CN110211605A - Smart machine speech sensitivity adjusting method, device, equipment and storage medium - Google Patents
Smart machine speech sensitivity adjusting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110211605A CN110211605A CN201910439164.7A CN201910439164A CN110211605A CN 110211605 A CN110211605 A CN 110211605A CN 201910439164 A CN201910439164 A CN 201910439164A CN 110211605 A CN110211605 A CN 110211605A
- Authority
- CN
- China
- Prior art keywords
- phonetic order
- smart machine
- phonetic
- triggering
- orders
- 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
- 230000035945 sensitivity Effects 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007619 statistical method Methods 0.000 claims abstract description 13
- 230000001960 triggered effect Effects 0.000 claims description 30
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 2
- 238000004378 air conditioning Methods 0.000 description 14
- 230000002354 daily effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
-
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses smart machine speech sensitivity adjusting method, device, equipment and storage mediums, wherein smart machine speech sensitivity adjusting method is the following steps are included: collect voice messaging corresponding to all phonetic orders that user issues to smart machine；It is for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes content；Summarize the sensitivity that all phonetic orders are accordingly arranged in content according to the phonetic order.Compared to traditional technology, the present invention can dynamically adjust the sensitivity of phonetic order, reduce the false wake-up rate of phonetic order and improve the positive wake-up rate of phonetic order, to can more match user for the voice control demand of smart machine.
Description
Technical field
The present invention relates to smart machine control fields, especially smart machine speech sensitivity adjusting method, device, equipment
And storage medium.
Background technique
Smart machine under current smart machine, especially interior living environment, no matter when, all voices refer to
The sensitivity of order is all fixed and invariable, i.e., dynamically will not be that each voice refers to according to the actual conditions of indoor living environment
The sensitivity for enabling matching suitable, will lead in this way: in the case where needing to meet user demand to execute the scene of phonetic order manipulation,
The wake-up rate of phonetic order is not high enough so that can not execute, or is not necessarily to execute the feelings under the scene of phonetic order manipulation in user
When condition, the false wake-up rate of phonetic order is too high so that wrong execution.
Summary of the invention
To solve the above-mentioned problems, the object of the present invention is to provide smart machine speech sensitivity adjusting method, device, set
Standby and storage medium can dynamically adjust the sensitivity of phonetic order, to can more match user for the voice of smart machine
Demand for control.
In order to make up for the deficiencies of the prior art, technical solution used in the embodiment of the present invention is:
Smart machine speech sensitivity adjusting method, comprising the following steps:
Collect voice messaging corresponding to all phonetic orders that user issues to smart machine；
It is for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes content；
Summarize the sensitivity that all phonetic orders are accordingly arranged in content according to the phonetic order.
Further, voice messaging corresponding to all phonetic orders that user issues to smart machine is collected, comprising:
Clock is matched for the smart machine；
Voice messaging corresponding to all phonetic orders that user issues to smart machine in several clock cycle is recorded,
Wherein, voice messaging corresponding to the phonetic order includes phonetic order triggering content and phonetic order triggered time.
Further, described for statistical analysis to voice messaging corresponding to all phonetic orders, obtain voice
Instruction summarizes content, comprising:
Between the time triggered between total degree, daily triggering times and adjacent triggering time for counting each phonetic order respectively
Every the triggering for obtaining all phonetic orders summarizes content.
Further, described content to be summarized according to the phonetic order the sensitive of all phonetic orders is accordingly set
Degree, comprising:
S31, given threshold range, the threshold range include triggering total degree threshold value, daily triggering times threshold value and phase
Time interval threshold value between neighbour's triggering time；
S32, will the triggering total degree of threshold range and each phonetic order, daily triggering times and it is adjacent triggering time between
Time interval compares；If the triggering total degree of phonetic order be more than it is described triggering total degree threshold value or phonetic order it is every
Day, triggering times were more than the time interval between the adjacent triggering time of the daily triggering times threshold value or phonetic order no more than institute
The time interval threshold value between adjacent triggering time is stated, then sets priority for the speech discrimination threshold of the phonetic order, otherwise sets
It is set to lag grade.
Further, voice messaging corresponding to the phonetic order further includes phonetic order triggering decibels.
Further, described for statistical analysis to voice messaging corresponding to all phonetic orders, obtain voice
Instruction summarizes content, further includes: counts interval the time required to the success to be triggered of each phonetic order respectively.
It further, further include step S30 between the step S31 and the step S32, the step S30 includes:
Set success required time interval threshold to be triggered；
To be spaced the time required to the success to be triggered of interval threshold and each phonetic order the time required to success to be triggered into
Row comparison, if interval threshold the time required to interval is more than the success to be triggered the time required to the success to be triggered of phonetic order,
It then sets the speech discrimination threshold of the phonetic order to priority and terminates to execute the step S32, otherwise execute the step
Rapid S32.
Smart machine speech sensitivity regulating device, comprising:
Information acquisition unit, for collecting the letter of voice corresponding to all phonetic orders that user issues to smart machine
Breath；
Storage unit, for for statistical analysis to voice messaging corresponding to all phonetic orders, acquisition
Phonetic order summarizes content；
Information process unit, for summarizing the spirit that all phonetic orders are accordingly arranged in content according to the phonetic order
Sensitivity.
Smart machine speech sensitivity adjustment equipment, including at least one control processor and for it is described at least one
The memory of control processor communication connection；The memory is stored with the finger that can be executed by least one described control processor
It enables, described instruction is executed by least one described control processor, so that at least one described control processor is able to carry out
State smart machine speech sensitivity adjusting method described in any technical solution.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer executable instructions,
The computer executable instructions are for making computer execute smart machine speech sensitivity described in any of the above-described technical solution
Adjusting method.
The one or more technical solutions provided in the embodiment of the present invention, at least have the following beneficial effects: and pass through collection
Phonetic order that user is issued simultaneously analyzes and counts information corresponding to phonetic order, and user can be recognized for intelligence
The control habit of energy equipment, to recognize the use demand of user, being based ultimately upon analysis statistical content can be to each phonetic order
Matching and modification sensitivity is carried out, to be more in line with the control habit of user, to reduce the false wake-up rate of phonetic order and mention
The positive wake-up rate of high phonetic order.Therefore, the present invention can dynamically adjust the sensitivity of phonetic order, reduce the mistake of phonetic order
Wake-up rate and the positive wake-up rate for improving phonetic order, to can more match user for the voice control demand of smart machine.
Detailed description of the invention
Present pre-ferred embodiments are provided, with reference to the accompanying drawing with the embodiment that the present invention will be described in detail.
Fig. 1 is the step schematic process flow diagram of smart machine speech sensitivity adjusting method of the embodiment of the present invention；
Fig. 2 is the structural schematic block diagram of smart machine speech sensitivity regulating device of the embodiment of the present invention；
Fig. 3 is a kind of specific implementation flow diagram of smart machine speech sensitivity adjusting method of the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
It should be noted that each feature in the embodiment of the present invention can be combined with each other, in this hair if do not conflicted
Within bright protection scope.In addition, though having carried out functional unit division in system schematic, shows patrol in flow charts
Volume sequence, but it is certain it is interior hold, can be shown in the dividing elements to be different from system or sequence in flow chart execute
The step of out or describing.
With reference to the accompanying drawing, the embodiment of the present invention is further elaborated.
Referring to Fig.1, the embodiment of the invention provides smart machine speech sensitivity adjusting methods, comprising the following steps:
S100, voice messaging corresponding to all phonetic orders that user issues to smart machine is collected；
It is S200, for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes
Content；
S300, summarize the sensitivity that all phonetic orders are accordingly arranged in content according to the phonetic order.
In the present embodiment, smart machine common are: air-conditioning, dust catcher and sweeping robot etc.；It is used by collecting
Phonetic order that family is issued simultaneously analyzes and counts information corresponding to phonetic order, and user can be recognized for intelligence
The control of equipment is accustomed to, to recognize the use demand of user, be based ultimately upon analysis statistical content can to each phonetic order into
Row Matching and modification sensitivity, being more in line with the control habit of user, reducing the false wake-up rate of phonetic order and improving voice
The positive wake-up rate of instruction.Therefore, the present invention can dynamically adjust the sensitivity of phonetic order, reduce the false wake-up rate of phonetic order
And the positive wake-up rate of phonetic order is improved, to can more match user for the voice control demand of smart machine.
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein collects
Voice messaging corresponding to all phonetic orders that user issues to smart machine, comprising:
S11, clock is matched for the smart machine；
S12, voice corresponding to all phonetic orders that user issues to smart machine in several clock cycle is recorded
Information, wherein voice messaging corresponding to the phonetic order includes phonetic order triggering content and phonetic order triggered time.
In the present embodiment, clock is convenient for control monitoring time section, so that acquisition time is limited to a specific time
In section, this meets actual demand；Simultaneously it is more convenient in terms of configuration, specific clock periodicity can according to the actual situation into
Row setting；Specifically, in terms of configuration, MCU can be carried on intelligent devices, when can match connection external crystal-controlled oscillation due to MCU
Clock module and repository, therefore there is the function of voice messaging corresponding to matching time clock feature and all phonetic orders of storage
Can, record information can use common infrared module to realize；
By taking air-conditioning as an example, time clock feature and instruction triggers writing function are added for air-conditioning voice socket model machine, with test body
Personnel are tested as user, by air-conditioning voice socket model machine distribute to test experience personnel carry out using.
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein described
It is for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes content, comprising:
Time between S21, the triggering total degree for counting each phonetic order respectively, daily triggering times and adjacent triggering time
Interval, the triggering for obtaining all phonetic orders summarize content.
In the present embodiment, triggering total degree can characterize the overall service condition of the phonetic order, and daily triggering times can
The dispersion service condition of the phonetic order is characterized, the time interval between adjacent triggering time can characterize the overall of the phonetic order and use
Frequency, the present embodiment more accurately qualitative phonetic order can actually be made by counting simultaneously to three of the above type
With situation, the case where judging by accident and its sensitivity is subjected to unreasonable regulation generation is prevented；
By taking air-conditioning as an example, personnel analyze statistics after tested, and " opening air-conditioning " and " closing air-conditioning " the two operating frequencies are most
It is high；(it is greater than 8 hours) in the case where closing air-conditioning for a long time and is again turned on air-conditioning, the operating frequency of temperature is adjusted in half an hour
It is high；The frequency that air-conditioning is operated again after opening 1 hour is lower；Air-conditioning, which is in the state that ultra-long time is closed, (is greater than 24
Hour), the operating frequency for carrying out opening air-conditioning again is lower etc.；It can recognize the use of user in real time by above-mentioned data
Demand.
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein described
Summarize the sensitivity that all phonetic orders are accordingly arranged in content according to the phonetic order, comprising:
S31, given threshold range, the threshold range include triggering total degree threshold value, daily triggering times threshold value and phase
Time interval threshold value between neighbour's triggering time；
S32, will the triggering total degree of threshold range and each phonetic order, daily triggering times and it is adjacent triggering time between
Time interval compares；If the triggering total degree of phonetic order be more than it is described triggering total degree threshold value or phonetic order it is every
Day, triggering times were more than the time interval between the adjacent triggering time of the daily triggering times threshold value or phonetic order no more than institute
The time interval threshold value between adjacent triggering time is stated, then sets priority for the speech discrimination threshold of the phonetic order, otherwise sets
It is set to lag grade.
In the present embodiment, each threshold value can be set by producer according to user's actual conditions Corresponding matching；The touching of phonetic order
It sends out total degree or daily triggering times is corresponding more than threshold range, then illustrate the phonetic order in long term time or short period
Access times it is very high, its service condition can be matched by being adjusted to priority at this time, similarly, it is adjacent triggering time between when
Between interval threshold similar designs, can equally match its service condition.
More specifically, voice threshold can be set to 1 grade, 2 grades, 3 grades and 4 grades, wherein 3 grades and 4 grades are priority, are called out
Effect of waking up is good, and false wake-up rate is high, and 1 grade and 2 grades is lag grade, and wake-up effect is general, and false wake-up rate is low；
Referring to Fig. 3, " Y " indicates "Yes" in figure, and " N " indicates "No", illustrate herein；Based on the above content, this can be provided
A kind of real work process of embodiment may is that
(1) assume that the initial speech threshold value of a phonetic order is arranged to 1 grade；
(2) waiting voice wakes up；
(3) judge whether voice is waken up, if being then transferred to step (4), be otherwise transferred to step (10)；
(4) judge that voice Wakeup interval whether more than 24 hours, if so, being then transferred to step (2), is otherwise transferred to step (5)；
(5) after voice wake-up, by voice threshold plus 4, that is, 4 grades are increased to；
(6) waiting voice instruction triggers；
(7) judge whether phonetic order triggers, if so, being then transferred to step (8), be otherwise transferred to step (6)；
(8) phonetic order is executed, and is transferred to step (6)；
(9) judge whether etc. to be triggered more than 10 seconds, if so, being transferred to step (2), be otherwise transferred to step (6)；
(10) judge whether speech discrimination threshold is 1 grade, if being then transferred to step (2), be otherwise transferred to step (11)；
(11) judge that whether voice wakes up more than 20 minutes, if being then transferred to step (12), be otherwise transferred to step (2)；
(12) speech discrimination threshold is reduced into a grade, is transferred to step (2).
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein described
Voice messaging corresponding to phonetic order further includes phonetic order triggering decibels.In the present embodiment, user can be obtained simultaneously
A decibel information of speaking can specifically be recorded realization using microphone and obtained preferably to be analyzed user's control scene.
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein described
It is for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes content, further includes: point
It is spaced the time required to the success to be triggered for not counting each phonetic order.In the present embodiment, being designed in this way targeted is mesh
Although the practical problem that preceding phonetic order sometimes is received but cannot be responded by smart machine, the time required to success to be triggered at once
Interval can characterize the triggering speed after phonetic order is received by smart machine, i.e. which phonetic order is easier to be triggered, than
As still by taking air-conditioning as an example, it is assumed that be divided into 1min between the time required to the success to be triggered.
Further, another embodiment of the present invention additionally provides smart machine speech sensitivity adjusting method, wherein described
It further include step S30 between step S31 and the step S32, the step S30 includes:
Set success required time interval threshold to be triggered；
To be spaced the time required to the success to be triggered of interval threshold and each phonetic order the time required to success to be triggered into
Row comparison, if interval threshold the time required to interval is more than the success to be triggered the time required to the success to be triggered of phonetic order,
It then sets the speech discrimination threshold of the phonetic order to priority and terminates to execute the step S32, otherwise execute the step
Rapid S32.
In the present embodiment, it is spaced the time required to the success to be triggered for preferentially judging phonetic order, if it is more than threshold value,
Illustrate that the phonetic order is not easy to be triggered, at this moment just further should preferentially improve its sensitivity, is just considered as voice later and refers to
The influence of the other voice messagings enabled, this meets practical application scene situation；Still by taking air-conditioning as an example, commonly use needed for success to be triggered
Time interval threshold value is 30s, is spaced 1min the time required to being less than success to be triggered, therefore should be by the voice of the phonetic order
Recognition threshold is set as priority.
Referring to Fig. 2, another embodiment of the present invention additionally provides smart machine speech sensitivity regulating device, comprising:
Information acquisition unit 130, for collecting voice corresponding to all phonetic orders that user issues to smart machine
Information；
Storage unit 140 is obtained for for statistical analysis to voice messaging corresponding to all phonetic orders
It obtains phonetic order and summarizes content；
All phonetic orders are accordingly arranged for summarizing content according to the phonetic order in information process unit 150
Sensitivity.
In the present embodiment, it should be noted that by smart machine speech sensitivity regulating device in this present embodiment
It is based on identical inventive concept with above-mentioned smart machine speech sensitivity adjusting method, it is therefore, corresponding in embodiment of the method
Content is equally applicable to present apparatus embodiment, and and will not be described here in detail.
Another embodiment of the present invention additionally provides smart machine speech sensitivity adjustment equipment, including at least one control
Manage device and the memory for communicating to connect at least one described control processor；The memory be stored with can by it is described extremely
The instruction that a few control processor executes, described instruction are executed by least one described control processor so that it is described at least
One control processor is able to carry out smart machine speech sensitivity adjusting method described in any of the above-described technical solution.
Another embodiment of the present invention additionally provides a kind of computer readable storage medium, the computer readable storage medium
Computer executable instructions are stored with, the computer executable instructions are for making computer execute any of the above-described technical solution institute
The smart machine speech sensitivity adjusting method stated.
Presently preferred embodiments of the present invention and basic principle is discussed in detail in the above content, but the invention is not limited to
Above embodiment, those skilled in the art should be recognized that also have on the premise of without prejudice to spirit of the invention it is various
Equivalent variations and replacement, these equivalent variations and replacement all fall within the protetion scope of the claimed invention.
Claims (10)
1. smart machine speech sensitivity adjusting method, which comprises the following steps:
Collect voice messaging corresponding to all phonetic orders that user issues to smart machine；
It is for statistical analysis to voice messaging corresponding to all phonetic orders, it obtains phonetic order and summarizes content；
Summarize the sensitivity that all phonetic orders are accordingly arranged in content according to the phonetic order.
2. smart machine speech sensitivity adjusting method according to claim 1, which is characterized in that collect user to intelligence
Voice messaging corresponding to all phonetic orders that equipment issues, comprising:
Clock is matched for the smart machine；
Voice messaging corresponding to all phonetic orders that user issues to smart machine in several clock cycle is recorded,
In, voice messaging corresponding to the phonetic order includes phonetic order triggering content and phonetic order triggered time.
3. smart machine speech sensitivity adjusting method according to claim 1, which is characterized in that described to described all
Voice messaging corresponding to phonetic order is for statistical analysis, obtains phonetic order and summarizes content, comprising:
The time interval between triggering total degree, daily triggering times and the adjacent triggering time of each phonetic order is counted respectively, is obtained
The triggering for obtaining all phonetic orders summarizes content.
4. according to any smart machine speech sensitivity adjusting method of claim 3, which is characterized in that described according to institute
It states phonetic order and summarizes the sensitivity that all phonetic orders are accordingly arranged in content, comprising:
S31, given threshold range, the threshold range include triggering total degree threshold value, daily triggering times threshold value and adjacent touching
Time interval threshold value between hair time；
S32, by the time between the triggering total degree of threshold range and each phonetic order, daily triggering times and adjacent triggering time
Interval compares；If the triggering total degree of phonetic order is more than the daily touching of the triggering total degree threshold value or phonetic order
The time interval sent out between the adjacent triggering time that number is more than the daily triggering times threshold value or phonetic order is no more than the phase
Time interval threshold value between neighbour's triggering time, then set priority for the speech discrimination threshold of the phonetic order, be otherwise provided as
Lag grade.
5. smart machine speech sensitivity adjusting method according to claim 1, which is characterized in that the phonetic order institute
Corresponding voice messaging further includes phonetic order triggering decibels.
6. smart machine speech sensitivity adjusting method according to claim 4, which is characterized in that described to described all
Voice messaging corresponding to phonetic order is for statistical analysis, obtains phonetic order and summarizes content, further includes: statistics is each respectively
Interval the time required to the success to be triggered of phonetic order.
7. smart machine speech sensitivity adjusting method according to claim 6, which is characterized in that the step S31 and
It further include step S30 between the step S32, the step S30 includes:
Set success required time interval threshold to be triggered；
It will interval carries out pair the time required to the success to be triggered of interval threshold and each phonetic order the time required to success to be triggered
Than, if interval threshold the time required to the success required time to be triggered interval of phonetic order is more than the success to be triggered, by
The speech discrimination threshold of the phonetic order is set as priority and terminates to execute the step S32, otherwise executes the step
S32。
8. smart machine speech sensitivity regulating device characterized by comprising
Information acquisition unit, for collecting voice messaging corresponding to all phonetic orders that user issues to smart machine；
Storage unit, for for statistical analysis to voice messaging corresponding to all phonetic orders, acquisition voice
Instruction summarizes content；
The sensitive of all phonetic orders is accordingly arranged for summarizing content according to the phonetic order in information process unit
Degree.
9. smart machine speech sensitivity adjustment equipment, which is characterized in that including at least one control processor and be used for and institute
State the memory of at least one control processor communication connection；The memory, which is stored with, to be handled by least one described control
The instruction that device executes, described instruction is executed by least one described control processor, so that at least one described control processor
It is able to carry out such as the described in any item smart machine speech sensitivity adjusting methods of claim 1-7.
10. a kind of computer readable storage medium, it is characterised in that: the computer-readable recording medium storage has computer can
It executes instruction, the computer executable instructions are for executing computer as the described in any item intelligence of claim 1-7 are set
Standby speech sensitivity adjusting method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439164.7A CN110211605A (en) | 2019-05-24 | 2019-05-24 | Smart machine speech sensitivity adjusting method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439164.7A CN110211605A (en) | 2019-05-24 | 2019-05-24 | Smart machine speech sensitivity adjusting method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110211605A true CN110211605A (en) | 2019-09-06 |
Family
ID=67788578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910439164.7A Pending CN110211605A (en) | 2019-05-24 | 2019-05-24 | Smart machine speech sensitivity adjusting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110211605A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989963A (en) * | 2019-11-22 | 2020-04-10 | 北京梧桐车联科技有限责任公司 | Awakening word recommendation method and device and storage medium |
| CN113330513A (en) * | 2021-04-20 | 2021-08-31 | 华为技术有限公司 | Voice information processing method and device |
| CN114153311A (en) * | 2021-11-19 | 2022-03-08 | 北京小米移动软件有限公司 | Device control method, device and storage medium |
| CN114326423A (en) * | 2021-12-21 | 2022-04-12 | 美的集团股份有限公司 | Automatic generation method of scene control scheme and scene control equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7668710B2 (en) * | 2001-12-14 | 2010-02-23 | Ben Franklin Patent Holding Llc | Determining voice recognition accuracy in a voice recognition system |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | Method and device for awakening voice service |
| CN106338924A (en) * | 2016-09-23 | 2017-01-18 | 广州视源电子科技股份有限公司 | Method and device for automatically adjusting equipment operation parameter threshold |
| CN107393033A (en) * | 2016-05-17 | 2017-11-24 | 上海搜林信息技术有限公司 | Board units wake up sensitivity adjustment method and its system |
| CN107610695A (en) * | 2017-08-08 | 2018-01-19 | 问众智能信息科技（北京）有限公司 | Driver's voice wakes up the dynamic adjusting method of instruction word weight |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN109003607A (en) * | 2018-07-12 | 2018-12-14 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
-
2019
- 2019-05-24 CN CN201910439164.7A patent/CN110211605A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7668710B2 (en) * | 2001-12-14 | 2010-02-23 | Ben Franklin Patent Holding Llc | Determining voice recognition accuracy in a voice recognition system |
| CN107393033A (en) * | 2016-05-17 | 2017-11-24 | 上海搜林信息技术有限公司 | Board units wake up sensitivity adjustment method and its system |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | Method and device for awakening voice service |
| CN106338924A (en) * | 2016-09-23 | 2017-01-18 | 广州视源电子科技股份有限公司 | Method and device for automatically adjusting equipment operation parameter threshold |
| CN107610695A (en) * | 2017-08-08 | 2018-01-19 | 问众智能信息科技（北京）有限公司 | Driver's voice wakes up the dynamic adjusting method of instruction word weight |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN109003607A (en) * | 2018-07-12 | 2018-12-14 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989963A (en) * | 2019-11-22 | 2020-04-10 | 北京梧桐车联科技有限责任公司 | Awakening word recommendation method and device and storage medium |
| CN113330513A (en) * | 2021-04-20 | 2021-08-31 | 华为技术有限公司 | Voice information processing method and device |
| CN114153311A (en) * | 2021-11-19 | 2022-03-08 | 北京小米移动软件有限公司 | Device control method, device and storage medium |
| CN114326423A (en) * | 2021-12-21 | 2022-04-12 | 美的集团股份有限公司 | Automatic generation method of scene control scheme and scene control equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110211605A (en) | Smart machine speech sensitivity adjusting method, device, equipment and storage medium | |
| CN101399672B (en) | Intrusion detection method for fusion of multiple neutral networks | |
| CN103530912A (en) | Attendance recording system having emotion identification function, and method thereof | |
| CN109256134A (en) | A kind of voice awakening method, storage medium and terminal | |
| CN106714023A (en) | Bone conduction earphone-based voice awakening method and system and bone conduction earphone | |
| WO2019062460A1 (en) | Application control method and apparatus, storage medium and electronic device | |
| CN103295584B (en) | Speech data detection device, speech supervisory system and method thereof | |
| CN202130312U (en) | Driver fatigue driving monitoring device | |
| CN110265036A (en) | Voice awakening method, system, electronic equipment and computer readable storage medium | |
| US20140310407A1 (en) | Terminal device | |
| CN105516652B (en) | A kind of intelligent campus street lamp illumination system | |
| CN114707562B (en) | Electromyographic signal sampling frequency control method and device and storage medium | |
| CN110347663A (en) | Dynamic environment monitoring method and system based on Complex event processing engine | |
| CN112198385A (en) | Non-invasive load monitoring method | |
| CN108492825A (en) | A kind of startup method, headset equipment and the speech recognition system of speech recognition | |
| CN108154457A (en) | The method and system of population analysis | |
| CN110516568A (en) | A kind of more contextual data management methods of colleges and universities based on recognition of face and system | |
| CN105786189A (en) | Finger independent action recognition method and system based on MMG signal | |
| CN109815088A (en) | A kind of monitoring householder method and device | |
| Xiao | Machine learning in smart home energy monitoring system | |
| CN107463490A (en) | A kind of cluster daily record centralized collection method being applied in platform development | |
| Hammer et al. | Exploiting usage statistics for energy-efficient logical status inference on mobile phones | |
| CN112651273A (en) | AI intelligent camera tracking method | |
| CN109946538B (en) | Mobile equipment monitoring method and system based on magnetic induction signals | |
| CN101499300A (en) | Audio attention rate analysis device based on spacing audio parameter |
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: 20190906 |