific embodiment：
Embodiment one：
A kind of method for reducing power consumption provided in an embodiment of the present invention, wherein sound identification module is located in equipment
Portion, when other modules in equipment are all in resting state, sound identification module is in detection voice in real time
The working condition of signal, detailed process is as follows：
Step one, sound identification module judges whether the signal received is voice signal, if it is, triggering
Software identifying system is analyzed the voice signal；
Sound identification module judges whether the signal received is that voice signal includes in this specific step：
When the signal is less than the first predetermined threshold value, it is not voice signal to determine the signal；
When the signal is higher than the first predetermined threshold value, it is voice signal to determine the signal.
Step 2, corresponding operating is realized according to analysis result to smart machine.
It can be seen that, after the method for the first the reduction power consumption provided using embodiment one, usable hardware realizes language
Sound identification module, now software identifying system, which can be constantly in, stops or resting state, when speech recognition mould
When block determines to have signal generation, just trigger software identifying system and carry out corresponding operating, can so substantially reduce
Power consumption.
But, the inventors discovered that, it is very short when running into some duration using the method in embodiment one
Signal be likely to also above the first predetermined threshold value but be not voice signal, for example, explosion sound, such as Fig. 4
Shown, wherein Bump is explosion sound, and Noise is noise, and Trigger level are the first predetermined threshold value, Voice
Voice signal for needed for.When smart machine receive be noise when, it is more likely that by explosion sound erroneous judgement
For voice signal, in order to avoid this phenomenon, the present invention provides another program：
Embodiment two：
The method that the embodiment of the present invention two is provided can filter out some non-voices on the basis of power consumption is reduced
The noise of signal, the difference with embodiment one is：It is determined that the signal that sound identification module is received is higher than
After first predetermined threshold value, and it is determined that the signal be voice signal before, further comprise：
Judge whether the signal duration exceedes preset time, if it is determine that the signal is believed for voice
Number.Preferably preset time can be set according to actual needs.
The method provided by embodiment two, paroxysmal sound can be filtered out well.
But the present inventors have additionally discovered that, reality in also exist some voice signals can more than the first predetermined threshold value,
But whether continuous sound, such as some knocks, as shown in figure 5, the value of the wherein visible knock
More than the first predetermined threshold value, and it continue for 4 times, but the duration is not above preset time, therefore should
It is filtered, it is specific as embodiment three is introduced：
Embodiment three：
On the basis for the method that the method that the embodiment of the present invention three is provided can be provided in embodiment two, enter one
Step filters out non-speech audio, and the difference with embodiment two is, it is determined that what sound identification module was received
Signal be higher than the first predetermined threshold value after, and it is determined that the signal be voice signal before, further comprise：
When judging whether the number of times that the signal occurs, and duration are respectively greater than preset times and are default
Between, if it is, determining that the signal is voice signal.Wherein preset times can be according to reality with preset time
Situation is set.
For example, in the embodiment three, if preset times are set to 10 times, preset time is set to 30ms,
Then can be by such a noise filtering.
The first predetermined threshold value mentioned into embodiment three in above-described embodiment one between noise signal peak value and
Between voice signal peak value.
The first predetermined threshold value is provided with example IV, the method for the reduction power consumption that the embodiment of the present invention four is provided
And second predetermined threshold value, after sound identification module receives signal, judge whether the signal is pre- first
If between threshold value and the second predetermined threshold value, it is voice signal if it is to determine the signal；And trigger software
Identifying system is analyzed the voice signal；Corresponding operating is realized to smart machine according to analysis result.
Embodiment five, the difference of the method and example IV of the reduction power consumption that the embodiment of the present invention five is provided exists
In, it is necessary to judge the number of times that the signal occurs, and duration whether be respectively greater than preset times and
Preset time, if it is, determining that the signal is voice signal.For example IV, embodiment
Five schemes provided are more suitable for judgement during multiple signals.
Embodiment six, the method that the embodiment of the present invention six provides the 6th kind of reduction power consumption, this method can be more
High frequency noise by a small margin is accurately and effectively filtered out, as shown in fig. 6, detailed process is as follows：
Step 61, when the external world produces certain sound, the sound identification module in equipment judges what is received
Whether signal is voice signal, and the method specifically judged is：
Judge the signal whether outside default first predetermined threshold value and the second predetermined threshold value；If
It is to perform step 62；Otherwise step 63 is performed；
Step 62, judge whether the number of times that the signal occurs, and duration are respectively greater than preset
Number of times and preset time, if performing step 64,；Otherwise step 63 is performed；
Step 63, determine what the signal produced for noise；
Step 64, it is voice signal to determine the signal；
Step 65, triggering software identifying system is analyzed the voice signal；According to analysis result pair
Smart machine realizes corresponding operating.
Judge that the number of times that signal occurs can be according to one of optional under type of actual conditions in above-described embodiment：
The first, number of times is used as using the number of the crest value of the signal；
Second, when the signal is higher than first predetermined threshold value, it is used as the beginning of this signal；Will
When the signal is less than second predetermined threshold value, the end of this signal is used as；According to opening for the signal
Begin and terminate the frequency of the determination signal.
, substantially can be only when there is voice signal after the embodiment provided using the present invention, voice is known
Other module starts software identifying system.Total power consumption more than 90% is being accounted for using software identifying system power consumption.
It is therefore assumed that saying within every 10 seconds that once command, i.e. sound identification module receive a voice signal, voice
Shi Changwei 2 seconds.Then power consumption more than 70% can be reduced using the program.Setting for intelligent electric appliance etc in fact
For standby, the instruction said for one day is general not over 100 times, for 100 times/24 hours, can drop
Low-power consumption 89.78%.
As shown in fig. 7, the embodiment of the present invention also provides a kind of device of reduction power consumption, including：
Sound identification module 71, whether the signal for judging to receive is voice signal；
Analysis module 73, for determining that received signal is voice signal when the sound identification module
When, triggering software identifying system is analyzed the voice signal；
Operation module 74, for realizing corresponding operating to smart machine according to analysis result.
The sound identification module 71 specifically for：Judge whether the signal is preset higher than default first
Threshold value；
When the signal is higher than the first predetermined threshold value, the signal is voice signal.
The sound identification module specifically for：Judge the signal whether default first predetermined threshold value with
And second between predetermined threshold value；
When the signal is between the first predetermined threshold value and the second predetermined threshold value, the signal is believed for voice
Number.
Described device also includes：Judge module 72, for judging it is pre- whether the signal duration exceedes
If the time, it is voice signal if it is to determine the signal.
Described device also includes：Judge module 72, for judging the number of times that the signal occurs, Yi Jichi
Whether the continuous time is respectively greater than preset times and preset time, if it is, determining that the signal is voice
Signal.
The sound identification module 71 specifically for：Judge the signal whether in the default first default threshold
Outside value and the second predetermined threshold value；
If it is, judge the number of times that the signal occurs, and whether duration is respectively greater than default time
Number and preset time, if it is, determining that the signal is voice signal.
Judge module 72 is additionally operable to, and number of times is used as using the number of the crest value of the signal.
The number of times for judging that signal occurs includes：
When the signal is higher than first predetermined threshold value, the beginning of this signal is used as；The signal is less than
During second predetermined threshold value, the end of this signal is used as；It is true according to the beginning of the signal and end
The frequency of the fixed signal.
In summary, beneficial effect：
Using method provided in an embodiment of the present invention, only sound identification module is constantly in working condition, i.e.,
Detect whether to receive voice signal in real time, software identification is just triggered after sound identification module determines and receives signal
System is analyzed voice signal and completes corresponding operation.The present embodiments relate to software recognize system
System includes CPU, RAM, FLASH flash memory etc. needs that voice signal is identified and locates in the prior art
The module of the operations such as reason, it is seen then that when no matter the method that the present invention is provided only having sound identification module
It is in running order, and software identifying system may be at dormancy or halted state, and the speech recognition mould
Block can be directly realized by by hardware, and because the frequency of voice signal is very low, so the work(of sound identification module
Consumption can accomplish very low, therefore save power consumption when most of voice arousal function is enabled, and greatly prolong
The stand-by time of smart machine is grown, while also reducing the power consumption of smart machine.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in this hair
Any modifications, equivalent substitutions and improvements made within bright spirit and principle etc., should be included in the present invention
Protection domain within.
Claims (14)
1. a kind of method for reducing power consumption, it is characterised in that methods described includes：
Sound identification module judges whether the signal received is voice signal, if it is, triggering software identifying system is analyzed the voice signal；
Corresponding operating is realized to smart machine according to analysis result.
2. the method as described in claim 1, it is characterised in that sound identification module judges whether the signal received is that voice signal includes：
Judge whether the signal is higher than default first predetermined threshold value；
When the signal is higher than the first predetermined threshold value, the signal is voice signal.
3. the method as described in claim 1, it is characterised in that the sound identification module judges whether the signal received is that voice signal includes：
Judge the signal whether between default first predetermined threshold value and the second predetermined threshold value；
When the signal is between the first predetermined threshold value and the second predetermined threshold value, the signal is voice signal.
4. method as claimed in claim 2, it is characterised in that after it is determined that the signal is higher than the first predetermined threshold value, and before it is determined that the signal is voice signal, further comprise：
Judge whether the signal duration exceedes preset time, it is voice signal if it is to determine the signal.
5. method as claimed in claim 2 or claim 3, it is characterised in that after it is determined that the signal is higher than the first predetermined threshold value, and before it is determined that the signal is voice signal, further comprise：
Judge whether the number of times that the signal occurs, and duration are respectively greater than preset times and preset time, if it is, determining that the signal is voice signal.
6. the method as described in claim 1, it is characterised in that sound identification module judges whether the signal received is that voice signal includes：
Judge the signal whether outside default first predetermined threshold value and the second predetermined threshold value；
If it is, judge the number of times that the signal occurs, and whether duration is respectively greater than preset times and preset time, if it is, determining that the signal is voice signal.
7. method as claimed in claim 5, it is characterised in that the number of times that the judgement signal occurs includes：
Number of times is used as using the number of the crest value of the signal.
8. method as claimed in claim 6, it is characterised in that the number of times that the judgement signal occurs includes：
When the signal is higher than first predetermined threshold value, the beginning of this signal is used as；When the signal is less than into second predetermined threshold value, the end of this signal is used as；The frequency of the signal is determined according to the beginning of the signal and end.
9. a kind of reduce the device of power consumption, it is characterised in that the device includes：
Sound identification module, whether the signal for judging to receive is voice signal；
Analysis module, for when it is voice signal that the sound identification module, which determines received signal, triggering software identifying system to be analyzed the voice signal；
Operation module, for realizing corresponding operating to smart machine according to analysis result.
10. device as claimed in claim 9, it is characterised in that the sound identification module specifically for：Judge whether the signal is higher than default first predetermined threshold value；
When the signal is higher than the first predetermined threshold value, the signal is voice signal.
11. device as claimed in claim 9, it is characterised in that the sound identification module specifically for：Judge the signal whether between default first predetermined threshold value and the second predetermined threshold value；
When the signal is between the first predetermined threshold value and the second predetermined threshold value, the signal is voice signal.
12. device as claimed in claim 10, it is characterised in that described device also includes：Judge module, for judging whether the signal duration exceedes preset time, it is voice signal if it is to determine the signal.
13. the device as described in claim 10 or 11, it is characterised in that described device also includes：Judge module, for judging whether the number of times that the signal occurs, and duration are respectively greater than preset times and preset time, if it is, determining that the signal is voice signal.
14. device as claimed in claim 9, it is characterised in that the sound identification module specifically for：Judge the signal whether outside default first predetermined threshold value and the second predetermined threshold value；
If it is, judge the number of times that the signal occurs, and whether duration is respectively greater than preset times and preset time, if it is, determining that the signal is voice signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610094626.2A CN107102713A (en) | 2016-02-19 | 2016-02-19 | It is a kind of to reduce the method and device of power consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610094626.2A CN107102713A (en) | 2016-02-19 | 2016-02-19 | It is a kind of to reduce the method and device of power consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107102713A true CN107102713A (en) | 2017-08-29 |
Family
ID=59658552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610094626.2A Pending CN107102713A (en) | 2016-02-19 | 2016-02-19 | It is a kind of to reduce the method and device of power consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107102713A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108668013A (en) * | 2018-04-06 | 2018-10-16 | 东莞市华睿电子科技有限公司 | mobile terminal unlocking method |
| CN110111789A (en) * | 2019-05-07 | 2019-08-09 | 百度国际科技（深圳）有限公司 | Voice interactive method, calculates equipment and computer-readable medium at device |
| CN110349566A (en) * | 2019-07-11 | 2019-10-18 | 龙马智芯（珠海横琴）科技有限公司 | Voice awakening method, electronic equipment and storage medium |
| CN110610710A (en) * | 2019-09-05 | 2019-12-24 | 晶晨半导体(上海)股份有限公司 | Construction device and construction method of self-learning voice recognition system |
| CN112106133A (en) * | 2018-05-09 | 2020-12-18 | 罗伯特·博世有限公司 | Method and device for aeroacoustic monitoring of a vehicle exterior and/or interior, vehicle and computer-readable storage medium |
| CN114885404A (en) * | 2022-05-06 | 2022-08-09 | 甄十信息科技（上海）有限公司 | Method and equipment for reducing call power consumption of smart watch |
-
2016
- 2016-02-19 CN CN201610094626.2A patent/CN107102713A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108668013A (en) * | 2018-04-06 | 2018-10-16 | 东莞市华睿电子科技有限公司 | mobile terminal unlocking method |
| CN112106133A (en) * | 2018-05-09 | 2020-12-18 | 罗伯特·博世有限公司 | Method and device for aeroacoustic monitoring of a vehicle exterior and/or interior, vehicle and computer-readable storage medium |
| CN110111789A (en) * | 2019-05-07 | 2019-08-09 | 百度国际科技（深圳）有限公司 | Voice interactive method, calculates equipment and computer-readable medium at device |
| CN110111789B (en) * | 2019-05-07 | 2022-02-08 | 阿波罗智联(北京)科技有限公司 | Voice interaction method and device, computing equipment and computer readable medium |
| CN110349566A (en) * | 2019-07-11 | 2019-10-18 | 龙马智芯（珠海横琴）科技有限公司 | Voice awakening method, electronic equipment and storage medium |
| CN110349566B (en) * | 2019-07-11 | 2020-11-24 | 龙马智芯（珠海横琴）科技有限公司 | Voice wake-up method, electronic device and storage medium |
| CN110610710A (en) * | 2019-09-05 | 2019-12-24 | 晶晨半导体(上海)股份有限公司 | Construction device and construction method of self-learning voice recognition system |
| CN110610710B (en) * | 2019-09-05 | 2022-04-01 | 晶晨半导体(上海)股份有限公司 | Construction device and construction method of self-learning voice recognition system |
| CN114885404A (en) * | 2022-05-06 | 2022-08-09 | 甄十信息科技（上海）有限公司 | Method and equipment for reducing call power consumption of smart watch |
| CN114885404B (en) * | 2022-05-06 | 2023-11-28 | 甄十信息科技（上海）有限公司 | Method and equipment for reducing communication power consumption of smart watch |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107102713A (en) | It is a kind of to reduce the method and device of power consumption | |
| CN103811003B (en) | A kind of audio recognition method and electronic equipment | |
| EP3522153B1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
| CN106448663B (en) | Voice awakening method and voice interaction device | |
| US8972252B2 (en) | Signal processing apparatus having voice activity detection unit and related signal processing methods | |
| KR20180084392A (en) | Electronic device and operating method thereof | |
| US20180293974A1 (en) | Spoken language understanding based on buffered keyword spotting and speech recognition | |
| CN108172242B (en) | Improved Bluetooth intelligent cloud sound box voice interaction endpoint detection method | |
| CN205051764U (en) | Electronic equipment | |
| CN103578468A (en) | Method for adjusting confidence coefficient threshold of voice recognition and electronic device | |
| CN110265036A (en) | Voice awakening method, system, electronic equipment and computer readable storage medium | |
| CN103198838A (en) | Abnormal sound monitoring method and abnormal sound monitoring device used for embedded system | |
| CN103871408A (en) | Method and device for voice identification and electronic equipment | |
| CN103971681A (en) | Voice recognition method and system | |
| CN103347136B (en) | Method and device for mobile phone energy saving processing | |
| WO2020253073A1 (en) | Speech endpoint detection method, apparatus and device, and storage medium | |
| CN105094816A (en) | Method for reducing power consumption of intelligent device and intelligent device | |
| CN103543814B (en) | Signal processing apparatus and signal processing method | |
| CN104050973A (en) | Low power audio trigger via intermittent sampling | |
| CN105118522A (en) | Noise detection method and device | |
| CN103941788A (en) | Chip adaptive voltage regulator and method | |
| CN111028831B (en) | Voice awakening method and device | |
| CN106531195A (en) | Dialogue conflict detection method and device | |
| CN111179924B (en) | Method and system for optimizing awakening performance based on mode switching | |
| CN113808585A (en) | Earphone awakening method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170829 |