CN109065054A - Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing - Google Patents
Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109065054A CN109065054A CN201811013550.1A CN201811013550A CN109065054A CN 109065054 A CN109065054 A CN 109065054A CN 201811013550 A CN201811013550 A CN 201811013550A CN 109065054 A CN109065054 A CN 109065054A
- Authority
- CN
- China
- Prior art keywords
- error correction
- user
- speech recognition
- library
- recognition result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 424
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000012986 modification Methods 0.000 claims description 26
- 230000004048 modification Effects 0.000 claims description 26
- 238000012217 deletion Methods 0.000 claims description 12
- 230000037430 deletion Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 230000001052 transient effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- LPUQAYUQRXPFSQ-DFWYDOINSA-M monosodium L-glutamate Chemical compound [Na+].[O-]C(=O)[C@@H](N)CCC(O)=O LPUQAYUQRXPFSQ-DFWYDOINSA-M 0.000 description 5
- 235000013923 monosodium glutamate Nutrition 0.000 description 5
- 239000004223 monosodium glutamate Substances 0.000 description 5
- 201000009487 Amblyopia Diseases 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 241000283153 Cetacea Species 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/187—Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
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)
- Machine Translation (AREA)
Abstract
The embodiment of the invention discloses a kind of speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing.This method comprises: obtaining the first speech recognition result to error correction of user；According to user's corresponding user's error correction library determine in the first speech recognition result to error correction term, and with to the corresponding substitute of error correction term, it will be replaced with to error correction term with to the corresponding substitute of error correction term in first speech recognition result, obtain the second speech recognition result.The scheme of the embodiment of the present invention, error correction to the speech recognition result of user, be determine and replace according to user's error correction corresponding to the user library in speech recognition result to error correction term, the error correction with user-association can be carried out to speech recognition result, effectively improve the accuracy rate of speech recognition result.
Description
Technical field
The present embodiments relate to technical field of voice recognition, more particularly to a kind of speech recognition error correction method, device,
Electronic equipment and readable storage medium storing program for executing.
Background technique
Speech recognition technology is the technology that a kind of pair of user voice signal is identified, with voice and natural language processing
The development of the relevant technologies, speech recognition are widely used to each electron-like at present and produce as a kind of common human-computer interaction technology
In product, liking for consumer is had received with its naturally convenient interactive mode, the mainstream for being increasingly becoming the intellectual product epoch is handed over
Mutual control mode.
In the specific implementation process, mistake can often occur to inventor in speech recognition result in the prior art for discovery, greatly
Affect user experience, how to improve the accuracy of semantics recognition result is the important of field of speech recognition urgent need to resolve
One of problem.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of speech recognition error correction method, device, electronic equipment and readable depositing
Storage media can effectively improve the accuracy rate of speech recognition result.
To solve the above-mentioned problems, the embodiment of the present invention mainly provides the following technical solutions:
In a first aspect, the embodiment of the invention provides a kind of speech recognition error correction methods, this method comprises:
Obtain the first speech recognition result to error correction of user；
According to user's error correction corresponding to the user library determine in the first speech recognition result to error correction term, and with wait entangle
The corresponding substitute of wrong word；
Wherein, user's error correction library is for storing by error correction information, by error correction information include by error correction term and with by error correction
The corresponding substitute of word, and/or, by error correction phonetic and with by the corresponding substitute of error correction phonetic；
It will be replaced with to error correction term with to the corresponding substitute of error correction term in first speech recognition result, obtain the second language
Sound recognition result.
Second aspect, the embodiment of the present invention also provide a kind of speech recognition error correction device, which includes:
Speech recognition result obtains module, for obtaining the first speech recognition result to error correction of user；
To error correction information determining module, for determining the first speech recognition result according to user's error correction corresponding to the user library
In to error correction term, and with to the corresponding substitute of error correction term；
Wherein, user's error correction library is for storing by error correction information, by error correction information include by error correction term and with by error correction
The corresponding substitute of word, and/or, by error correction phonetic and with by the corresponding substitute of error correction phonetic；
Speech recognition correction module, for by the first speech recognition result to error correction term replacing with to error correction term pair
The substitute answered obtains the second speech recognition result.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment, comprising:
At least one processor；
And bus connected to the processor, at least one processor；Wherein,
Processor, memory complete mutual communication by bus；
Processor is used to call the program instruction in memory, to execute above-mentioned speech recognition error correction method.
Fourth aspect, the embodiment of the present invention also provide a kind of non-transient computer readable storage medium, non-transient computer
Readable storage medium storing program for executing stores computer instruction, and computer instruction makes computer execute above-mentioned speech recognition error correction method.
By above-mentioned technical proposal, technical solution provided in an embodiment of the present invention is at least had the advantage that
Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing provided in an embodiment of the present invention, for
The error correction of the speech recognition result at family, be determined according to user's error correction corresponding to the user library in speech recognition result wait entangle
Wrong word, and will be replaced to error correction term, the error correction to speech recognition result is realized, since user's error correction library is corresponding with user
, therefore, it is based on user's error correction library, the error correction with user-association can be carried out to speech recognition result, realizes personalization
Error correction can effectively improve the accuracy rate of speech recognition result.
Above description is only the general introduction of technical solution of the embodiment of the present invention, in order to better understand the embodiment of the present invention
Technological means, and can be implemented in accordance with the contents of the specification, and in order to allow above and other mesh of the embodiment of the present invention
, feature and advantage can be more clearly understood, the special specific embodiment for lifting the embodiment of the present invention below.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
The limitation of embodiment.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of speech recognition error correction method provided in an embodiment of the present invention；
Fig. 2 shows the process signals of the method for the voice data to be identified for obtaining user a kind of in the embodiment of the present invention
Figure；
Fig. 3 shows a kind of structural schematic diagram of speech recognition error correction device provided in an embodiment of the present invention；
Fig. 4 shows the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 shows a kind of flow diagram of speech recognition error correction method provided in an embodiment of the present invention, such as institute in figure
Show, which may include:
Step S110: the first speech recognition result to error correction of user is obtained；
Step S120: according to user's error correction corresponding to the user library determine in the first speech recognition result to error correction term,
And with to the corresponding substitute of error correction term, wherein user's error correction library includes quilt by error correction information for storing by error correction information
Error correction term and with by the corresponding substitute of error correction term, and/or, by error correction phonetic and with by the corresponding replacement of error correction phonetic
Word；
Step S130: by the first speech recognition result to error correction term replace with to the corresponding substitute of error correction term,
Obtain the second speech recognition result.
In the embodiment of the present invention, error correction for the speech recognition result of user is entangled according to user corresponding to the user
Wrong library come determine in speech recognition result to error correction term, and will be replaced, be realized to speech recognition result to error correction term
Error correction, due to user's error correction library be it is corresponding to the user, be based on user's error correction library, can to speech recognition result into
The capable error correction with user-association, realizes personalized error correcting, can effectively improve the accuracy rate of speech recognition result.
In the embodiment of the present invention, the first speech recognition result can be the preliminary recognition result of voice data, voice data
The voice data to be identified that can be the user being currently received, voice number being got before being also possible to or receiving
According to the first speech recognition result can be textual form.
It is understood that the executing subject of the speech recognition error correction method of the embodiment of the present application can be user terminal and set
It is standby, it is also possible to server, correspondingly, user's error correction library corresponding can configure in subscriber terminal equipment or server.?
In one optional embodiment, voice error correction recognition methods can be executed by server.
On the basis of the above embodiments, speech recognition error correction method provided in an embodiment of the present invention can also include:
The error correction configuring request of user is obtained, includes by the configuration-direct of error correction information, configuration in error correction configuring request
Instruction may include at least one of addition instruction, modification instruction and deletion instruction；
If configuration-direct includes addition instruction, by instruction is corresponding is added to user's error correction library by error correction information with addition
In；
If configuration-direct includes modification instruction and/or deletes instruction, instructed and/or deleted according to modification and instruct, to entangling
It is performed corresponding processing accordingly by error correction information in wrong library.
By the embodiment, user is able to participate in user's error correction library by the configuration of error correction information, most due to user
Oneself is understood using in speech recognition process, for individual subscriber, which information is often identified mistake, therefore,
User can send error correction configuring request, subscriber terminal equipment or speech recognition correction services according to the practical application request of oneself
Device performs corresponding processing the information in user's error correction library to user by the voice error correction configuring request of acquisition user,
Such as add it is new by error correction information, be deleted or modified it is existing by error correction information in user's error correction library.
It is understood that may include needing to be added to use in addition instruction when configuration-direct includes addition instruction
Family error correction library by error correction information, can specifically include need it is to be added by error correction term and by the corresponding substitute of error correction term,
And/or it needs to be added by error correction phonetic and by the corresponding substitute of error correction phonetic.
It, specifically can be with to being modified in user's error correction library by error correction information when configuration-direct includes modification instruction
It also may include to by the modification of error correction phonetic or to it including the modification to substitute is corresponded to by the modification of error correction term or to it
The modification of corresponding substitute.Modification instruction in may include need modify by error correction information and with modification by error correction information
Information after corresponding modification, wherein need to modify can be by error correction information by error correction term, need modify by error correction term pair
The substitute answered, need to modify by error correction phonetic, need to modify by one or more in the corresponding substitute of error correction phonetic
?.For example, in user's error correction library being " A → B " by error correction information, A is by error correction term, and B is corresponding substitute, modification instruction
It can serve to indicate that and A is replaced with into C, alternatively, B is replaced with D etc..
When configuration-direct includes deleting instruction, to being deleted by error correction information in user's error correction library, can be pair
By the deletion of error correction term and its corresponding substitute, it is also possible to by the deletion of error correction phonetic and its corresponding substitute.Deletion refers to
It may include needing to delete by error correction information in order, what which deleted can be by error correction information by error correction term, by error correction
The corresponding substitute of word, by error correction phonetic, by one or more in the substitute of error correction phonetic.For example, still being entangled with above-mentioned
It for wrong information " A → B ", is needing to delete this by error correction information, is deleting instruction and then can serve to indicate that and entangled A is corresponding
Wrong information deletion can be used for instruction and be deleted by error correction information by B is corresponding, and subscriber terminal equipment or server are receiving
When the above two any instruction deleted in instruction, then it can will be deleted in user's error correction library by error correction information " A → B ".
In practical applications, the error correction configuration information of user can be obtained by providing error correction platform for user.For example,
In one example, when the executing subject of voice error correction method of the embodiment of the present invention is server, user can be flat by error correction
Platform sends error correction configuring request to server, and can corresponding user's error correction library be respectively created for each user in advance in server,
The user corresponding user's error correction library or corresponding to the user will be added to by error correction information after receiving error correction configuring request
Error correction library in modified or deleted by error correction information, be also possible to for the first time receive user addition instruction when, then
Corresponding user's error correction library is created for user.
In another example, when the executing subject of the voice error correction method of the embodiment of the present invention is subscriber terminal equipment,
User can send error correction configuring request to subscriber terminal equipment by the error correction platform, it is to be understood that user is by entangling
When wrong platform sends configuring request to subscriber terminal equipment, which, which can be, is transmitted directly to subscriber terminal equipment, can also be with
It is to be sent to subscriber terminal equipment by other equipment.For example, if user can log in the platform by subscriber terminal equipment,
Then subscriber terminal equipment can directly receive the error correction configuring request of user, put down if user logs in the error correction by other equipment
Error correction configuring request after other equipment receive the error correction configuring request of user, can be sent to subscriber terminal equipment by platform,
Subscriber terminal equipment can be sent to by server, subscriber terminal equipment is created after getting error correction configuring request for user
Build or update user's error correction library.
In another example, when the executing subject of the voice error correction method of the embodiment of the present invention is subscriber terminal equipment,
Error correction configuring request can be sent to server by error correction platform by user, and user's error correction library of each user is completed by server
Creation or update, subscriber terminal equipment periodically can obtain user's error correction library of the equipment user to server and update, or
Person is entangled periodically or when user's error correction library changes to the user that subscriber terminal equipment pushes the equipment user from server
Wrong library, so that subscriber terminal equipment executes the voice error correction method of the embodiment of the present invention based on the user's error correction library received.Together
Sample, it, can also be whole by the user of each user when the executing subject of the voice error correction method of the embodiment of the present invention is server
End equipment completes the creation or update in user's error correction library of each user, by each according to the error correction configuring request of the user got
User's error correction library of the respective each equipment user for creating or updating is sent to server by subscriber terminal equipment, so that server base
The voice error correction method of the embodiment of the present invention is executed in the user's error correction library received.
It is understood that the concrete form of above-mentioned error correction platform can configure according to the actual application, for example, can be with
It is configured to website, user can submit the error correction configuring request of oneself by logging in corresponding website；It is also configured as applying
The form of program (APP), user can download the corresponding APP of installation, submit the error correction configuring request of oneself.Specifically, for example
User can configure corresponding function choosing by clicking error correction on website by the corresponding website of mobile phone sign-on access
, and the error correction configuring request submitted required for can filling in the User Page shown can " addition be entangled by selection
Error correction configuring request comprising addition instruction is sent to server or user terminal by the corresponding function button of wrong configuration information "
Equipment, server or subscriber terminal equipment upon receiving the request, will " if " replace with that " amblyopia " is corresponding to be believed by error correction
Breath is added in user's error correction library.User when submitting an error correction configuring request, can also submit simultaneously including addition instruction,
Delete the error correction configuring request of a variety of instructions such as instruction, modification instruction.
In the embodiment of the present invention, the user that can be by error correction information in user's error correction library needs certainly according to the use of itself
Definition setting, several situations including but not limited to below:
User has the use needs of specialized vocabulary, for example, user needs commonly using medical vocabulary " amblyopia ", the first voice
May often be identified as in recognition result " if ", then user can according to need submission will " if " replace with " amblyopia "
Error correction configuring request, then the first speech recognition result be " if " when, the method based on the embodiment of the present invention, will " if "
Replace with " amblyopia ".
The use demand of user's common words, for example, " broadcasting " this word is commonly used in user, in the first speech recognition result
It may often be identified as " dialling ", then user can according to need the error correction configuring request submitted and " dialling " is replaced with to " broadcasting ".
Then when the first speech recognition result is " dialling entertainment news ", the method based on the embodiment of the present invention can be replaced " dialling "
It is changed to " broadcasting ", obtains second speech recognition result of " broadcasting entertainment news ".
There are words caused by specific pronunciation to mispronounce by user, for example, user can send out " er " as " e ", the knowledge of the first voice
It may will recognise that text (such as " hungry ") corresponding with pronunciation " e " in other result, user, which can according to need, submits pronunciation " e "
Corresponding text (such as " hungry ") replaces with the error correction configuring request for the correspondence text (such as " two ") that pronunciation is " er ", then in the first voice
When recognition result is the correspondence text of pronunciation " e ", the method based on the embodiment of the present invention can be by the related text of pronunciation " e "
Replace with the correspondence text of pronunciation " er ".
The speech recognition error correction method of the embodiment of the present invention, user can participate in corresponding user's error correction library
The personalized language of including but not limited to above situation may be implemented based on each user corresponding user's error correction library for the configuration of information
Sound identification error correction targetedly realizes error correction for different user, improves the correctness of recognition result.
Certainly, can also be believed based on what the statistical data in speech recognition pre-seted by error correction with server in user's error correction library
Breath, such as be easy to be specifically as follows the phonetically similar word being erroneously identified, dialect etc. by the word of speech recognition errors, replaced accordingly
Changing word can be the corresponding correct recognition results such as the above-mentioned phonetically similar word being erroneously identified, dialect.
Step S120 in the above embodiment of the present invention can be there are many embodiment, one of optional embodiment
Are as follows:
If the participle in the first speech recognition result is identical by error correction term as in user's error correction library, alternatively, the spelling of participle
Sound is identical by error correction phonetic as in user's error correction library, it is determined that segments as to error correction term；
Will with segment it is identical by the corresponding substitute of error correction term or identical with the phonetic of participle by error correction phonetic pair
The error correction term answered is determined as to the corresponding substitute of error correction term.
In the embodiment of the present invention, the first speech recognition result can be made of multiple participles, by each participle and can be used
What is stored in the error correction library of family is compared by error correction term, and if they are the same, then the participle is confirmed as to error correction term, identical as the participle
Be then the corresponding substitute of the participle by the corresponding substitute of error correction term.Also the phonetic of available participle, by the spelling of participle
Sound in user's error correction library compared with storing by error correction phonetic, and if they are the same, then the phonetic of the participle is to error correction phonetic, with this point
The identical phonetic of word by the corresponding substitute of error correction phonetic is then to wait for the corresponding substitute of error correction phonetic with this.
On the basis of the above embodiments, when including by error correction phonetic by error correction information, side provided in an embodiment of the present invention
Method can also include:
User's error correction library is also stored with by the tone of error correction phonetic, the phonetic of participle and being spelled in user's error correction library by error correction
Sound is identical, refers to that the phonetic of participle is identical by error correction phonetic as in user's error correction library, and the tone of the phonetic segmented and user
The tone by error correction phonetic in error correction library is identical.
In the embodiment of the present invention, can also configure by the tone of error correction phonetic so that not same tone by error correction phonetic
It can be corresponding with substitute respectively.Specifically, the phonetic and tone that are segmented in available first speech recognition result, it will
Phonetic and tone are segmented compared with being stored in user's error correction library by error correction phonetic and tone, and then determines the first speech recognition knot
The phonetic and tone of participle in fruit whether with it is all the same by error correction phonetic and tone in user's error correction library, if all the same,
The phonetic of the participle is to be replaced with the correspondence substitute stored in user's error correction library to error correction phonetic.
It is understood that when user's error correction library is also stored with the tone by error correction phonetic, correspondingly, the error correction of user is matched
Set include in request by can also be comprising by error correction phonetic and by the tone of error correction phonetic in error correction information.To user's error correction library
In the deletion by error correction information can also include being combined pair to by error correction phonetic and its tone and by error correction phonetic and its tone
The deletion for the substitute answered；It can also include to by error correction phonetic and its sound to the modification by error correction information in user's error correction library
The modification of tune or the modification that corresponding substitute is combined to error correction phonetic and its tone.
In alternative embodiment of the invention, by being replaced with to error correction term and to error correction term pair in the first speech recognition result
Before the substitute answered, can also include:
According to error correction term, to the corresponding substitute of error correction term and to error correction term in the first speech recognition result
Contextual information, determination will be replaced with to error correction term to the corresponding substitute of error correction term.
In practical applications, it in order to avoid will directly be replaced with to error correction term with to the corresponding substitute of error correction term, causes
The problem of error correction mistake, can be after determining to error correction term and corresponding substitute, before being replaced, based on wait entangle
Contextual information of the wrong word in the first speech recognition result, it is determined whether need to replace, to avoid occurring asking for mistake after replacement
Topic, improves the accuracy rate of final recognition result.
For example, in one example, in user's error correction library includes that " dialling " is replaced with " broadcasting " by error correction information, but the first language
Sound recognition result be " phone for requesting A ", then according to " dialling ", " broadcasting " and " phone for requesting A " contextual information,
It knows " dialling " is replaced with " broadcasting ", therefore, does not need then to be replaced at this time.In another example, user's error correction library
In by error correction information include " monosodium glutamate " replace with " micro- whale ", the first speech recognition result be " monosodium glutamate TV please be open ",
Then it can determine according to the contextual information of " monosodium glutamate ", " micro- whale " and the first speech recognition result at this time and need " will to open
" monosodium glutamate " in monosodium glutamate TV " replaces with " micro- whale ".
Step S110 in above-described embodiment can be there are many embodiment, as shown in Fig. 2, one of optional implementation
Mode are as follows:
Step S111: the voice data to be identified of user is obtained；
Step S112: speech recognition is carried out to voice data to be identified, obtains the first speech recognition result.
In the embodiment of the present invention, when the executing subject of speech recognition error correction method is subscriber terminal equipment, user terminal is set
The standby voice data to be identified that can directly receive user, when executing subject is server, server can pass through user's end
The voice data to be identified of end equipment acquisition user.
In practical applications, user's error correction library can reside in server, and the first speech recognition result is set by user terminal
Preparation gives server, and server returns to the second speech recognition result that error correction obtains to subscriber terminal equipment after being handled,
So that subscriber terminal equipment can be exported or be responded to the second speech recognition result；User's error correction library can also exist on
Subscriber terminal equipment, subscriber terminal equipment are handled it after receiving the first speech recognition result, obtain the knowledge of the second voice
Not as a result, the second speech recognition result is exported or responded.
It is understood that in practical applications, if not determined in the first speech recognition result according to user's error correction library
Out to error correction term, then it can be performed corresponding processing based on the first speech recognition result, such as the first speech recognition result is provided
Corresponding operation is carried out to user or based on the first speech recognition result.It is of course also possible to being not determined by when error correction term, base
Error correction etc. is carried out to the first speech recognition result in the voice error correcting system of other pre-configurations.
Fig. 3 shows a kind of structural schematic diagram of speech recognition error correction device provided in an embodiment of the present invention, such as Fig. 3 institute
Show, which may include:
Speech recognition result obtains module 210, for obtaining the first speech recognition result to error correction of user；
To error correction information determining module 220, for determining the first speech recognition according to user's error correction corresponding to the user library
As a result in error correction term, and with to the corresponding substitute of error correction term；
Wherein, user's error correction library is for storing by error correction information, by error correction information include by error correction term and with by error correction
The corresponding substitute of word, and/or, by error correction phonetic and with by the corresponding substitute of error correction phonetic；
Speech recognition correction module 230, for by the first speech recognition result to error correction term replacing with to error correction
The corresponding substitute of word, obtains the second speech recognition result.
The embodiment of the invention provides a kind of speech recognition error correction devices, the error correction for the speech recognition result of user,
Be determined according to user's error correction corresponding to the user library in speech recognition result to error correction term, and will be replaced to error correction term
Change, realize error correction to speech recognition result, due to user's error correction library be it is corresponding to the user, be based on user's error correction
Library can carry out the error correction with user-association to speech recognition result, realize personalized error correcting, can effectively improve voice knowledge
The accuracy rate of other result.
Optionally, above-mentioned speech recognition error correction device 20 can also include:
Error correction information configuration module includes to being entangled for obtaining the error correction configuring request of user, in error correction configuring request
The configuration-direct of wrong information, configuration-direct include at least one of addition instruction, modification instruction and deletion instruction；
If configuration-direct includes addition instruction, by instruction is corresponding is added to user's error correction library by error correction information with addition
In；
If configuration-direct includes modification instruction and/or deletes instruction, instructed and/or deleted according to modification and instruct, to entangling
It is performed corresponding processing accordingly by error correction information in wrong library.
Optionally, above-mentioned speech recognition error correction device 20 can also include:
Error correction determining module, for replacing in the first speech recognition result to error correction term is corresponding with to error correction term
Substitute before, according to error correction term, to the corresponding substitute of error correction term and to error correction term in the first speech recognition result
In contextual information, determination will replaces with to error correction term to the corresponding substitute of error correction term.
Optionally, can be specifically used for error correction information determining module 220:
When the participle in the first speech recognition result is identical by error correction term as in user's error correction library, alternatively, participle
When phonetic is identical by error correction phonetic as in user's error correction library, determine participle for error correction term；
Will with segment it is identical by the corresponding substitute of error correction term or identical with the phonetic of participle by error correction phonetic pair
The error correction term answered is determined as to the corresponding substitute of error correction term.
Optionally, user's error correction library is also stored with by the tone of error correction phonetic, in the phonetic of participle and user's error correction library
It is identical by error correction phonetic, the sound for the phonetic for referring to that the phonetic of participle is identical by error correction phonetic as in user's error correction library, and segmenting
It adjusts identical as the tone by error correction phonetic in user's error correction library.
Optionally, speech recognition result obtains module 210 and can be specifically used for:
The voice data to be identified for obtaining user carries out speech recognition to voice data to be identified, obtains the knowledge of the first voice
Other result.
Since the speech recognition error correction device that the present embodiment is introduced is that can execute the voice in the embodiment of the present invention to know
The device of other error correction method, so based on speech recognition error correction method described in the embodiment of the present invention, the affiliated skill in this field
Art personnel can understand the specific embodiment and its various change form of the speech recognition error correction device of the present embodiment, so
How speech recognition error correction method in embodiment of the present invention in detail is realized if being no longer situated between for the speech recognition error correction device at this
It continues.As long as those skilled in the art implement device used by speech recognition error correction method in the embodiment of the present invention, all belong to
In the range that the application to be protected.
The embodiment of the invention provides a kind of electronic equipment, as shown in Figure 4, comprising: at least one processor
(processor)41；And at least one processor (memory) 42, the bus 43 being connect with processor 41；Wherein,
Processor 41, memory 42 complete mutual communication by bus 43；
Processor 41 is used to call the program instruction in memory 42, to execute the step in above method embodiment.
The embodiment of the invention provides a kind of electronic devices, the error correction for the speech recognition result of user, be according to
User corresponding user's error correction library come determine in speech recognition result to error correction term, and will be replaced, realize to error correction term
Error correction to speech recognition result, due to user's error correction library be it is corresponding to the user, be based on user's error correction library, can
Error correction with user-association is carried out to speech recognition result, personalized error correcting is realized, speech recognition result can be effectively improved
Accuracy rate.
The embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storages
Medium storing computer instruction, computer instruction make computer execute method provided by above-mentioned each method embodiment.
The embodiment of the invention provides a kind of non-transient computer readable storage mediums, for the speech recognition result of user
Error correction, be determined according to user's error correction corresponding to the user library in speech recognition result to error correction term, and will be to error correction
Word is replaced, and realizes error correction to speech recognition result, due to user's error correction library be it is corresponding to the user, based on should
User's error correction library can carry out the error correction with user-association to speech recognition result, realize personalized error correcting, can effectively mention
The accuracy rate of high speech recognition result.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of speech recognition error correction method characterized by comprising
Obtain the first speech recognition result to error correction of user；
According to user's error correction library corresponding with the user determine in first speech recognition result to error correction term, Yi Jiyu
It is described to the corresponding substitute of error correction term；
Wherein, user's error correction library is for storing by error correction information, by error correction information include by error correction term and with by error correction
The corresponding substitute of word, and/or, by error correction phonetic and with by the corresponding substitute of error correction phonetic；
It will replace with described to error correction term to the corresponding substitute of error correction term described in first speech recognition result, obtain
To the second speech recognition result.
2. a kind of speech recognition error correction method according to claim 1, which is characterized in that further include:
Obtain the error correction configuring request of the user, include in the error correction configuring request to by the configuration-direct of error correction information,
The configuration-direct includes at least one of addition instruction, modification instruction and deletion instruction；
If the configuration-direct includes the addition instruction, institute is added to by error correction information by corresponding with the addition instruction
It states in user's error correction library；
If the configuration-direct includes the modification instruction and/or deletes instruction, is instructed according to the modification and/or deletion refers to
It enables, to being performed corresponding processing accordingly by error correction information in the error correction library.
3. a kind of speech recognition error correction method according to claim 1, which is characterized in that described to know first voice
In other result it is described to error correction term replace with before the corresponding substitute to error correction term, comprising:
According to it is described to error correction term, it is described to the corresponding substitute of error correction term and it is described to error correction term in first voice
Contextual information in recognition result, determine replaced with described to error correction term it is described to the corresponding substitute of error correction term.
4. a kind of speech recognition error correction method according to any one of claim 1 to 3, which is characterized in that the basis
User's error correction library of the user determine in first speech recognition result to error correction term, and with described to error correction term pair
The substitute answered, comprising:
If the participle in first speech recognition result is identical by error correction term as in user's error correction library, alternatively, described
The phonetic of participle is identical by error correction phonetic as in user's error correction library, it is determined that the participle is to be described to error correction term；
Will be identical with the participle by the corresponding substitute of error correction term, or identical with the phonetic of the participle spelled by error correction
The corresponding error correction term of sound is determined as described to the corresponding substitute of error correction term.
5. a kind of speech recognition error correction method according to claim 4, which is characterized in that user's error correction library also stores
Have by the tone of error correction phonetic, the phonetic of the participle is identical by error correction phonetic as in user's error correction library, refers to described
The phonetic of participle is identical by error correction phonetic as in user's error correction library, and the tone of the phonetic of the participle and user's error correction
The tone by error correction phonetic in library is identical.
6. a kind of speech recognition error correction method according to any one of claim 1 to 3, which is characterized in that the acquisition
The first speech recognition result to error correction of user, comprising:
Obtain the voice data to be identified of the user；
Speech recognition is carried out to the voice data to be identified, obtains first speech recognition result.
7. a kind of speech recognition error correction device characterized by comprising
Speech recognition result obtains module, for obtaining the first speech recognition result to error correction of user；
To error correction information determining module, for determining first speech recognition according to user's error correction library corresponding with the user
As a result in error correction term, and with described to the corresponding substitute of error correction term；
Wherein, user's error correction library is for storing by error correction information, by error correction information include by error correction term and with by error correction
The corresponding substitute of word, and/or, by error correction phonetic and with by the corresponding substitute of error correction phonetic；
Speech recognition correction module, for by described in first speech recognition result to error correction term replace with it is described to
The corresponding substitute of error correction term, obtains the second speech recognition result.
8. a kind of speech recognition error correction device according to claim 7, which is characterized in that further include:
Error correction information configuration module includes pair in the error correction configuring request for obtaining the error correction configuring request of the user
By the configuration-direct of error correction information, the configuration-direct includes at least one of addition instruction, modification instruction and deletion instruction；
If the configuration-direct includes the addition instruction, institute is added to by error correction information by corresponding with the addition instruction
It states in user's error correction library；
If the configuration-direct includes the modification instruction and/or deletes instruction, is instructed according to the modification and/or deletion refers to
It enables, to being performed corresponding processing accordingly by error correction information in the error correction library.
9. a kind of electronic equipment characterized by comprising
At least one processor；
And bus, at least one processor being connected to the processor；Wherein,
The processor, the memory complete mutual communication by the bus；
The processor is used to call the program instruction in the memory, any into claim 6 with perform claim requirement 1
Speech recognition error correction method described in.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Store up computer instruction, the computer instruction requires the computer perform claim 1 to described in any one of claim 6
Speech recognition error correction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811013550.1A CN109065054A (en) | 2018-08-31 | 2018-08-31 | Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811013550.1A CN109065054A (en) | 2018-08-31 | 2018-08-31 | Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109065054A true CN109065054A (en) | 2018-12-21 |
Family
ID=64759098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811013550.1A Pending CN109065054A (en) | 2018-08-31 | 2018-08-31 | Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109065054A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021293A (en) * | 2019-04-08 | 2019-07-16 | 上海汽车集团股份有限公司 | Audio recognition method and device, readable storage medium storing program for executing |
| CN110211577A (en) * | 2019-07-19 | 2019-09-06 | 宁波方太厨具有限公司 | Terminal device and its voice interactive method |
| CN110379214A (en) * | 2019-06-27 | 2019-10-25 | 武汉职业技术学院 | A kind of Picture writing training method and device based on speech recognition |
| CN110516248A (en) * | 2019-08-27 | 2019-11-29 | 出门问问(苏州)信息科技有限公司 | Method for correcting error of voice identification result, device, storage medium and electronic equipment |
| CN111128185A (en) * | 2019-12-25 | 2020-05-08 | 北京声智科技有限公司 | Method, device, terminal and storage medium for converting voice into characters |
| CN111462748A (en) * | 2019-01-22 | 2020-07-28 | 北京猎户星空科技有限公司 | Voice recognition processing method and device, electronic equipment and storage medium |
| CN111524517A (en) * | 2020-06-24 | 2020-08-11 | 深圳前海微众银行股份有限公司 | Voice recognition method, device, equipment and storage medium |
| CN112201248A (en) * | 2020-09-28 | 2021-01-08 | 杭州九阳小家电有限公司 | Streaming voice recognition method and system based on long connection |
| CN112331191A (en) * | 2021-01-07 | 2021-02-05 | 广州华源网络科技有限公司 | Voice recognition system and method based on big data |
| WO2021104102A1 (en) * | 2019-11-25 | 2021-06-03 | 科大讯飞股份有限公司 | Speech recognition error correction method, related devices, and readable storage medium |
| CN113012705A (en) * | 2021-02-24 | 2021-06-22 | 海信视像科技股份有限公司 | Error correction method and device for voice text |
| CN113053359A (en) * | 2019-12-27 | 2021-06-29 | 深圳Tcl数字技术有限公司 | Voice recognition method, intelligent terminal and storage medium |
| CN113158649A (en) * | 2021-05-27 | 2021-07-23 | 广州广电运通智能科技有限公司 | Error correction method, equipment, medium and product for subway station name recognition |
| CN113362817A (en) * | 2020-03-04 | 2021-09-07 | 株式会社东芝 | Speech recognition error correction device, speech recognition error correction method, and speech recognition error correction program |
| CN113674743A (en) * | 2021-08-20 | 2021-11-19 | 云知声（上海）智能科技有限公司 | ASR result replacement processing device and processing method used in natural language processing |
| US11264034B2 (en) | 2019-03-05 | 2022-03-01 | Baidu Online Network Technology (Beijing) Co., Ltd | Voice identification method, device, apparatus, and storage medium |
| KR20230040951A (en) * | 2020-05-18 | 2023-03-23 | 아이플라이텍 캄파니 리미티드 | Speech recognition method, apparatus and device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1399191A (en) * | 2002-09-09 | 2003-02-26 | 北京南山高科技有限公司 | Processing method for Chinese phonetic recognition word library |
| US20120117046A1 (en) * | 2010-11-08 | 2012-05-10 | Sony Corporation | Videolens media system for feature selection |
| EP3093775A1 (en) * | 2015-05-15 | 2016-11-16 | Baidu Online Network Technology Beijing Co., Ltd. | Method and apparatus for speech-based information push |
| CN107544726A (en) * | 2017-07-04 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Method for correcting error of voice identification result, device and storage medium based on artificial intelligence |
| CN107608963A (en) * | 2017-09-12 | 2018-01-19 | 马上消费金融股份有限公司 | A kind of Chinese error correction based on mutual information, device, equipment and storage medium |
| CN107679032A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Voice changes error correction method and device |
-
2018
- 2018-08-31 CN CN201811013550.1A patent/CN109065054A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1399191A (en) * | 2002-09-09 | 2003-02-26 | 北京南山高科技有限公司 | Processing method for Chinese phonetic recognition word library |
| US20120117046A1 (en) * | 2010-11-08 | 2012-05-10 | Sony Corporation | Videolens media system for feature selection |
| EP3093775A1 (en) * | 2015-05-15 | 2016-11-16 | Baidu Online Network Technology Beijing Co., Ltd. | Method and apparatus for speech-based information push |
| CN107544726A (en) * | 2017-07-04 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Method for correcting error of voice identification result, device and storage medium based on artificial intelligence |
| CN107679032A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Voice changes error correction method and device |
| CN107608963A (en) * | 2017-09-12 | 2018-01-19 | 马上消费金融股份有限公司 | A kind of Chinese error correction based on mutual information, device, equipment and storage medium |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462748B (en) * | 2019-01-22 | 2023-09-26 | 北京猎户星空科技有限公司 | Speech recognition processing method and device, electronic equipment and storage medium |
| CN111462748A (en) * | 2019-01-22 | 2020-07-28 | 北京猎户星空科技有限公司 | Voice recognition processing method and device, electronic equipment and storage medium |
| US11264034B2 (en) | 2019-03-05 | 2022-03-01 | Baidu Online Network Technology (Beijing) Co., Ltd | Voice identification method, device, apparatus, and storage medium |
| CN110021293A (en) * | 2019-04-08 | 2019-07-16 | 上海汽车集团股份有限公司 | Audio recognition method and device, readable storage medium storing program for executing |
| CN110379214A (en) * | 2019-06-27 | 2019-10-25 | 武汉职业技术学院 | A kind of Picture writing training method and device based on speech recognition |
| CN110211577A (en) * | 2019-07-19 | 2019-09-06 | 宁波方太厨具有限公司 | Terminal device and its voice interactive method |
| CN110211577B (en) * | 2019-07-19 | 2021-06-04 | 宁波方太厨具有限公司 | Terminal equipment and voice interaction method thereof |
| CN110516248A (en) * | 2019-08-27 | 2019-11-29 | 出门问问(苏州)信息科技有限公司 | Method for correcting error of voice identification result, device, storage medium and electronic equipment |
| KR102648306B1 (en) * | 2019-11-25 | 2024-03-15 | 아이플라이텍 캄파니 리미티드 | Speech recognition error correction method, related devices, and readable storage medium |
| WO2021104102A1 (en) * | 2019-11-25 | 2021-06-03 | 科大讯飞股份有限公司 | Speech recognition error correction method, related devices, and readable storage medium |
| EP4068280A4 (en) * | 2019-11-25 | 2023-11-01 | Iflytek Co., Ltd. | Speech recognition error correction method, related devices, and readable storage medium |
| KR20220035222A (en) * | 2019-11-25 | 2022-03-21 | 아이플라이텍 캄파니 리미티드 | Speech recognition error correction method, related devices, and readable storage medium |
| CN111128185B (en) * | 2019-12-25 | 2022-10-21 | 北京声智科技有限公司 | Method, device, terminal and storage medium for converting voice into characters |
| CN111128185A (en) * | 2019-12-25 | 2020-05-08 | 北京声智科技有限公司 | Method, device, terminal and storage medium for converting voice into characters |
| CN113053359A (en) * | 2019-12-27 | 2021-06-29 | 深圳Tcl数字技术有限公司 | Voice recognition method, intelligent terminal and storage medium |
| CN113362817A (en) * | 2020-03-04 | 2021-09-07 | 株式会社东芝 | Speech recognition error correction device, speech recognition error correction method, and speech recognition error correction program |
| KR20230040951A (en) * | 2020-05-18 | 2023-03-23 | 아이플라이텍 캄파니 리미티드 | Speech recognition method, apparatus and device, and storage medium |
| KR102668530B1 (en) | 2020-05-18 | 2024-05-24 | 아이플라이텍 캄파니 리미티드 | Speech recognition methods, devices and devices, and storage media |
| CN111524517B (en) * | 2020-06-24 | 2023-11-03 | 深圳前海微众银行股份有限公司 | Speech recognition method, device, equipment and storage medium |
| CN111524517A (en) * | 2020-06-24 | 2020-08-11 | 深圳前海微众银行股份有限公司 | Voice recognition method, device, equipment and storage medium |
| CN112201248A (en) * | 2020-09-28 | 2021-01-08 | 杭州九阳小家电有限公司 | Streaming voice recognition method and system based on long connection |
| CN112201248B (en) * | 2020-09-28 | 2024-01-05 | 杭州九阳小家电有限公司 | Stream type voice recognition method and system based on long connection |
| CN112331191A (en) * | 2021-01-07 | 2021-02-05 | 广州华源网络科技有限公司 | Voice recognition system and method based on big data |
| CN113012705A (en) * | 2021-02-24 | 2021-06-22 | 海信视像科技股份有限公司 | Error correction method and device for voice text |
| CN113012705B (en) * | 2021-02-24 | 2022-12-09 | 海信视像科技股份有限公司 | Error correction method and device for voice text |
| CN113158649A (en) * | 2021-05-27 | 2021-07-23 | 广州广电运通智能科技有限公司 | Error correction method, equipment, medium and product for subway station name recognition |
| CN113674743A (en) * | 2021-08-20 | 2021-11-19 | 云知声（上海）智能科技有限公司 | ASR result replacement processing device and processing method used in natural language processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109065054A (en) | Speech recognition error correction method, device, electronic equipment and readable storage medium storing program for executing | |
| CN107437416A (en) | A kind of consultation service processing method and processing device based on speech recognition | |
| US10656907B2 (en) | Translation of natural language into user interface actions | |
| CN110442330A (en) | List element conversion method, device, electronic equipment and storage medium | |
| CN107038041A (en) | The dynamic compatibility method of data processing method, error code, device and system | |
| CN109036424A (en) | Audio recognition method, device, electronic equipment and computer readable storage medium | |
| CN105678625A (en) | Method and equipment for determining identity information of user | |
| CN105678129A (en) | Method and device for determining user identity information | |
| CN108804100A (en) | Create method, apparatus, storage medium and the mobile terminal of interface element | |
| CN112735407A (en) | Conversation processing method and device | |
| CN116894188A (en) | Service tag set updating method and device, medium and electronic equipment | |
| US20200250279A1 (en) | Performing multi-objective tasks via primal networks trained with dual networks | |
| CN113408254A (en) | Page form information filling method, device, equipment and readable medium | |
| JP7182584B2 (en) | A method for outputting information of parsing anomalies in speech comprehension | |
| CN108942925A (en) | The control method and device of robot | |
| US20190121649A1 (en) | User interface metadata from an application program interface | |
| CN107547607B (en) | Cluster migration method and device | |
| CN114968917A (en) | Method and device for rapidly importing file data | |
| CN108804088A (en) | Protocol processes method and apparatus | |
| CN107704502A (en) | A kind of method for routing, device, equipment and system | |
| CN110968334B (en) | Application resource updating method, resource package manufacturing method, device, medium and equipment | |
| CN110704742B (en) | Feature extraction method and device | |
| US11132408B2 (en) | Knowledge-graph based question correction | |
| CN111582482B (en) | Method, apparatus, device and medium for generating network model information | |
| CN116467178B (en) | Database detection method, apparatus, electronic device and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |