CN108847219A - A kind of wake-up word presets confidence threshold value adjusting method and system - Google Patents
A kind of wake-up word presets confidence threshold value adjusting method and system Download PDFInfo
- Publication number
- CN108847219A CN108847219A CN201810516713.1A CN201810516713A CN108847219A CN 108847219 A CN108847219 A CN 108847219A CN 201810516713 A CN201810516713 A CN 201810516713A CN 108847219 A CN108847219 A CN 108847219A
- Authority
- CN
- China
- Prior art keywords
- user
- threshold value
- wake
- confidence threshold
- word
- 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 25
- 230000003542 behavioural effect Effects 0.000 claims abstract description 23
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 description 11
- 230000002618 waking effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction 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
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/28—Constructional details of speech recognition systems
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting
- G10L2015/0636—Threshold criteria for the updating
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)
- Artificial Intelligence (AREA)
- Electric Clocks (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a kind of wake-up words to preset confidence threshold value adjusting method, including step：S11. user's routine use behavioral data is obtained；S12. it is adjusted according to user's routine use behavioral data and wakes up the default confidence threshold value of word.The present invention, which is set dynamically and adjusts by obtaining user's routine use behavioral data, wakes up the default confidence threshold value of word, fully consider the personal use feature of user, the daily behavior confidence level average value of user is first passed through to determine whether whole lower default confidence threshold value, default confidence threshold value is further adjusted further according to the access times of each period, effectively increase equipment wake-up rate and reduces false wake-up rate.
Description
Technical field
Confidence threshold value adjusting method is preset the present invention relates to speech processes field more particularly to a kind of wake-up word and is
System.
Background technique
Speech recognition technology achieves significant progress in recent years, which has entered industry, household electrical appliances, smart home etc.
Every field.Voice wake-up is a kind of form of speech recognition technology, is not directly contacted with hardware device, passes through voice
Equipment is waken up and is run.Voice wake-up is exactly to allow equipment (intelligent sound box, mobile phone, toy, household electrical appliances etc.) in suspend mode or screen lock state
Under can also detect the sound (phonetic order of setting, i.e. wake-up word) of user, the equipment under allowing in a dormant state directly into
Enter to command status is waited, opens the interactive voice first step.Under normal circumstances, most equipment is set by physical button realization
Standby wake-up or operation.However, this is for user experience and bad.Voice as the most natural exchange way of people,
By voice wake up this contactless mode starting device be undoubtedly it is more friendly,
In the prior art, success rate is waken up in order to improve voice, is all by being trained to speech model, setting is suitable
Confidence threshold value, confidence level be user language in-put and preset language model matching degree of conformity, confidence level is higher, represent
The language in-put of user is more matched with preset language model, otherwise is more mismatched.Software is judging whether user language behavior calls out
When equipment of waking up, the confidence value and default confidence level inputted by user compares, and then wakes up success greater than default confidence level,
Otherwise failure is waken up.But these schemes are fixed by the confidence threshold value of speech model training, may be only available for common use
Family scene, different user use threshold value be all it is identical, the personal use feature of different user is not accounted for, although and energy
It improves and wakes up success rate, but false wake-up rate cannot be reduced.
The patent of Publication No. CN105702253A discloses a kind of voice awakening method and device, utilizes language for improving
The accuracy of sound wake-up terminal device.The method includes：When what terminal device received user's input wakes up word comprising default
The first voice data when, first voice data and preset language model are matched, the first voice number is obtained
According to confidence level；Judge whether the confidence level is less than default confidence threshold value；When the confidence level is less than the default confidence
When spending threshold value, predetermined registration operation is executed；When the confidence level is greater than or equal to the default confidence threshold value, the terminal is waken up
The voice control function of equipment.When the technical solution makes user wake up terminal device failure using voice, terminal device can
The confidence level of the first voice data is improved by executing predetermined registration operation, wakes up terminal device using voice to improve user
The Experience Degree of accuracy and user.Although being the failure to reduce false wake-up rate, and should the method increase success rate is waken up
Confidence threshold value in method is also fixation, does not comprehensively consider the personal use feature of different user.
Summary of the invention
It is a kind of based on user behavior dynamic regulation wake-up word the purpose of the present invention is in view of the drawbacks of the prior art, providing
The method and system of confidence threshold value solve prior art confidence threshold value and fix, do not consider the personal use of different user
The problem of feature and for fail lower false wake-up rate the problem of.
In order to achieve the goal above, the present invention uses following technical scheme：
A kind of default confidence threshold value adjusting method of wake-up word, including step：
S1. user's routine use behavioral data is obtained；
S2. it is adjusted according to user's routine use behavioral data and wakes up the default confidence threshold value of word.
Further, user's daily behavior data include that the daily behavior confidence level average value of user and user are each daily
The wake-up times of a period.
It further, further include step before the step S2：
The daily high frequency usage time interval of user and low frequency are determined according to the wake-up times of the user each period daily
Usage time interval.
Further, which is characterized in that the step S2 is specially：
S201. judge whether the daily behavior confidence level average value of the user is much higher than the default confidence threshold value, if
It is no, then jump to step S202；
S202. whole to lower the default confidence threshold value.
It further, further include step after the step S202：
Judge that the period where current time is in the high frequency usage time interval or the low frequency usage time interval；
The default confidence threshold value is lowered if in the high frequency usage time interval, if use in the low frequency
Between section then raise the default confidence threshold value.
Correspondingly, a kind of wake-up word presets confidence threshold value regulating system, including：
Data acquisition module, for obtaining user's routine use behavioral data；
Adjustment module wakes up the default confidence threshold value of word for adjusting according to user's routine use behavioral data.
Further, user's daily behavior data include that the daily behavior confidence level average value of user and user are each daily
The wake-up times of a period.
Further, further include：
Low-and high-frequency usage time interval determining module, for according to the user daily each period wake-up times determine
The daily high frequency usage time interval of user and low frequency usage time interval.
Further, the adjustment module includes：
First judgment module, for judging whether the daily behavior confidence level average value of the user is much higher than described pre-set
Confidence threshold；
The first adjustment module, for not being much higher than the default confidence in the daily behavior confidence level average value of the user
The default confidence threshold value is integrally lowered when spending threshold value.
Further, the adjustment module further includes：
Second judgment module, for judging that the period where current time is in the high frequency usage time interval or institute
State low frequency usage time interval；
Second adjustment module, when being in the high frequency usage time interval for the period locating for current time described in downward
Default confidence threshold value, the period locating for current time raise the default confidence level when being in the low frequency usage time interval
Threshold value.
Compared with prior art, the present invention is set dynamically and adjusts wake-up by obtaining user's routine use behavioral data
Word presets confidence threshold value, fully considers the personal use feature of user, first passes through the daily behavior confidence level average value of user
Judge whether that whole lower presets confidence threshold value, it is default further to adjust further according to the access times of each period user
Confidence threshold value effectively increases equipment wake-up rate and reduces false wake-up rate.
Detailed description of the invention
Fig. 1 is that a kind of wake-up word that embodiment one provides presets confidence threshold value adjusting method flow chart；
Fig. 2 is that a kind of wake-up word that embodiment two provides presets confidence threshold value regulating system structure chart.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
The present invention is using speech production in daily life as research object, and main impetus is to improve speech production
Wake-up rate and reduction false wake-up rate, usage experience of the optimization user to speech production.The present invention is lacked aiming at the prior art
It falls into, provides a kind of method and system for waking up word confidence threshold value based on user behavior dynamic regulation, solve the prior art
Confidence threshold value is fixed, and does not consider the problems of the personal use feature of different user and to fail to lower asking for false wake-up rate
Topic promotes user experience.
Embodiment one
The present embodiment provides a kind of wake-up words to preset confidence threshold value adjusting method, as shown in Figure 1, including step：
S11. user's routine use behavioral data is obtained；
S12. it is adjusted according to user's routine use behavioral data and wakes up the default confidence threshold value of word.
Wake-up word in the present embodiment is preset confidence threshold value adjusting method and is applied in terminal device, which can
To be that mobile phone, computer, intelligent sound box, toy, household electrical appliances, digital broadcast terminal, messaging devices, tablet device, medical treatment are set
Any equipment with voice control function such as standby, body-building equipment, personal digital assistant.
The word that wakes up of the present embodiment presets the executing subject of confidence threshold value adjusting method as above-mentioned terminal device.
It should be noted that the wake-up word is word relevant to the voice control function of terminal device, it is pre- by user
First set.For example, if presetting and waking up word may include sky when the voice control function of terminal device includes control smart home
The word related with smart home such as tune, TV, curtain；For another example if the voice control function of terminal device includes being connected to
Cloud server and by cloud server search for the network information when, preset wake up word may include search, inquiry, weather, train
The word relevant to network service such as ticket.
Specifically, before user is using the terminal device, when user being needed to upload gender, age, terminal device use
Between section, terminal function preference etc. obtain the setting of user base usage behavior information and wake up word presetting confidence threshold value size.
Then user's routine use behavioral data can be obtained, wake-up word is adjusted according to user's routine use behavioral data and is pre-seted
Reliability.
Optionally, user's daily behavior data include that the daily behavior confidence level average value of user and user are each daily
The wake-up times of period.
It optionally, further include step before the step S12：
The daily high frequency usage time interval of user and low frequency are determined according to the wake-up times of the user each period daily
Usage time interval.
Specifically, terminal device can calculate the confidence level average value of the daily behavior of user at daily 24 points, it is specific to calculate
Process is：Word confidence value is waken up in counting user a whole day every time, then by wake-up word confidence values all at the end of the day
Be added and has then just obtained the daily behavior confidence level average value of user divided by wake-up times.
On the other hand, the wake-up times of terminal device want counting user each period daily are to determine the daily high frequency of user
Usage time interval and low frequency usage time interval.
Optionally, each period can be to be every two hours a period.Such as 0 point to 2 points be one when
Between section, 2 points to 4 points be a period, and so on, then just there is within one day 12 periods.
It optionally, is low frequency usage time interval if the frequency of use of user in a period of time is lower than twice, if with
It is then high frequency usage time interval that the frequency of use of family in a period of time, which is higher than ten times,.Such as：As shown in the table, following table is to use
Family each period and corresponding wake-up times daily.
By upper table it is known that being less than in the number that [0,2], [2,4], [4,6], [6,8] this 4 period users wake up
Twice, then this 4 periods are just low frequency usage time interval, and in [16,18], [18,20], [20,22] this 3 periods
The wake-up times of user are greater than ten times, then this 3 periods are just high frequency usage time interval.
Optionally, the step S12 is specially：
S1201. judge whether the daily behavior confidence level average value of the user is much higher than the default confidence threshold value, if
It is no, then jump to step S1202；
S1202. whole to lower the default confidence threshold value.
Specifically, after the confidence level average value that terminal device calculates the daily behavior of user at daily 24 points, then by user
Daily behavior confidence level average value is compared with default confidence threshold value, if the daily behavior confidence level average value of user is far high
In default confidence threshold value, then to default confidence threshold value without adjustment, because the daily behavior execution degree draw value of user is remote
Higher than default confidence threshold value, so the confidence value of the voice data of user's input easily reaches default confidence threshold value,
Therefore it does not need to adjust the size of default confidence threshold value at this time.If the daily behavior confidence level average value of user is not much higher than
(close) default confidence threshold value, then it is whole to lower default confidence threshold value, default confidence threshold value is lowered by whole, so that
The confidence value of the voice data of user's input more easily reachs default confidence threshold value, thus is easier to identify the voice of user
Data, to improve user to the wake-up rate of terminal device.
It optionally, further include step after the step S1202：
Judge that the period where current time is in the high frequency usage time interval or the low frequency usage time interval；
The default confidence threshold value is lowered if in the high frequency usage time interval, if use in the low frequency
Between section then raise the default confidence threshold value.
Specifically, terminal device can also adjust default confidence threshold value according to daily each period, if when current
Between locating period be high frequency usage time interval (i.e. wake-up times are more than ten periods), then lower and preset confidence level threshold
Value, so that the confidence value of the voice data of user's input more easily reachs default confidence threshold value, in this way when high frequency uses
Between section user can be improved to the wake-up rate of terminal device, if the period locating for current time is low frequency usage time interval
(i.e. wake-up times are lower than period twice) then raises default confidence level because low frequency usage time interval uses fewer
Threshold value, so that the confidence value of the voice data of user's input is not readily reachable by default confidence threshold value relative to other times,
To which user can be lowered to the false wake-up rate of terminal device in low frequency usage time interval.
The present embodiment, which is set dynamically and adjusts by obtaining user's routine use behavioral data, wakes up the default confidence level of word
Threshold value fully considers the personal use feature of user, first passes through the daily behavior confidence level average value of user to determine whether entirety
Default confidence threshold value is lowered, further adjusts default confidence threshold value further according to the access times of each period, effectively
It improves wake-up rate and reduces false wake-up rate.
Embodiment two
The present embodiment provides a kind of wake-up words to preset confidence threshold value regulating system, as shown in Fig. 2, including：
Data acquisition module 11, for obtaining user's routine use behavioral data；
Adjustment module 12 wakes up the default confidence threshold value of word for adjusting according to user's routine use behavioral data.
Wake-up word in the present embodiment is preset confidence threshold value adjusting method and is applied in terminal device, which can
To be that mobile phone, computer, intelligent sound box, toy, household electrical appliances, digital broadcast terminal, messaging devices, tablet device, medical treatment are set
Any equipment with voice control function such as standby, body-building equipment, personal digital assistant.
It should be noted that the wake-up word is word relevant to the voice control function of terminal device, it is pre- by user
First set.For example, if presetting and waking up word may include sky when the voice control function of terminal device includes control smart home
The word related with smart home such as tune, TV, curtain；For another example if the voice control function of terminal device includes being connected to
Cloud server and by cloud server search for the network information when, preset wake up word may include search, inquiry, weather, train
The word relevant to network service such as ticket.
Specifically, before user is using the terminal device, when user being needed to upload gender, age, terminal device use
Between section, terminal function preference etc. obtain the setting of user base usage behavior information and wake up word presetting confidence threshold value size.
Then user's routine use behavioral data can be obtained, wake-up word is adjusted according to user's routine use behavioral data and is pre-seted
Reliability.
Optionally, user's daily behavior data include that the daily behavior confidence level average value of user and user are each daily
The wake-up times of period.
Optionally, further include：
Low-and high-frequency usage time interval determining module, for according to the user daily each period wake-up times determine
The daily high frequency usage time interval of user and low frequency usage time interval.
Specifically, terminal device can calculate the confidence level average value of the daily behavior of user at daily 24 points, it is specific to calculate
Process is：Word confidence value is waken up in counting user a whole day every time, then by wake-up word confidence values all at the end of the day
Be added and has then just obtained the daily behavior confidence level average value of user divided by wake-up times.
On the other hand, the wake-up times of terminal device want counting user each period daily are to determine the daily high frequency of user
Usage time interval and low frequency usage time interval.
Optionally, each period can be to be every two hours a period.Such as 0 point to 2 points be one when
Between section, 2 points to 4 points be a period, and so on, then just there is within one day 12 periods.
It optionally, is low frequency usage time interval if the frequency of use of user in a period of time is lower than twice, if with
It is then high frequency usage time interval that the frequency of use of family in a period of time, which is higher than ten times,.Such as：As shown in the table, following table is to use
Family each period and corresponding wake-up times daily.
By upper table it is known that being less than in the number that [0,2], [2,4], [4,6], [6,8] this 4 period users wake up
Twice, then this 4 periods are just low frequency usage time interval, and in [16,18], [18,20], [20,22] this 3 periods
The wake-up times of user are greater than ten times, then this 3 periods are just high frequency usage time interval.
Optionally, the adjustment module includes：
First judgment module, for judging whether the daily behavior confidence level average value of the user is much higher than described pre-set
Confidence threshold；
The first adjustment module, for not being much higher than the default confidence in the daily behavior confidence level average value of the user
The default confidence threshold value is integrally lowered when spending threshold value.
Specifically, after the confidence level average value that terminal device calculates the daily behavior of user at daily 24 points, then by user
Daily behavior confidence level average value is compared with default confidence threshold value, if the daily behavior confidence level average value of user is far high
In default confidence threshold value, then to default confidence threshold value without adjustment, because the daily behavior execution degree draw value of user is remote
Higher than default confidence threshold value, so the confidence value of the voice data of user's input easily reaches default confidence threshold value,
Therefore it does not need to adjust the size of default confidence threshold value at this time.If the daily behavior confidence level average value of user is not much higher than
(close) default confidence threshold value, then it is whole to lower default confidence threshold value, default confidence threshold value is lowered by whole, so that
The confidence value of the voice data of user's input more easily reachs default confidence threshold value, thus is easier to identify the voice of user
Data, to improve user to the wake-up rate of terminal device.
Optionally, the adjustment module further includes：
Second judgment module, for judging that the period where current time is in the high frequency usage time interval or institute
State low frequency usage time interval；
Second adjustment module, when being in the high frequency usage time interval for the period locating for current time described in downward
Default confidence threshold value, the period locating for current time raise the default confidence level when being in the low frequency usage time interval
Threshold value.
Specifically, terminal device can also adjust default confidence threshold value according to daily each period, if when current
Between locating period be high frequency usage time interval (i.e. wake-up times are more than ten periods), then lower and preset confidence level threshold
Value, so that the confidence value of the voice data of user's input more easily reachs default confidence threshold value, in this way when high frequency uses
Between section user can be improved to the wake-up rate of terminal device, if the period locating for current time is low frequency usage time interval
(i.e. wake-up times are lower than period twice) then raises default confidence level because low frequency usage time interval uses fewer
Threshold value, so that the confidence value of the voice data of user's input is not readily reachable by default confidence threshold value relative to other times,
To which user can be lowered to the false wake-up rate of terminal device in low frequency usage time interval.
The present embodiment obtains user's routine use behavioral data by data acquisition module to be set dynamically and adjust wake-up
Word presets confidence threshold value, fully considers the personal use feature of user, effectively increases wake-up rate and reduces false wake-up rate, mentions
Rise user experience.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of wake-up word presets confidence threshold value adjusting method, which is characterized in that including step：
S1. user's routine use behavioral data is obtained；
S2. it is adjusted according to user's routine use behavioral data and wakes up the default confidence threshold value of word.
2. a kind of wake-up word confidence threshold value adjusting method according to claim 1, which is characterized in that the user is daily
The wake-up times of behavioral data includes the daily behavior confidence level average value of user and user each period daily.
3. a kind of wake-up word confidence threshold value adjusting method according to claim 2, which is characterized in that the step S2 it
Before further include step：
Determine that the daily high frequency usage time interval of user and low frequency use according to the wake-up times of the user each period daily
Period.
4. a kind of wake-up word according to claim 3 presets confidence threshold value adjusting method, which is characterized in that the step
S2 is specially：
S201. judge whether the daily behavior confidence level average value of the user is much higher than the default confidence threshold value, if it is not, then
Jump to step S202；
S202. whole to lower the default confidence threshold value.
5. a kind of wake-up word according to claim 4 presets confidence threshold value adjusting method, which is characterized in that the step
It further include step after S202：
Judge that the period where current time is in the high frequency usage time interval or the low frequency usage time interval；
The default confidence threshold value is lowered if in the high frequency usage time interval, if being in the low frequency usage time interval
Then raise the default confidence threshold value.
6. a kind of wake-up word presets confidence threshold value regulating system, which is characterized in that including：
Data acquisition module, for obtaining user's routine use behavioral data；
Adjustment module wakes up the default confidence threshold value of word for adjusting according to user's routine use behavioral data.
7. a kind of wake-up word according to claim 6 presets confidence threshold value regulating system, which is characterized in that the user
The wake-up times of daily behavior data include the daily behavior confidence level average value of user and user each period daily.
8. a kind of wake-up word according to claim 7 presets confidence threshold value regulating system, which is characterized in that further include：
Low-and high-frequency usage time interval determining module, for determining user according to the wake-up times of the user each period daily
Daily high frequency usage time interval and low frequency usage time interval.
9. a kind of wake-up word according to claim 7 presets confidence threshold value regulating system, which is characterized in that the adjusting
Module includes：
First judgment module, for judging whether the daily behavior confidence level average value of the user is much higher than the default confidence level
Threshold value；
The first adjustment module, for not being much higher than the default confidence level threshold in the daily behavior confidence level average value of the user
The default confidence threshold value is integrally lowered when value.
10. a kind of wake-up word according to claim 9 presets confidence threshold value regulating system, which is characterized in that the tune
Saving module further includes：
Second judgment module, for judging that the period where current time is in the high frequency usage time interval or described low
Frequency usage time interval；
Second adjustment module is lowered described default when being in the high frequency usage time interval for the period locating for current time
Confidence threshold value, the period locating for current time raise the default confidence level threshold when being in the low frequency usage time interval
Value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516713.1A CN108847219B (en) | 2018-05-25 | 2018-05-25 | Awakening word preset confidence threshold adjusting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810516713.1A CN108847219B (en) | 2018-05-25 | 2018-05-25 | Awakening word preset confidence threshold adjusting method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108847219A true CN108847219A (en) | 2018-11-20 |
| CN108847219B CN108847219B (en) | 2020-12-25 |
Family
ID=64213481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810516713.1A Active CN108847219B (en) | 2018-05-25 | 2018-05-25 | Awakening word preset confidence threshold adjusting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108847219B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109256134A (en) * | 2018-11-22 | 2019-01-22 | 深圳市同行者科技有限公司 | A kind of voice awakening method, storage medium and terminal |
| CN109801629A (en) * | 2019-03-01 | 2019-05-24 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
| CN109859774A (en) * | 2019-01-02 | 2019-06-07 | 珠海格力电器股份有限公司 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
| CN109887507A (en) * | 2019-04-22 | 2019-06-14 | 成都启英泰伦科技有限公司 | A method of reducing comparable speech order word false recognition rate |
| CN109920418A (en) * | 2019-02-20 | 2019-06-21 | 北京小米移动软件有限公司 | Adjust the method and device of wakeup sensitivity |
| CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
| CN110136707A (en) * | 2019-04-22 | 2019-08-16 | 北京云知声信息技术有限公司 | It is a kind of for carrying out the man-machine interactive system of more equipment autonomously decisions |
| CN110148405A (en) * | 2019-04-10 | 2019-08-20 | 北京梧桐车联科技有限责任公司 | Phonetic order processing method and processing device, electronic equipment and storage medium |
| CN110211605A (en) * | 2019-05-24 | 2019-09-06 | 珠海多士科技有限公司 | Smart machine speech sensitivity adjusting method, device, equipment and storage medium |
| CN110265018A (en) * | 2019-07-01 | 2019-09-20 | 成都启英泰伦科技有限公司 | A kind of iterated command word recognition method continuously issued |
| CN110570861A (en) * | 2019-09-24 | 2019-12-13 | Oppo广东移动通信有限公司 | method and device for voice wake-up, terminal equipment and readable storage medium |
| CN110782891A (en) * | 2019-10-10 | 2020-02-11 | 珠海格力电器股份有限公司 | Audio processing method and device, computing equipment and storage medium |
| CN111128155A (en) * | 2019-12-05 | 2020-05-08 | 珠海格力电器股份有限公司 | Awakening method, device, equipment and medium for intelligent equipment |
| CN111261143A (en) * | 2018-12-03 | 2020-06-09 | 杭州嘉楠耘智信息科技有限公司 | Voice wake-up method and device and computer readable storage medium |
| CN111292737A (en) * | 2018-12-07 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Voice interaction and voice awakening detection method, device, equipment and storage medium |
| CN111427293A (en) * | 2020-03-26 | 2020-07-17 | 广州立功科技股份有限公司 | Multichannel input sampling awakening method and device and control equipment |
| CN111816178A (en) * | 2020-07-07 | 2020-10-23 | 云知声智能科技股份有限公司 | Voice equipment control method, device and equipment |
| US10827028B1 (en) | 2019-09-05 | 2020-11-03 | Spotify Ab | Systems and methods for playing media content on a target device |
| CN112086096A (en) * | 2019-06-14 | 2020-12-15 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium |
| CN112102821A (en) * | 2019-06-18 | 2020-12-18 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium applied to electronic equipment |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN112767935A (en) * | 2020-12-28 | 2021-05-07 | 北京百度网讯科技有限公司 | Awakening index monitoring method and device and electronic equipment |
| US11094319B2 (en) | 2019-08-30 | 2021-08-17 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| CN113488050A (en) * | 2021-07-09 | 2021-10-08 | 北京有竹居网络技术有限公司 | Voice awakening method and device, storage medium and electronic equipment |
| CN113834192A (en) * | 2021-09-18 | 2021-12-24 | 珠海格力电器股份有限公司 | State adjustment method for voice recognition device in air conditioner and air conditioner |
| CN114187904A (en) * | 2020-08-25 | 2022-03-15 | 广州华凌制冷设备有限公司 | Similarity threshold acquisition method, voice household appliance and computer readable storage medium |
| US11308959B2 (en) | 2020-02-11 | 2022-04-19 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| US11328722B2 (en) | 2020-02-11 | 2022-05-10 | Spotify Ab | Systems and methods for generating a singular voice audio stream |
| US11462217B2 (en) | 2019-06-11 | 2022-10-04 | Samsung Electronics Co., Ltd. | Electronic apparatus and control method thereof |
| US11822601B2 (en) | 2019-03-15 | 2023-11-21 | Spotify Ab | Ensemble-based data comparison |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011248107A (en) * | 2010-05-27 | 2011-12-08 | Nippon Telegr & Teleph Corp <Ntt> | Voice recognition result search method, apparatus and program for the same |
| CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
| CN103578468A (en) * | 2012-08-01 | 2014-02-12 | 联想(北京)有限公司 | Method for adjusting confidence coefficient threshold of voice recognition and electronic device |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
-
2018
- 2018-05-25 CN CN201810516713.1A patent/CN108847219B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011248107A (en) * | 2010-05-27 | 2011-12-08 | Nippon Telegr & Teleph Corp <Ntt> | Voice recognition result search method, apparatus and program for the same |
| CN103578468A (en) * | 2012-08-01 | 2014-02-12 | 联想(北京)有限公司 | Method for adjusting confidence coefficient threshold of voice recognition and electronic device |
| CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109256134B (en) * | 2018-11-22 | 2021-11-02 | 深圳市同行者科技有限公司 | Voice awakening method, storage medium and terminal |
| CN109256134A (en) * | 2018-11-22 | 2019-01-22 | 深圳市同行者科技有限公司 | A kind of voice awakening method, storage medium and terminal |
| CN111261143B (en) * | 2018-12-03 | 2024-03-22 | 嘉楠明芯(北京)科技有限公司 | Voice wakeup method and device and computer readable storage medium |
| CN111261143A (en) * | 2018-12-03 | 2020-06-09 | 杭州嘉楠耘智信息科技有限公司 | Voice wake-up method and device and computer readable storage medium |
| CN111292737A (en) * | 2018-12-07 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Voice interaction and voice awakening detection method, device, equipment and storage medium |
| CN109859774A (en) * | 2019-01-02 | 2019-06-07 | 珠海格力电器股份有限公司 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
| CN109859774B (en) * | 2019-01-02 | 2021-04-02 | 珠海格力电器股份有限公司 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
| CN109920418B (en) * | 2019-02-20 | 2021-06-22 | 北京小米移动软件有限公司 | Method and device for adjusting awakening sensitivity |
| CN109920418A (en) * | 2019-02-20 | 2019-06-21 | 北京小米移动软件有限公司 | Adjust the method and device of wakeup sensitivity |
| CN109801629A (en) * | 2019-03-01 | 2019-05-24 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
| US11822601B2 (en) | 2019-03-15 | 2023-11-21 | Spotify Ab | Ensemble-based data comparison |
| CN110148405A (en) * | 2019-04-10 | 2019-08-20 | 北京梧桐车联科技有限责任公司 | Phonetic order processing method and processing device, electronic equipment and storage medium |
| CN110148405B (en) * | 2019-04-10 | 2021-07-13 | 北京梧桐车联科技有限责任公司 | Voice instruction processing method and device, electronic equipment and storage medium |
| CN110136707A (en) * | 2019-04-22 | 2019-08-16 | 北京云知声信息技术有限公司 | It is a kind of for carrying out the man-machine interactive system of more equipment autonomously decisions |
| CN109887507B (en) * | 2019-04-22 | 2021-03-12 | 成都启英泰伦科技有限公司 | Method for reducing similar voice command word misrecognition rate |
| CN109887507A (en) * | 2019-04-22 | 2019-06-14 | 成都启英泰伦科技有限公司 | A method of reducing comparable speech order word false recognition rate |
| CN110211605A (en) * | 2019-05-24 | 2019-09-06 | 珠海多士科技有限公司 | Smart machine speech sensitivity adjusting method, device, equipment and storage medium |
| CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
| US11462217B2 (en) | 2019-06-11 | 2022-10-04 | Samsung Electronics Co., Ltd. | Electronic apparatus and control method thereof |
| CN112086096B (en) * | 2019-06-14 | 2024-04-05 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium |
| CN112086096A (en) * | 2019-06-14 | 2020-12-15 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium |
| CN112102821B (en) * | 2019-06-18 | 2024-01-12 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium applied to electronic equipment |
| CN112102821A (en) * | 2019-06-18 | 2020-12-18 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and medium applied to electronic equipment |
| WO2020253265A1 (en) * | 2019-06-18 | 2020-12-24 | 北京京东尚科信息技术有限公司 | Data processing method, apparatus, and system applied to electronic device, and medium |
| CN110265018B (en) * | 2019-07-01 | 2022-03-04 | 成都启英泰伦科技有限公司 | Method for recognizing continuously-sent repeated command words |
| CN110265018A (en) * | 2019-07-01 | 2019-09-20 | 成都启英泰伦科技有限公司 | A kind of iterated command word recognition method continuously issued |
| US11551678B2 (en) | 2019-08-30 | 2023-01-10 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| US11094319B2 (en) | 2019-08-30 | 2021-08-17 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| US10827028B1 (en) | 2019-09-05 | 2020-11-03 | Spotify Ab | Systems and methods for playing media content on a target device |
| CN110570861A (en) * | 2019-09-24 | 2019-12-13 | Oppo广东移动通信有限公司 | method and device for voice wake-up, terminal equipment and readable storage medium |
| CN110570861B (en) * | 2019-09-24 | 2022-02-25 | Oppo广东移动通信有限公司 | Method and device for voice wake-up, terminal equipment and readable storage medium |
| CN110782891A (en) * | 2019-10-10 | 2020-02-11 | 珠海格力电器股份有限公司 | Audio processing method and device, computing equipment and storage medium |
| CN110782891B (en) * | 2019-10-10 | 2022-02-18 | 珠海格力电器股份有限公司 | Audio processing method and device, computing equipment and storage medium |
| CN111128155A (en) * | 2019-12-05 | 2020-05-08 | 珠海格力电器股份有限公司 | Awakening method, device, equipment and medium for intelligent equipment |
| US11810564B2 (en) | 2020-02-11 | 2023-11-07 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| US11308959B2 (en) | 2020-02-11 | 2022-04-19 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| US11328722B2 (en) | 2020-02-11 | 2022-05-10 | Spotify Ab | Systems and methods for generating a singular voice audio stream |
| CN111427293A (en) * | 2020-03-26 | 2020-07-17 | 广州立功科技股份有限公司 | Multichannel input sampling awakening method and device and control equipment |
| CN111816178A (en) * | 2020-07-07 | 2020-10-23 | 云知声智能科技股份有限公司 | Voice equipment control method, device and equipment |
| CN114187904A (en) * | 2020-08-25 | 2022-03-15 | 广州华凌制冷设备有限公司 | Similarity threshold acquisition method, voice household appliance and computer readable storage medium |
| CN112767935B (en) * | 2020-12-28 | 2022-11-25 | 北京百度网讯科技有限公司 | Awakening index monitoring method and device and electronic equipment |
| CN112767935A (en) * | 2020-12-28 | 2021-05-07 | 北京百度网讯科技有限公司 | Awakening index monitoring method and device and electronic equipment |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN113488050A (en) * | 2021-07-09 | 2021-10-08 | 北京有竹居网络技术有限公司 | Voice awakening method and device, storage medium and electronic equipment |
| CN113488050B (en) * | 2021-07-09 | 2024-03-26 | 北京有竹居网络技术有限公司 | Voice wakeup method and device, storage medium and electronic equipment |
| CN113834192A (en) * | 2021-09-18 | 2021-12-24 | 珠海格力电器股份有限公司 | State adjustment method for voice recognition device in air conditioner and air conditioner |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108847219B (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108847219A (en) | A kind of wake-up word presets confidence threshold value adjusting method and system | |
| CN105654949B (en) | A kind of voice awakening method and device | |
| CN107144819B (en) | A kind of sound localization method, device and electronic equipment | |
| CN105118257B (en) | Intelligent control system and method | |
| CN107743289B (en) | Intelligent sound box control method in intelligent household scene | |
| CN107580237A (en) | Operating method, device, system and the storage medium of TV | |
| CN112420041B (en) | Control method and device for wake-up threshold of intelligent device, intelligent device and storage medium | |
| CN111968644B (en) | Intelligent device awakening method and device and electronic device | |
| CN104064185B (en) | Information processing method and system, electronic equipment | |
| CN109754866A (en) | Attention training method, device and computer readable storage medium | |
| CN106126167B (en) | A kind of sound effect treatment method and terminal device | |
| CN111949323B (en) | Optimization method and device for waking up intelligent equipment, intelligent equipment and storage medium | |
| CN107358954A (en) | It is a kind of to change the device and method for waking up word in real time | |
| CN106131337A (en) | A kind of method and device out of service based on User Status control application | |
| CN104168263B (en) | A kind of server and its alarm clock implementing method | |
| CN104665619A (en) | Cooking control system and cooking control method of intelligent oven | |
| CN110620705B (en) | Control terminal and control method of intelligent bathroom and electronic equipment | |
| CN112185369B (en) | Volume adjusting method, device, equipment and medium based on voice control | |
| CN111312222A (en) | Awakening and voice recognition model training method and device | |
| CN106970774A (en) | A kind of volume adjustment device and method, a kind of terminal | |
| CN109712623A (en) | Sound control method, device and computer readable storage medium | |
| CN107508979B (en) | Volume adjusting method, device, terminal and storage medium | |
| CN107526569B (en) | A kind of volume adjusting method, device, storage medium and mobile terminal | |
| WO2022193633A1 (en) | Projection-based wake-up method and apparatus, and projection device and computer storage medium | |
| CN108804069A (en) | Volume adjusting method and device, storage medium and electronic 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190402 Address after: 201616 No. 3666 Sixian Road, Songjiang District, Shanghai Applicant after: PHICOMM (SHANGHAI) Co.,Ltd. Address before: 610000 No. 125 Longquan Street Park Road, Longquanyi District, Chengdu City, Sichuan Province Applicant before: SICHUAN FEIXUN QUANZHI INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201109 Address after: Room 10242, No. 260, Jiangshu Road, Xixing street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou Jiji Intellectual Property Operation Co.,Ltd. Address before: 201616 Shanghai city Songjiang District Sixian Road No. 3666 Applicant before: Phicomm (Shanghai) Co.,Ltd. |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20201208 Address after: Room 703, building 3, Yangguang Chuncheng, Lubei street, Luqiao District, Taizhou City, Zhejiang Province Applicant after: Taizhou zhiao communication equipment Co.,Ltd. Address before: Room 10242, No. 260, Jiangshu Road, Xixing street, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: Hangzhou Jiji Intellectual Property Operation Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230109 Address after: 313000 room 1019, Xintiandi commercial office, Yishan street, Wuxing District, Huzhou, Zhejiang, China Patentee after: Huzhou YingLie Intellectual Property Operation Co.,Ltd. Address before: Room 703, building 3, Yangguang Chuncheng, Lubei street, Luqiao District, Taizhou City, Zhejiang Province Patentee before: Taizhou zhiao communication equipment Co.,Ltd. |
|
| TR01 | Transfer of patent right |