CN106601236A - Speech recognition method and apparatus - Google Patents
Speech recognition method and apparatus Download PDFInfo
- Publication number
- CN106601236A CN106601236A CN201611201707.4A CN201611201707A CN106601236A CN 106601236 A CN106601236 A CN 106601236A CN 201611201707 A CN201611201707 A CN 201611201707A CN 106601236 A CN106601236 A CN 106601236A
- Authority
- CN
- China
- Prior art keywords
- default
- target
- clause name
- text template
- set text
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
Abstract
The invention provides a speech recognition method and apparatus wherein the method comprises: in the process of using a preset speech recognition model to identify the speech information inputted by a user and filling the recognition result in a preset text template, receiving the chosen instruction of the key words in the preset speech template inputted by the user; according to the key words corresponding to the chosen instruction, updating the preset speech recognition model; using the updated preset speech recognition model to identify the speech information inputted by the user. Through the technical schemes of the invention, it is possible for the user to update the preset speech recognition model more conveniently so as to ensure the success rate of speech recognition.
Description
Technical field
The present invention relates to technical field of voice recognition, more particularly to a kind of audio recognition method and device.
Background technology
In correlation technique, when user is when the forms such as case are filled in, need to be filled in manually, i.e., user is by being input into text
The mode of word is filled in, and so, user operation is loaded down with trivial details, is experienced not good.
The content of the invention
The embodiment of the present invention provides a kind of audio recognition method and device, to realize that user can pass through phonetic entry
Mode fills in case form etc., reduces the operation of user, so as to lift the experience of user.
A kind of first aspect according to embodiments of the present invention, there is provided audio recognition method, including：
The voice messaging of user input is identified using default speech recognition modeling and by recognition result fill in
During pre-set text template, receiving user's input chooses order to target keyword in the pre-set text template；
The corresponding target keyword of order is chosen according to described, the default speech recognition modeling is updated；
Default speech recognition modeling after using renewal is identified to the voice messaging of user input.
In this embodiment it is possible to be identified to the voice messaging of user input by default speech recognition modeling, enter
And recognition result is filled in into pre-set text template, but, in identification process, if default speech recognition modeling can not
The voice messaging of identifying user input, that is, do not include key word of user input etc. in presetting speech recognition modeling, then user can
So that the key word is manually entered in pre-set text template, and then the key word is chosen, thus the key word can be added
Into default speech recognition modeling, such user next time again the phonetic entry key word when, it is possible to known by default voice
Other Model Identification goes out the key word.By the technical scheme, it is easy to user to update default speech recognition modeling, so as to ensure voice
The success rate of identification.
In one embodiment, the voice messaging includes clause name and the corresponding entry contents of the clause name,
The pre-set text template includes default clause name and entry space corresponding with the default clause name, described using pre-
If speech recognition modeling is identified to the voice messaging of user input and recognition result is filled in pre-set text template, bag
Include：
The voice messaging of user input is identified using default speech recognition modeling, obtains the clause name correspondence
The first word content and corresponding second word content of the entry contents；
The default bar of the target matched with first word content is searched in the default clause name of pre-set text template
Mesh title；
When the default clause name of the target is found, second word content is filled in the pre-set text mould
In the default corresponding target entry space of clause name of target described in plate.
In this embodiment, the default bar in the corresponding clause name of voice messaging that will identify that and pre-set text template
Mesh title is matched, if finding default clause name corresponding with clause name, by clause name corresponding entry
Content is filled up in the corresponding target entry space of default clause name, so as to realize Auto-writing pre-set text template.
Wherein, if finding default clause name corresponding with clause name, illustrate by default speech recognition mould
The corresponding recognition result of voice messaging that type is obtained is correct, if searched less than default entry name corresponding with clause name
Claim, then illustrate incorrect by presetting the corresponding recognition result of voice messaging that obtains of speech recognition modeling, or by default
Speech recognition modeling cannot recognize that the voice messaging.
In one embodiment, the pre-set text template includes case template.
In this embodiment, pre-set text template can be case template, it is of course also possible to be other templates.If pre-
If text template is case template, then presetting clause name can include symptom, medical history, allergies, prescription etc., and corresponding
Entry contents include medical data language material, such as nomenclature of drug, symptom of various diseases etc..So, doctor is when actually used,
Need not be manually entered, it is only necessary to input voice information, just the corresponding Word message of voice messaging that doctor is input into can be filled in
To in the space of corresponding bar code title.
In one embodiment, methods described also includes：
When the default clause name of the target is not found, information is exported, the information is used to point out to use
Family does not find the content matched with the voice messaging in pre-set text template.
In this embodiment, if the default clause name of target is not found in pre-set text template, illustrate to pass through
The corresponding recognition result of voice messaging that default speech recognition modeling is obtained is incorrect, or by default speech recognition modeling not
The voice messaging is can recognize that, at this point it is possible to information is exported, so as to point out user not find in pre-set text template
The content matched with the voice messaging, is facilitated user to choose key word, and then updates default speech recognition modeling.
In one embodiment, it is described search in the default clause name of pre-set text template with first word
Hold the default clause name of target of matching, including：
Obtain in the pre-set text template, the position that current cursor is located；
In the corresponding preset range in position that current cursor is located, the target matched with first word content is searched
Default clause name；
The default clause name of the target is not found in the preset range, institute is removed in the pre-set text template
State outside preset range other in the range of search the default clause name of the target.
In this embodiment, search in the default clause name of pre-set text template and match with first word content
Target default clause name when, the position that current cursor in pre-set text template is located can be obtained, and then near cursor
The default clause name of target is searched, as such, it is possible to find the default clause name of target as early as possible, the lookup time is reduced.
A kind of second aspect according to embodiments of the present invention, there is provided speech recognition equipment, including：
Receiver module, for being identified to the voice messaging of user input using default speech recognition modeling and will known
During other result is filled in pre-set text template, receiving user's input to target keyword in the pre-set text template
Choose order；
Update module, for choosing the corresponding target keyword of order according to described, updates the default voice and knows
Other model；
First identification module, is carried out to the voice messaging of user input for the default speech recognition modeling after using renewal
Identification.
In one embodiment, the voice messaging includes clause name and the corresponding entry contents of the clause name,
The pre-set text template includes default clause name and entry space corresponding with the default clause name, and described device is also
Including：
Second identification module, for using default speech recognition modeling to be identified the voice messaging of user input, obtains
To corresponding first word content of the clause name and corresponding second word content of the entry contents；
Searching modul, is matched with first word content for searching in the default clause name of pre-set text template
The default clause name of target；
Fill in module, for when the default clause name of the target is found, by second word content fill in
In the default corresponding target entry space of clause name of target described in the pre-set text template.
In one embodiment, described device also includes：
Reminding module, for when the default clause name of the target is not found, exporting information, the prompting letter
Cease for pointing out user that the content matched with the voice messaging is not found in pre-set text template.
In one embodiment, the searching modul includes：
Acquisition submodule, for obtaining in the pre-set text template, the position that current cursor is located；
First searches submodule, in the corresponding preset range in the position for being located in current cursor, searches and described the
The default clause name of target of one word content matching；
Second searches submodule, for the default clause name of the target is not found in the preset range, in institute
State in pre-set text template in addition to the preset range other in the range of search the default clause name of the target.
In one embodiment, the pre-set text template includes case template.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Other features and advantages of the present invention will be illustrated in the following description, also, partly be become from description
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
In book, claims and accompanying drawing, specifically noted structure is realizing and obtain.
Below by drawings and Examples, technical scheme is described in further detail.
Description of the drawings
During accompanying drawing herein is merged in description and the part of this specification is constituted, show the enforcement for meeting the present invention
Example, and be used for explaining the principle of the present invention together with description.
Fig. 1 is a kind of flow chart of the audio recognition method according to an exemplary embodiment.
Fig. 2 is the flow chart of another kind of audio recognition method according to an exemplary embodiment.
Fig. 3 is the flow chart of another audio recognition method according to an exemplary embodiment.
Fig. 4 is the flow chart of another audio recognition method according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of the speech recognition equipment according to an exemplary embodiment.
Fig. 6 is the block diagram of another kind of speech recognition equipment according to an exemplary embodiment.
Fig. 7 is the block diagram of another speech recognition equipment according to an exemplary embodiment.
Fig. 8 is the block diagram of searching modul in another speech recognition equipment according to an exemplary embodiment.
Specific embodiment
Here in detail exemplary embodiment will be illustrated, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.Conversely, they be only with as appended by
The example of consistent apparatus and method in terms of some described in detail in claims, the present invention.
Fig. 1 is a kind of flow chart of the audio recognition method according to an exemplary embodiment.The audio recognition method
It is applied in terminal unit, the terminal unit can be mobile phone, and computer, digital broadcast terminal, messaging devices are swum
Arbitrary equipment with voice control function such as play control station, tablet device, armarium, body-building equipment, personal digital assistant.
As shown in figure 1, the method comprising the steps of S101-S103：
In step S101, the voice messaging of user input is being identified using default speech recognition modeling and will known
During other result is filled in pre-set text template, the choosing to target keyword in pre-set text template of receiving user's input
Middle order；
In step s 102, according to the corresponding target keyword of order is chosen, update default speech recognition modeling；
In step s 103, using renewal after default speech recognition modeling the voice messaging of user input is known
Not.
In this embodiment it is possible to be identified to the voice messaging of user input by default speech recognition modeling, enter
And recognition result is filled in into pre-set text template, but, in identification process, if default speech recognition modeling can not
The voice messaging of identifying user input, that is, do not include key word of user input etc. in presetting speech recognition modeling, then user can
So that the key word is manually entered in pre-set text template, and then the key word is chosen, thus the key word can be added
Into default speech recognition modeling, such user next time again the phonetic entry key word when, it is possible to known by default voice
Other Model Identification goes out the key word.By the technical scheme, it is easy to user to update default speech recognition modeling, so as to ensure voice
The success rate of identification.
Fig. 2 is the flow chart of another kind of audio recognition method according to an exemplary embodiment.
As shown in Fig. 2 in one embodiment, voice messaging is included in clause name and the corresponding entry of clause name
Hold, pre-set text template includes default clause name and entry space corresponding with default clause name, known using default voice
Other model is identified to the voice messaging of user input and recognition result is filled in pre-set text template, including step
S201-S203：
In step s 201, the voice messaging of user input is identified using default speech recognition modeling, obtains bar
Corresponding first word content of mesh title and corresponding second word content of entry contents；
In step S202, the mesh matched with the first word content is searched in the default clause name of pre-set text template
The default clause name of mark；
In step S203, when the default clause name of target is found, the second word content is filled in pre-set text
In template in the default corresponding target entry space of clause name of target.
In this embodiment, the default bar in the corresponding clause name of voice messaging that will identify that and pre-set text template
Mesh title is matched, if finding default clause name corresponding with clause name, by clause name corresponding entry
Content is filled up in the corresponding target entry space of default clause name, so as to realize Auto-writing pre-set text template.
Wherein, if finding default clause name corresponding with clause name, illustrate by default speech recognition mould
The corresponding recognition result of voice messaging that type is obtained is correct, if searched less than default entry name corresponding with clause name
Claim, then illustrate incorrect by presetting the corresponding recognition result of voice messaging that obtains of speech recognition modeling, or by default
Speech recognition modeling cannot recognize that the voice messaging.
In one embodiment, pre-set text template includes case template.
In this embodiment, pre-set text template can be case template, it is of course also possible to be other templates.If pre-
If text template is case template, then presetting clause name can include symptom, medical history, allergies, prescription etc., and corresponding
Entry contents include medical data language material, such as nomenclature of drug, symptom of various diseases etc..So, doctor is when actually used,
Need not be manually entered, it is only necessary to input voice information, just the corresponding Word message of voice messaging that doctor is input into can be filled in
To in the space of corresponding bar code title.
Fig. 3 is the flow chart of another audio recognition method according to an exemplary embodiment.
As shown in figure 3, in one embodiment, said method also includes step S301：
In step S301, when the default clause name of target is not found, information is exported, information is used to carry
Show that user does not find the content matched with voice messaging in pre-set text template.
In this embodiment, if the default clause name of target is not found in pre-set text template, illustrate to pass through
The corresponding recognition result of voice messaging that default speech recognition modeling is obtained is incorrect, or by default speech recognition modeling not
The voice messaging is can recognize that, at this point it is possible to information is exported, so as to point out user not find in pre-set text template
The content matched with voice messaging, is facilitated user to choose key word, and then updates default speech recognition modeling.
Fig. 4 is the flow chart of another audio recognition method according to an exemplary embodiment.
As shown in figure 4, in one embodiment, above-mentioned steps S202 include step S401-S403：
In step S401, obtain in pre-set text template, the position that current cursor is located；
In step S402, in the corresponding preset range in position that current cursor is located, search and the first word content
The default clause name of the target of matching；
In step S403, the default clause name of target is not found in preset range, is removed in pre-set text template
The default clause name of target is searched in the range of other outside preset range.
In this embodiment, the mesh that lookup is matched with the first word content in the default clause name of pre-set text template
The position at current cursor place in pre-set text template when mark presets clause name, can be obtained, and then is searched near cursor
Target presets clause name, as such, it is possible to find the default clause name of target as early as possible, reduces the lookup time.
It is following for apparatus of the present invention embodiment, can be used for performing the inventive method embodiment.
Fig. 5 is a kind of block diagram of the speech recognition equipment according to an exemplary embodiment, and the device can pass through soft
Being implemented in combination with of part, hardware or both becomes some or all of of terminal unit.As shown in figure 5, the speech recognition equipment
Including：
Receiver module 51, for being identified to the voice messaging of user input using default speech recognition modeling and being incited somebody to action
During recognition result is filled in pre-set text template, receiving user's input to target critical in the pre-set text template
Word chooses order；
Update module 52, for choosing the corresponding target keyword of order according to described, updates the default voice
Identification model；
First identification module 53, enters to the voice messaging of user input for the default speech recognition modeling after using renewal
Row identification.
In this embodiment it is possible to be identified to the voice messaging of user input by default speech recognition modeling, enter
And recognition result is filled in into pre-set text template, but, in identification process, if default speech recognition modeling can not
The voice messaging of identifying user input, that is, do not include key word of user input etc. in presetting speech recognition modeling, then user can
So that the key word is manually entered in pre-set text template, and then the key word is chosen, thus the key word can be added
Into default speech recognition modeling, such user next time again the phonetic entry key word when, it is possible to known by default voice
Other Model Identification goes out the key word.By the technical scheme, it is easy to user to update default speech recognition modeling, so as to ensure voice
The success rate of identification.
Fig. 6 is the block diagram of another kind of speech recognition equipment according to an exemplary embodiment.
As shown in fig. 6, in one embodiment, the voice messaging includes that clause name and the clause name are corresponding
Entry contents, the pre-set text template include default clause name and entry space corresponding with the default clause name,
Said apparatus also include：
Second identification module 61, for using default speech recognition modeling to be identified the voice messaging of user input,
Obtain corresponding first word content of the clause name and corresponding second word content of the entry contents；
Searching modul 62, for searching in the default clause name of pre-set text template and first word content
The default clause name of target matched somebody with somebody；
Module 63 is filled in, for when the default clause name of the target is found, second word content being filled in
To the default corresponding target entry space of clause name of target described in the pre-set text template.
In this embodiment, the default bar in the corresponding clause name of voice messaging that will identify that and pre-set text template
Mesh title is matched, if finding default clause name corresponding with clause name, by clause name corresponding entry
Content is filled up in the corresponding target entry space of default clause name, so as to realize Auto-writing pre-set text template.
Wherein, if finding default clause name corresponding with clause name, illustrate by default speech recognition mould
The corresponding recognition result of voice messaging that type is obtained is correct, if searched less than default entry name corresponding with clause name
Claim, then illustrate incorrect by presetting the corresponding recognition result of voice messaging that obtains of speech recognition modeling, or by default
Speech recognition modeling cannot recognize that the voice messaging.
In one embodiment, the pre-set text template includes case template.
In this embodiment, pre-set text template can be case template, it is of course also possible to be other templates.If pre-
If text template is case template, then presetting clause name can include symptom, medical history, allergies, prescription etc., and corresponding
Entry contents include medical data language material, such as nomenclature of drug, symptom of various diseases etc..So, doctor is when actually used,
Need not be manually entered, it is only necessary to input voice information, just the corresponding Word message of voice messaging that doctor is input into can be filled in
To in the space of corresponding bar code title.
Fig. 7 is the block diagram of another speech recognition equipment according to an exemplary embodiment.
As shown in fig. 7, in one embodiment, said apparatus also include：
Reminding module 71, for when the default clause name of the target is not found, exporting information, the prompting
Information is used to point out user that the content matched with the voice messaging is not found in pre-set text template.
In this embodiment, if the default clause name of target is not found in pre-set text template, illustrate to pass through
The corresponding recognition result of voice messaging that default speech recognition modeling is obtained is incorrect, or by default speech recognition modeling not
The voice messaging is can recognize that, at this point it is possible to information is exported, so as to point out user not find in pre-set text template
The content matched with the voice messaging, is facilitated user to choose key word, and then updates default speech recognition modeling.
Fig. 8 is the block diagram of searching modul in another speech recognition equipment according to an exemplary embodiment.
As shown in figure 8, in one embodiment, the searching modul 62 includes：
Acquisition submodule 81, for obtaining in the pre-set text template, the position that current cursor is located；
First search submodule 82, in the corresponding preset range in the position for being located in current cursor, search with it is described
The default clause name of target of the first word content matching；
Second searches submodule 83, for the default clause name of the target is not found in the preset range,
The default clause name of the target is searched in the range of other in the pre-set text template in addition to the preset range.
In this embodiment, search in the default clause name of pre-set text template and match with first word content
Target default clause name when, the position that current cursor in pre-set text template is located can be obtained, and then near cursor
The default clause name of target is searched, as such, it is possible to find the default clause name of target as early as possible, the lookup time is reduced.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can adopt complete hardware embodiment, complete software embodiment or with reference to the reality in terms of software and hardware
Apply the form of example.And, the present invention can be using the computer for wherein including computer usable program code at one or more
The shape of the computer program implemented in usable storage medium (including but not limited to disk memory and optical memory etc.)
Formula.
The present invention be with reference to method according to embodiments of the present invention, equipment (system), and computer program flow process
Figure and/or block diagram are describing.It should be understood that can be by computer program instructions flowchart and/or each stream in block diagram
The combination of journey and/or square frame and flow chart and/or flow process and/or square frame in block diagram.These computer programs can be provided
The processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of specifying in present one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory is produced to be included referring to
Make the manufacture of device, the command device realize in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or
The function of specifying in multiple square frames.
These computer program instructions can be also loaded in computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented process, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow process of flow chart or multiple flow processs and/or block diagram one
The step of function of specifying in individual square frame or multiple square frames.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of audio recognition method, it is characterised in that include：
The voice messaging of user input is being identified using default speech recognition modeling and recognition result is being filled in default
During text template, receiving user's input chooses order to target keyword in the pre-set text template；
The corresponding target keyword of order is chosen according to described, the default speech recognition modeling is updated；
Default speech recognition modeling after using renewal is identified to the voice messaging of user input.
2. method according to claim 1, it is characterised in that the voice messaging includes clause name and the entry name
Claim corresponding entry contents, the pre-set text template includes default clause name and bar corresponding with the default clause name
Mesh space, it is described the voice messaging of user input is identified using default speech recognition modeling and by recognition result fill in
Pre-set text template, including：
The voice messaging of user input is identified using default speech recognition modeling, obtains the clause name corresponding
One word content and corresponding second word content of the entry contents；
The default entry name of the target matched with first word content is searched in the default clause name of pre-set text template
Claim；
When the default clause name of the target is found, second word content is filled in into the pre-set text template
In the default corresponding target entry space of clause name of the target.
3. method according to claim 2, it is characterised in that methods described also includes：
When the default clause name of the target is not found, information is exported, the information is used to point out user to exist
The content matched with the voice messaging is not found in pre-set text template.
4. method according to claim 2, it is characterised in that described to look in the default clause name of pre-set text template
The default clause name of the target matched with first word content is looked for, including：
Obtain in the pre-set text template, the position that current cursor is located；
In the corresponding preset range in position that current cursor is located, search the target matched with first word content and preset
Clause name；
The default clause name of the target is not found in the preset range, except described pre- in the pre-set text template
If the default clause name of the target is searched in the range of other outside scope.
5. method according to any one of claim 1 to 4, it is characterised in that the pre-set text template includes case
Template.
6. a kind of speech recognition equipment, it is characterised in that include：
Receiver module, for being identified to the voice messaging of user input using default speech recognition modeling and knot being recognized
During fruit is filled in pre-set text template, the choosing to target keyword in the pre-set text template of receiving user's input
Middle order；
Update module, for choosing the corresponding target keyword of order according to described, updates the default speech recognition mould
Type；
First identification module, knows to the voice messaging of user input for the default speech recognition modeling after using renewal
Not.
7. device according to claim 6, it is characterised in that the voice messaging includes clause name and the entry name
Claim corresponding entry contents, the pre-set text template includes default clause name and bar corresponding with the default clause name
Mesh space, described device also include：
Second identification module, for using default speech recognition modeling to be identified the voice messaging of user input, obtains institute
State corresponding first word content of clause name and corresponding second word content of the entry contents；
Searching modul, for the mesh matched with first word content is searched in the default clause name of pre-set text template
The default clause name of mark；
Module is filled in, for when the default clause name of the target is found, second word content is filled in described
In the default corresponding target entry space of clause name of target described in pre-set text template.
8. device according to claim 7, it is characterised in that described device also includes：
Reminding module, for when the default clause name of the target is not found, exporting information, the information is used
The content matched with the voice messaging is not found in prompting user in pre-set text template.
9. device according to claim 7, it is characterised in that the searching modul includes：
Acquisition submodule, for obtaining in the pre-set text template, the position that current cursor is located；
First searches submodule, in the corresponding preset range in the position for being located in current cursor, searches literary with described first
The default clause name of the target of word content matching；
Second searches submodule, for the default clause name of the target is not found in the preset range, described pre-
If the default clause name of the target is searched in the range of other in text template in addition to the preset range.
10. the device according to any one of claim 6 to 9, it is characterised in that the pre-set text template includes case
Template.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611201707.4A CN106601236A (en) | 2016-12-22 | 2016-12-22 | Speech recognition method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611201707.4A CN106601236A (en) | 2016-12-22 | 2016-12-22 | Speech recognition method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106601236A true CN106601236A (en) | 2017-04-26 |
Family
ID=58602874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611201707.4A Pending CN106601236A (en) | 2016-12-22 | 2016-12-22 | Speech recognition method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106601236A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107342086A (en) * | 2017-06-16 | 2017-11-10 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN108573754A (en) * | 2017-11-29 | 2018-09-25 | 北京金山云网络技术有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN109003648A (en) * | 2018-06-29 | 2018-12-14 | 北京大学口腔医学院 | Outpatient Service Stomatology speech electronic case history generation method and computer readable storage medium |
| CN109360571A (en) * | 2018-10-31 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Processing method and processing device, storage medium, the computer equipment of credit information |
| CN110210014A (en) * | 2019-05-31 | 2019-09-06 | 贵州精准医疗电子有限公司 | Intelligent form system |
| CN110858479A (en) * | 2018-08-08 | 2020-03-03 | Oppo广东移动通信有限公司 | Voice recognition model updating method and device, storage medium and electronic equipment |
| CN112650916A (en) * | 2019-10-12 | 2021-04-13 | 青岛海信移动通信技术股份有限公司 | Communication terminal and information query method |
| CN113157964A (en) * | 2021-03-10 | 2021-07-23 | 深圳市明源云科技有限公司 | Method and device for searching data set through voice and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325465A1 (en) * | 2011-11-23 | 2013-12-05 | Advanced Medical Imaging and Teleradiology, LLC | Medical image reading system |
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN105786797A (en) * | 2016-02-23 | 2016-07-20 | 北京云知声信息技术有限公司 | Information processing method and device based on voice input |
| CN105931644A (en) * | 2016-04-15 | 2016-09-07 | 广东欧珀移动通信有限公司 | Voice recognition method and mobile terminal |
-
2016
- 2016-12-22 CN CN201611201707.4A patent/CN106601236A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325465A1 (en) * | 2011-11-23 | 2013-12-05 | Advanced Medical Imaging and Teleradiology, LLC | Medical image reading system |
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN105786797A (en) * | 2016-02-23 | 2016-07-20 | 北京云知声信息技术有限公司 | Information processing method and device based on voice input |
| CN105931644A (en) * | 2016-04-15 | 2016-09-07 | 广东欧珀移动通信有限公司 | Voice recognition method and mobile terminal |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107342086A (en) * | 2017-06-16 | 2017-11-10 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN108573754A (en) * | 2017-11-29 | 2018-09-25 | 北京金山云网络技术有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN109003648A (en) * | 2018-06-29 | 2018-12-14 | 北京大学口腔医学院 | Outpatient Service Stomatology speech electronic case history generation method and computer readable storage medium |
| CN109003648B (en) * | 2018-06-29 | 2022-03-08 | 北京大学口腔医学院 | Oral outpatient speech electronic medical record generation method and computer readable storage medium |
| CN110858479A (en) * | 2018-08-08 | 2020-03-03 | Oppo广东移动通信有限公司 | Voice recognition model updating method and device, storage medium and electronic equipment |
| CN110858479B (en) * | 2018-08-08 | 2022-04-22 | Oppo广东移动通信有限公司 | Voice recognition model updating method and device, storage medium and electronic equipment |
| US11423880B2 (en) | 2018-08-08 | 2022-08-23 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for updating a speech recognition model, electronic device and storage medium |
| CN109360571A (en) * | 2018-10-31 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Processing method and processing device, storage medium, the computer equipment of credit information |
| CN110210014A (en) * | 2019-05-31 | 2019-09-06 | 贵州精准医疗电子有限公司 | Intelligent form system |
| CN110210014B (en) * | 2019-05-31 | 2023-05-30 | 贵州精准医疗电子有限公司 | Intelligent form system |
| CN112650916A (en) * | 2019-10-12 | 2021-04-13 | 青岛海信移动通信技术股份有限公司 | Communication terminal and information query method |
| CN113157964A (en) * | 2021-03-10 | 2021-07-23 | 深圳市明源云科技有限公司 | Method and device for searching data set through voice and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106601236A (en) | Speech recognition method and apparatus | |
| CN106649694A (en) | Method and device for identifying user's intention in voice interaction | |
| CN105786797B (en) | A kind of information processing method and device based on voice input | |
| EP2523188A1 (en) | Speech recognition system and method based on word-level candidate generation | |
| CN108242235A (en) | Electronic equipment and its audio recognition method | |
| CN111261144A (en) | Voice recognition method, device, terminal and storage medium | |
| CN105094798A (en) | Haptic design authoring tool | |
| CN105283868A (en) | Probabilistic parsing | |
| CN108519998B (en) | Problem guiding method and device based on knowledge graph | |
| CN106328145A (en) | Voice correction method and voice correction device | |
| CN110175223A (en) | A kind of method and device that problem of implementation generates | |
| CN107608532A (en) | A kind of association-feeding method, device and electronic equipment | |
| CN106649696A (en) | Information classification method and device | |
| CN109256125B (en) | Off-line voice recognition method and device and storage medium | |
| JP6180470B2 (en) | Sentence candidate presentation terminal, sentence candidate presentation system, sentence candidate presentation method, and program | |
| CN107832035B (en) | Voice input method of intelligent terminal | |
| CN106649746A (en) | Answer acquisition method and device | |
| CN106649238A (en) | Voice transferring method and device | |
| CN107609047A (en) | Using recommendation method, apparatus, mobile device and storage medium | |
| EP4174714A1 (en) | Text sequence generation method, apparatus and device, and medium | |
| CN108255939A (en) | A kind of cross-language search method and apparatus, a kind of device for cross-language search | |
| CN103488669A (en) | Information processing apparatus, information processing method and program | |
| CN106886294B (en) | Input method error correction method and device | |
| CN105164669A (en) | Information processing apparatus, information processing method, and program | |
| CN114334007A (en) | Gene off-target prediction model training method, prediction method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |