CN106439967B - Method and system for improving voice recognition rate of range hood - Google Patents
Method and system for improving voice recognition rate of range hood Download PDFInfo
- Publication number
- CN106439967B CN106439967B CN201610899191.9A CN201610899191A CN106439967B CN 106439967 B CN106439967 B CN 106439967B CN 201610899191 A CN201610899191 A CN 201610899191A CN 106439967 B CN106439967 B CN 106439967B
- Authority
- CN
- China
- Prior art keywords
- voice command
- kitchen ventilator
- fan
- rotation speed
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004321 preservation Methods 0.000 claims description 13
- 239000000779 smoke Substances 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007717 exclusion 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24C—DOMESTIC STOVES OR RANGES ; DETAILS OF DOMESTIC STOVES OR RANGES, OF GENERAL APPLICATION
- F24C15/00—Details
- F24C15/20—Removing cooking fumes
- F24C15/2021—Arrangement or mounting of control or safety 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
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- 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
-
- 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
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Combustion & Propulsion (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Air Conditioning Control Device (AREA)
- Ventilation (AREA)
Abstract
The invention discloses a method and a system for improving the voice recognition rate of a range hood, wherein the method comprises the following steps: when the number of continuous failures of the first voice command recognition exceeds a set value, reducing the current fan rotating speed of the range hood; receiving a second voice command and recognizing the second voice command; and if the second voice command is successfully recognized within the set time, executing an instruction matched with the second voice command. The method for improving the voice recognition rate of the range hood provided by the embodiment of the invention realizes that when the difficulty in voice recognition is monitored, the voice recognition rate is improved by properly reducing the running noise of the range hood.
Description
Technical field
The present embodiments relate to technical field of voice recognition more particularly to a kind of sides for improving kitchen ventilator phonetic recognization rate
Method and system.
Background technique
With the rapid development of electronic technology and speech recognition technology, speech recognition technology has been widely used for each row
Each industry, more and more voice control kitchen ventilators had come into the family life of people in recent years, realize and difference can be used
Languages and voice command control kitchen ventilator various functions, for example, by voice command control kitchen ventilator switch, blower
The functions such as gear and timing, greatly facilitate people's lives, while also eliminating function button previous on kitchen ventilator,
Particularly convenient the elderly's use.
But due to when kitchen ventilator itself is run noise it is bigger, biggish operation noise certainly will influence to user issue
Voice command identification, cause phonetic recognization rate to decline.In order to improve the above problem, in the prior art usually by improving language
The complexity of sound recognizer trains speech recognition modeling according to the noise of operation, but if speech recognition algorithm and
It is complicated, will definitely increase the work load of CPU (Central Processing Unit, central processing unit), influences equipment
Response speed, and increase the power consumption of equipment；And the method that speech recognition modeling is trained for the noise by operation, lead to
Normal kitchen ventilator is both provided with multiple running speeds, and the noise generated when running in different kitchen environments is also different, therefore instructs
The speech recognition modeling got is not necessarily suitable for the actual use environment of kitchen ventilator.
Summary of the invention
The embodiment of the invention provides a kind of method and system for improving kitchen ventilator phonetic recognization rate, are monitored with realizing to work as
When speech recognition difficulty, phonetic recognization rate is improved by suitably reducing the operation noise of kitchen ventilator itself.
In a first aspect, the embodiment of the invention provides a kind of methods for improving kitchen ventilator phonetic recognization rate, this method comprises:
When being identified that the number continuously to fail is more than setting value to the first voice command, reduce the current wind of kitchen ventilator
Machine revolving speed；
The second voice command is received, and second voice command is identified；
If being identified successfully to second voice command within the set time, execute and second voice command
The instruction matched.
Further, it is described when the first voice command is identified continuously fail number be more than setting value when after,
Before the current rotation speed of fan of reduction kitchen ventilator, further includes:
Save first voice command；
It is matched with first voice command based on whether there is in the current rotation speed of fan inquiry database of kitchen ventilator
Speech samples record, and if it exists, then execute the instruction with the speech samples record matching and otherwise execute the reduction oil smoke
The operation of the current rotation speed of fan of machine.
Further, the method also includes: if within the set time to the second voice command recognition failures,
Restore the rotation speed of fan of the kitchen ventilator, and deletes first voice command of preservation.
Further, if it is described within the set time to second voice command identify successfully, execute with it is described
After the matched instruction of second voice command, further includes:
If the similarity of first voice command and second voice command is greater than similarity threshold, by described the
The current rotation speed of fan of one voice command, kitchen ventilator and second voice command are associated, and are saved in database；
If the similarity of first voice command and second voice command is not more than similarity threshold, guarantor is deleted
First voice command deposited.
Second aspect, the embodiment of the invention also provides a kind of system for improving kitchen ventilator phonetic recognization rate, the system packets
It includes:
Reduce module, for reducing when being identified that the number continuously to fail is more than setting value to the first voice command
The current rotation speed of fan of kitchen ventilator；
Receiving module for receiving the second voice command, and identifies second voice command；
Indicate execution module, if within the set time to second voice command identify successfully, execution and
The matched instruction of second voice command.
Further, the system also includes:
First voice command preserving module, for that ought be identified the number continuously to fail to the first voice command described
After when more than setting value, before reducing the current rotation speed of fan of kitchen ventilator, first voice command is saved；
Enquiry module, for based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first language
The speech samples of sound commands match record；
Accordingly, the instruction execution module, if being also used to exist and first voice command in the database
The speech samples record matched, then execute the instruction with the speech samples record matching；
The reduction module, if being also used to be not present and the matched voice sample of first voice command in the database
This record executes the operation for reducing the current rotation speed of fan of kitchen ventilator.
Further, the system also includes:
Recovery module, if for restoring the oil within the set time to the second voice command recognition failures
The rotation speed of fan of smoke machine, and delete first voice command of preservation.
Further, the system also includes:
Preserving module, if being executed for being identified successfully to second voice command within the set time described
After the matched instruction of the second voice command, if the similarity of first voice command and second voice command
Greater than similarity threshold, then by the current rotation speed of fan of first voice command, kitchen ventilator and second voice command
It is associated, and is saved in database.
Further, the system also includes:
Removing module, if being executed for being identified successfully to second voice command within the set time described
After the matched instruction of the second voice command, if the similarity of first voice command and second voice command
No more than similarity threshold, then first voice command of preservation is deleted.
A kind of method improving kitchen ventilator phonetic recognization rate provided in an embodiment of the present invention, by when to the first voice command
When being identified that the number continuously to fail is more than setting value, reduce the current rotation speed of fan of kitchen ventilator；Later to received
Two voice commands are identified；If being identified successfully to second voice command within the set time, execute and described the
The technological means of the matched instruction of two voice commands, realizes when monitoring speech recognition difficulty, by suitably reducing oil smoke
The operation noise of machine itself improves phonetic recognization rate.
Detailed description of the invention
Fig. 1 is a kind of method flow schematic diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention one provides；
Fig. 2 is a kind of method flow schematic diagram for improving kitchen ventilator phonetic recognization rate provided by Embodiment 2 of the present invention；
Fig. 3 is a kind of method flow schematic diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention three provides；
Fig. 4 is a kind of method flow schematic diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention four provides；
Fig. 5 is a kind of system structure diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing or method described as flow chart.Although every step is described as the processing of sequence by flow chart, therein to be permitted
Multi-step can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of every step can be rearranged.When it
The processing can be terminated when step completion, it is also possible to have the additional step being not included in attached drawing.The processing
It can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 is a kind of method flow diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention one provides, this method
It is applicable to identify the voice command that user issues during kitchen ventilator works and execute the feelings of corresponding operating
Condition can be executed by the system of raising kitchen ventilator phonetic recognization rate.The system can be real by way of hardware and/or software
It is existing.This method specifically comprises the following steps:
Step 110, when to the first voice command identified continuously fail number be more than setting value when, reduce kitchen ventilator
Current rotation speed of fan.
Wherein, the first signified voice command of the present invention and the second voice command refer both to the control kitchen ventilator of user's input
The voice command of function, first voice command and the second voice command may be identical, it is also possible to different, the side of being intended merely to
Just description is just defined by " first ", " second "；It is every by the control kitchen ventilator for sending of speaking specifically to can be user
The speech utterances such as the voice of function, such as " opening light ", " starting big exhaust fan ", " closing " or " timing 10 minutes ".When
User issues voice command, and the speech recognition system on kitchen ventilator can identify institute's speech commands, and respond institute's predicate
Sound order, to realize the purpose for passing through voice control kitchen ventilator various functions.After if user issued a certain voice command, oil smoke
Machine does not execute corresponding operation according to institute's speech commands and thinks that kitchen ventilator is primary to institute's speech commands recognition failures；It is logical
Chang Ruguo kitchen ventilator is not responding to voice command, and user can issue identical voice command again, and certain kitchen ventilator can execute one again
The secondary identification to institute's speech commands operates, when being identified that the number continuously to fail is more than setting to a certain same voice order
When value, that is, think there is speech recognition difficulty at this time, it may be possible to which the running noises of kitchen ventilator itself cause greatly very much.It is possible thereby to
Understand, described " being identified the number continuously to fail to the first voice command ", which does not imply that, in this programme connects single
The voice command received repeatedly identified and continuously fail number, and refer to the same voice command repeatedly received into
The capable number for identifying and continuously failing.The setting value can go to set according to design experiences, for example, can be it is 3 inferior, to increase
Strong user experience, setting value will not generally be arranged it is too big, avoid the occurrence of repeatedly issue voice command but without response the case where.
Illustratively, the acoustic feature value for extracting the voice command of each user's input, when adjacent acoustic feature twice
When the similarity of value is higher than preset value, that is, think that the adjacent voice command twice is identical voice command.If user
The repeatedly identical voice command of input (as twice), and kitchen ventilator does not respond thereto, then it is assumed that there is voice knowledge at this time
It is not difficult, reduce the operation noise of kitchen ventilator itself by reducing the current rotation speed of fan of kitchen ventilator, to improve speech recognition
Rate.In the operational process of kitchen ventilator, the control mode that the revolving speed of blower can't be too complicated to user generally passes through multiple shelves
Position selects rotation speed of fan, correspondingly, is reducing the current rotation speed of fan of kitchen ventilator, be not reduce current blower at random
Revolving speed, but it is reduced to the corresponding rotation speed of fan of adjacent gear positions.
Step 120 receives the second voice command, and identifies to second voice command.
After reducing kitchen ventilator current rotation speed of fan, receive the voice command of user's input again, and to receiving
Voice command carries out speech recognition, to realize the purpose for the voice command for being able to respond user.It should be noted that the present invention is simultaneously
The speech recognition algorithm of use is not defined, speech recognition algorithm existing in the prior art can use the present invention
In.
If step 130 within the set time identifies successfully second voice command, execute and second language
The instruction of sound commands match.
If the language for the user that successfully makes an immediate response is identified to the voice command of user's input in reasonable setting time
Sound order executes and the matched instruction of institute's speech commands；Such as the operation such as " opening light " or " timing ".
A kind of method improving kitchen ventilator phonetic recognization rate provided in this embodiment, by being carried out when to the first voice command
When the number that identification continuously fails is more than setting value, reduce the current rotation speed of fan of kitchen ventilator；Later to the second language received
Sound order is identified；If being identified successfully to second voice command within the set time, execute and second language
The technological means of the instruction of sound commands match is realized when monitoring speech recognition difficulty, by the blower for reducing kitchen ventilator
Revolving speed suitably reduces the operation noise of kitchen ventilator itself to improve phonetic recognization rate.
Embodiment two
Fig. 2 is a kind of method flow schematic diagram for improving kitchen ventilator phonetic recognization rate provided by Embodiment 2 of the present invention,
On the basis of embodiment one, the present embodiment is advanced optimized, the benefit of optimization be by database it is stored with
The matched speech samples of voice command record to respond the control command of user, and then improve phonetic recognization rate.Referring specifically to Fig. 2
Shown, this method specifically includes as follows:
Step 210, when being identified that the number continuously to fail is more than setting value to the first voice command, save described the
One voice command.
Step 220, based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first voice order
Matched speech samples are enabled to record, and if it exists, to then follow the steps 230, otherwise, execute step 240.
For example, it is assumed that when first voice command that user issues in quiet environment is " opening light ", it is corresponding
Voice recognition data be " 111111 ", when the current rotation speed of fan of kitchen ventilator be 100 revs/min when, kitchen ventilator itself can generate
Certain noise, user issues the correspondence voice data that first voice command of " opening light " is identified in such a case
For " 111100 ", if that there are such speech samples records in database --- " 100-111100-111111 " then may be used
To judge first voice command recognized when the current rotation speed of fan of kitchen ventilator is 100 revs/min for " 111100 "
When, corresponding voice command is substantially " opening light ", then the central control machine structure of kitchen ventilator is immediately performed the behaviour for opening light
Make.
Step 230, execute with the instruction of the speech samples record matching, terminate process.
Step 240 reduces the current rotation speed of fan of kitchen ventilator.
The purpose for reducing the current rotation speed of fan of kitchen ventilator is the noise generated in reduction kitchen ventilator itself to a certain degree, is mentioned
Discrimination of the height to voice command.
Step 250 receives the second voice command, and identifies to second voice command.
If step 260 within the set time identifies successfully second voice command, execute and second language
The instruction of sound commands match.
A kind of method improving kitchen ventilator phonetic recognization rate provided in this embodiment, in the base of above-described embodiment technical solution
On plinth, by saving first voice when being identified that the number continuously to fail is more than setting value to the first voice command
Order, and based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and the matched language of the first voice command
Sound sample record, and if it exists, then execute the technological means with the instruction of the speech samples record matching, realize and pass through data
It is stored in library to record with the matched speech samples of voice command to respond the control command of user, and then improve voice knowledge
Not rate.
Embodiment three
Fig. 3 is a kind of method flow schematic diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention three provides,
On the basis of above-described embodiment, the present embodiment is advanced optimized, and the benefit of optimization realizes accurate exclude in vain
Voice command.Referring specifically to shown in Fig. 3, this method is specific as follows:
Step 310, when being identified that the number continuously to fail is more than setting value to the first voice command, save described the
One voice command.
Step 320, based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first voice order
Matched speech samples are enabled to record, and if it exists, to then follow the steps 330, otherwise, execute step 340.
Step 330 executes and the instruction of the speech samples record matching.
Step 340 reduces the current rotation speed of fan of kitchen ventilator.
Step 350 receives the second voice command, and identifies to second voice command.
If step 360 within the set time identifies successfully second voice command, 370 are thened follow the steps, it is no
Then, step 380 is executed.
Step 370 executes and the matched instruction of the second voice command.
Step 380, the rotation speed of fan for restoring the kitchen ventilator, and delete first voice command of preservation.
After the rotation speed of fan for reducing kitchen ventilator, the noise that kitchen ventilator itself runs generation is reduced, at this point, such as
Fruit is within the set time to the second voice command recognition failures, then it is assumed that second voice command is one invalid
Voice command, it may be possible to other extraneous sound interferences, it is also possible to which the dialogue between the kinsfolk of user is not to oil
The control command of smoke machine function.
A kind of method improving kitchen ventilator phonetic recognization rate provided in this embodiment, in the base of above-described embodiment technical solution
On plinth, if by the way that the second voice command recognition failures, the blower for restoring the kitchen ventilator turns within the set time
Speed, and the technological means of first voice command of preservation is deleted, achieve the purpose that the invalid voice command of accurate exclusion.
Example IV
Fig. 4 is a kind of method flow schematic diagram for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention four provides,
On the basis of above-described embodiment, the present embodiment is advanced optimized, and the benefit of optimization is to realize real-time update database,
To improve the phonetic recognization rate of next time.Referring specifically to shown in Fig. 4, this method is specific as follows:
Step 410, when being identified that the number continuously to fail is more than setting value to the first voice command, save described the
One voice command.
Step 420, based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first voice order
Matched speech samples are enabled to record, and if it exists, to then follow the steps 430, otherwise, execute step 440.
Step 430 executes and the instruction of the speech samples record matching.
Step 440 reduces the current rotation speed of fan of kitchen ventilator.
Step 450 receives the second voice command, and identifies to second voice command.
If step 460 within the set time identifies successfully second voice command, 470 are thened follow the steps, it is no
Then, step 480 is executed.
Step 470, execution and the matched instruction of the second voice command, and continue to execute step 490a and step
490b。
Step 480, the rotation speed of fan for restoring the kitchen ventilator, and delete first voice command of preservation.
If the similarity of step 490a, described first voice command and second voice command is greater than similarity threshold,
Then the current rotation speed of fan of first voice command, kitchen ventilator and second voice command are associated, and saved
Into database.
If the similarity of first voice command and second voice command is greater than similarity threshold, then it is assumed that described
First voice command and second voice command are identical voice command, then work as first voice command, kitchen ventilator
Preceding rotation speed of fan and second voice command are associated, and are saved in database, in case next time carries out voice knowledge
It is used when other.
For example, corresponding voice recognition data is " 111111 " when second voice command is " opening light ", work as oil
When the current rotation speed of fan of smoke machine is 100 revs/min, the corresponding identification data of first voice command recognized are
" 111100 ", and the similarity of first voice command and second voice command is greater than similarity threshold, then it will be described
The current rotation speed of fan of first voice command, kitchen ventilator and second voice command are associated to obtain such voice sample
" 100-111100-111111 " is saved in this record --- " 100-111100-111111 " records the speech samples ---
In database, query calls when facilitating next speech recognition, to improve phonetic recognization rate.If rotation speed of fan is limited to multiple shelves
Position operating, then the gear association directly corresponding with the first voice command of the first voice command and the second voice command saves and is
It can.
If the similarity of step 490b, described first voice command and second voice command is not more than similarity threshold
Value, then delete first voice command of preservation.
If the similarity of first voice command and second voice command is not more than similarity threshold, then it is assumed that institute
Stating the first voice command and second voice command is different voice command, thinks that first voice command is at this time
Invalid voice command, is given up.
A kind of method improving kitchen ventilator phonetic recognization rate provided in this embodiment, in the base of above-described embodiment technical solution
On plinth, " if the similarity of first voice command and second voice command is greater than similarity threshold, incited somebody to action by increase
The current rotation speed of fan of first voice command, kitchen ventilator and second voice command are associated, and are saved in number
According to first voice command in library, otherwise deleting preservation " technological means, reached real-time update database, with improve
The phonetic recognization rate of next time, and accurately exclude the purpose of invalid voice command.
Embodiment five
Fig. 5 is a kind of structural block diagram of the system for raising kitchen ventilator phonetic recognization rate that the embodiment of the present invention five provides, should
System specifically includes as follows:
Reduce module 510, receiving module 520 and instruction execution module 530；
Wherein, reduce module 510, identified that the number continuously to fail is more than setting value to the first voice command for working as
When, reduce the current rotation speed of fan of kitchen ventilator；Receiving module 520, for receiving the second voice command, and to second voice
Order is identified；Indicate execution module 530, if for being identified successfully to second voice command within the set time,
Then execute and the matched instruction of the second voice command；
Further, the system can also include:
First voice command preserving module, for that ought be identified the number continuously to fail to the first voice command described
After when more than setting value, before reducing the current rotation speed of fan of kitchen ventilator, first voice command is saved；
Enquiry module, for based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first language
The speech samples of sound commands match record；
Accordingly, it indicates execution module 530, is matched if being also used to exist in the database with first voice command
Speech samples record, then execute and the instruction of the speech samples record matching；
Reduce module 510, if being also used to be not present and the matched voice sample of first voice command in the database
This record executes the operation for reducing the current rotation speed of fan of kitchen ventilator.
Further, the system can also include:
Recovery module, if for restoring the oil within the set time to the second voice command recognition failures
The rotation speed of fan of smoke machine, and delete first voice command of preservation.
Further, the system can also include:
Preserving module, if being executed for being identified successfully to second voice command within the set time described
After the matched instruction of the second voice command, if the similarity of first voice command and second voice command
Greater than similarity threshold, then by the current rotation speed of fan of first voice command, kitchen ventilator and second voice command
It is associated, and is saved in database.
Further, the system can also include:
Removing module, if being executed for being identified successfully to second voice command within the set time described
After the matched instruction of the second voice command, if the similarity of first voice command and second voice command
No more than similarity threshold, then first voice command of preservation is deleted.
A kind of system improving kitchen ventilator phonetic recognization rate provided in an embodiment of the present invention, by when to the first voice command
When being identified that the number continuously to fail is more than setting value, reduce the current rotation speed of fan of kitchen ventilator；Later to received
Two voice commands are identified；If being identified successfully to second voice command within the set time, execute and described the
The technological means of the matched instruction of two voice commands, realizes when monitoring speech recognition difficulty, by suitably reducing oil smoke
The operation noise of machine itself improves phonetic recognization rate.
Method provided by any embodiment of the invention can be performed in the said goods, has the corresponding functional module of execution method
And beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to side provided by any embodiment of the invention
Method.
It will be appreciated by those skilled in the art that implementing the method for the above embodiments is that can pass through
Program is completed to instruct relevant hardware, which is stored in a storage medium, including some instructions are used so that one
A equipment (can be single-chip microcontroller, chip etc.) or processor (processor) execute each embodiment the method for the application
All or part of the steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
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 method for improving kitchen ventilator phonetic recognization rate characterized by comprising
When being identified that the number continuously to fail is more than setting value to the first voice command, reduces the current blower of kitchen ventilator and turn
Speed；
The second voice command is received, and second voice command is identified；
If being identified successfully to second voice command within the set time, execute matched with second voice command
Instruction.
2. the method according to claim 1, wherein described ought carry out the first voice command to identify continuous failure
Number when being more than setting value after, before reducing the current rotation speed of fan of kitchen ventilator, further includes:
Save first voice command；
Based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and the matched voice of the first voice command
Sample record, and if it exists, then execute the instruction with the speech samples record matching, otherwise, execute the reduction kitchen ventilator and work as
The operation of preceding rotation speed of fan.
3. according to the method described in claim 2, it is characterized by further comprising:
If the rotation speed of fan of the kitchen ventilator is restored to the second voice command recognition failures within the set time, and
Delete first voice command saved.
4. according to the method described in claim 3, it is characterized in that, if described within the set time order second voice
Order identify successfully, then execution and the matched instruction of the second voice command after, further includes:
If the similarity of first voice command and second voice command is greater than similarity threshold, by first language
The current rotation speed of fan of sound order, kitchen ventilator and second voice command are associated, and are saved in database.
5. according to the method described in claim 3, it is characterized in that, if described within the set time order second voice
Order identify successfully, then execution and the matched instruction of the second voice command after, further includes:
If the similarity of first voice command and second voice command is not more than similarity threshold, preservation is deleted
First voice command.
6. a kind of system for improving kitchen ventilator phonetic recognization rate characterized by comprising
Reduce module, for reducing oil smoke when being identified that the number continuously to fail is more than setting value to the first voice command
The current rotation speed of fan of machine；
Receiving module for receiving the second voice command, and identifies second voice command；
Indicate execution module, if within the set time to second voice command identify successfully, execution with it is described
The matched instruction of second voice command.
7. system according to claim 6, which is characterized in that further include:
First voice command preserving module, for that ought be identified that the number continuously to fail is more than to the first voice command described
After when setting value, before reducing the current rotation speed of fan of kitchen ventilator, first voice command is saved；
Enquiry module, for based on kitchen ventilator it is current rotation speed of fan inquiry database in whether there is and first voice order
Matched speech samples are enabled to record；
Accordingly, the instruction execution module, if being also used to exist in the database matched with first voice command
Speech samples record then executes the instruction with the speech samples record matching；
The reduction module, if being also used in the database, there is no remember with the matched speech samples of first voice command
Record executes the operation for reducing the current rotation speed of fan of kitchen ventilator.
8. system according to claim 7, which is characterized in that further include:
Recovery module, if for restoring the kitchen ventilator within the set time to the second voice command recognition failures
Rotation speed of fan, and delete first voice command of preservation.
9. system according to claim 8, which is characterized in that further include:
Preserving module, if for being identified successfully to second voice command within the set time described, execution and institute
After stating the matched instruction of the second voice command, if the similarity of first voice command and second voice command is greater than
Similarity threshold then carries out the current rotation speed of fan of first voice command, kitchen ventilator and second voice command
Association, and be saved in database.
10. system according to claim 8, which is characterized in that further include:
Removing module, if for being identified successfully to second voice command within the set time described, execution and institute
After stating the matched instruction of the second voice command, if the similarity of first voice command and second voice command is little
In similarity threshold, then first voice command of preservation is deleted.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610899191.9A CN106439967B (en) | 2016-10-14 | 2016-10-14 | Method and system for improving voice recognition rate of range hood |
| PCT/CN2016/113278 WO2018068422A1 (en) | 2016-10-14 | 2016-12-29 | Method and system for improving kitchen ventilator voice recognition rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610899191.9A CN106439967B (en) | 2016-10-14 | 2016-10-14 | Method and system for improving voice recognition rate of range hood |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106439967A CN106439967A (en) | 2017-02-22 |
| CN106439967B true CN106439967B (en) | 2019-01-04 |
Family
ID=58175056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610899191.9A Active CN106439967B (en) | 2016-10-14 | 2016-10-14 | Method and system for improving voice recognition rate of range hood |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106439967B (en) |
| WO (1) | WO2018068422A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106875945B (en) * | 2017-03-09 | 2020-06-26 | 广东美的制冷设备有限公司 | Voice control method and device and air conditioner |
| CN111076245B (en) * | 2018-10-19 | 2021-07-23 | 宁波方太厨具有限公司 | Intelligent noise reduction method for range hood |
| 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 |
| CN113380265A (en) * | 2020-03-10 | 2021-09-10 | 博西华电器（江苏）有限公司 | Household appliance noise reduction method and device, storage medium, household appliance and range hood |
| US20220180865A1 (en) * | 2020-12-03 | 2022-06-09 | International Business Machines Corporation | Runtime topic change analyses in spoken dialog contexts |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090240496A1 (en) * | 2008-03-24 | 2009-09-24 | Kabushiki Kaisha Toshiba | Speech recognizer and speech recognizing method |
| JP2009230620A (en) * | 2008-03-25 | 2009-10-08 | Panasonic Corp | Information processor |
| JP4622124B2 (en) * | 2001-03-13 | 2011-02-02 | 株式会社デンソー | Navigation device |
| CN102761721A (en) * | 2011-04-27 | 2012-10-31 | 海尔集团公司 | Volume control method and system for TV |
| CN202561865U (en) * | 2012-05-08 | 2012-11-28 | 成都众询科技有限公司 | Voice control kitchen ventilator |
| US20130332159A1 (en) * | 2012-06-08 | 2013-12-12 | Apple Inc. | Using fan throttling to enhance dictation accuracy |
| CN104715752A (en) * | 2015-04-09 | 2015-06-17 | 刘文军 | Voice recognition method, voice recognition device and voice recognition system |
| CN205208686U (en) * | 2015-12-22 | 2016-05-04 | 嵊州市乐普斯电器有限公司 | Speech input controls range hood |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10208466A1 (en) * | 2002-02-27 | 2004-01-29 | BSH Bosch und Siemens Hausgeräte GmbH | Household electrical appliance |
| ATE466240T1 (en) * | 2005-08-10 | 2010-05-15 | Best S P A | EXTRACTOR HOOD WITH COMMUNICATION FUNCTION |
| CN103673008B (en) * | 2013-09-16 | 2017-01-04 | 宁波方太厨具有限公司 | A kind of intelligent range hood and the control method of this range hood |
| CN104505092B (en) * | 2014-12-10 | 2017-12-22 | 广东美的制冷设备有限公司 | Air conditioner sound control method and system |
| CN104464729A (en) * | 2014-12-16 | 2015-03-25 | 佛山市顺德区美的电热电器制造有限公司 | Voice-control electric appliance and voice control method thereof |
| CN104517607A (en) * | 2014-12-16 | 2015-04-15 | 佛山市顺德区美的电热电器制造有限公司 | Speed-controlled appliance and method of filtering noise therein |
| CN104992709B (en) * | 2015-06-25 | 2019-06-11 | 广州视源电子科技股份有限公司 | Voice instruction execution method and voice recognition equipment |
| CN105653233B (en) * | 2015-12-30 | 2019-06-04 | 芜湖美智空调设备有限公司 | It is associated with the method and controlling terminal of voice signal and control instruction |
-
2016
- 2016-10-14 CN CN201610899191.9A patent/CN106439967B/en active Active
- 2016-12-29 WO PCT/CN2016/113278 patent/WO2018068422A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4622124B2 (en) * | 2001-03-13 | 2011-02-02 | 株式会社デンソー | Navigation device |
| US20090240496A1 (en) * | 2008-03-24 | 2009-09-24 | Kabushiki Kaisha Toshiba | Speech recognizer and speech recognizing method |
| JP2009230620A (en) * | 2008-03-25 | 2009-10-08 | Panasonic Corp | Information processor |
| CN102761721A (en) * | 2011-04-27 | 2012-10-31 | 海尔集团公司 | Volume control method and system for TV |
| CN202561865U (en) * | 2012-05-08 | 2012-11-28 | 成都众询科技有限公司 | Voice control kitchen ventilator |
| US20130332159A1 (en) * | 2012-06-08 | 2013-12-12 | Apple Inc. | Using fan throttling to enhance dictation accuracy |
| CN104715752A (en) * | 2015-04-09 | 2015-06-17 | 刘文军 | Voice recognition method, voice recognition device and voice recognition system |
| CN205208686U (en) * | 2015-12-22 | 2016-05-04 | 嵊州市乐普斯电器有限公司 | Speech input controls range hood |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106439967A (en) | 2017-02-22 |
| WO2018068422A1 (en) | 2018-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106439967B (en) | Method and system for improving voice recognition rate of range hood | |
| JP2019533193A (en) | Voice control system, wakeup method thereof, wakeup device, home appliance, coprocessor | |
| CN110262273A (en) | Household equipment control method and device, storage medium and intelligent household system | |
| CN108564948A (en) | A kind of audio recognition method and electronic equipment | |
| CN111128192A (en) | Voice recognition noise reduction method, system, mobile terminal and storage medium | |
| CN112382285B (en) | Voice control method, voice control device, electronic equipment and storage medium | |
| CN105931639B (en) | A kind of voice interactive method for supporting multistage order word | |
| CN105336324A (en) | Language identification method and device | |
| CN107909998A (en) | Phonetic order processing method, device, computer equipment and storage medium | |
| CN105679315A (en) | Voice-activated and voice-programmed control method and control system | |
| CN109545213A (en) | Equipment control method and device, storage medium and air conditioner | |
| CN112735482A (en) | Endpoint detection method and system based on combined deep neural network | |
| CN110570873A (en) | voiceprint wake-up method and device, computer equipment and storage medium | |
| TWI557722B (en) | Method to filter out speech interference, system using the same, and computer readable recording medium | |
| JP7208951B2 (en) | Voice interaction method, apparatus, device and computer readable storage medium | |
| WO2021169711A1 (en) | Instruction execution method and apparatus, storage medium, and electronic device | |
| AU2021258012B1 (en) | Utilizing machine learning models to provide cognitive speaker fractionalization with empathy recognition | |
| CN109859752A (en) | Voice control method, device, storage medium and voice joint control system | |
| CN107910003A (en) | A kind of voice interactive method and speech control system for smart machine | |
| CN109065036A (en) | Method, apparatus, electronic equipment and the computer readable storage medium of speech recognition | |
| CN107742516B (en) | Intelligent recognition method, robot and computer readable storage medium | |
| Bukhsh et al. | On out-of-distribution detection for audio with deep nearest neighbors | |
| CN114571473A (en) | Control method and device for foot type robot and foot type robot | |
| US9626967B2 (en) | Information processing method and electronic device | |
| Komatani et al. | User adaptive restoration for incorrectly-segmented utterances in spoken dialogue systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |