CN109559744A - Processing method, device and the readable storage medium storing program for executing of voice data - Google Patents
Processing method, device and the readable storage medium storing program for executing of voice data Download PDFInfo
- Publication number
- CN109559744A CN109559744A CN201811517309.2A CN201811517309A CN109559744A CN 109559744 A CN109559744 A CN 109559744A CN 201811517309 A CN201811517309 A CN 201811517309A CN 109559744 A CN109559744 A CN 109559744A
- Authority
- CN
- China
- Prior art keywords
- voice data
- voice
- processed
- packet
- language identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
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)
- Telephonic Communication Services (AREA)
Abstract
The processing method of voice data provided by the invention, device and readable storage medium storing program for executing, receive voice data to be processed, speech recognition is carried out to the voice data to be processed, with the corresponding voice key word information of the determination voice data, according to the voice key word information, determine that the language identification of type corresponding with the voice data to be processed supports packet, packet is supported to convert the voice data to be processed according to the determining language identification, obtain treated voice conversion data, the voice key word information of voice data to be processed is obtained by filtering, and support packet is selected to support to wrap with the most matched language identification of voice data to be processed from different types of language identification according to voice key word information, to support packet to handle voice data to be processed using the language identification, the letter of its process It is single, it is conducive to use.
Description
Technical field
The present invention relates to computer technology more particularly to a kind of processing methods of voice data, device and readable storage medium
Matter.
Background technique
With the development of electronic technology, development trend is become using paperless office, is handled official business by way of voice
It is one such mode.
It also needs to identify voice by the way of voice office, and due to the demand of different business, identify institute
The language used supports the type of packet also different.In the prior art, user needs the voice phase for selecting to input with oneself
After matched language supports packet, corresponding voice could be inputted, so that service platform supports packet to language according to the language of the selection
Sound is handled.
The processing mode process of such voice data is cumbersome, be extremely unfavorable for using.
Summary of the invention
It is corresponding for the above-mentioned content selection for needing the voice for inputting based on oneself in the prior art referred to
Language support packet after, could start voice input operation, process flow is cumbersome, be unfavorable for using the problem of, the present invention mentions
Processing method, device and the readable storage medium storing program for executing of a kind of voice data are supplied.
On the one hand, the present invention provides a kind of processing methods of voice data, comprising:
Receive voice data to be processed；
Speech recognition is carried out to the voice data to be processed, with the corresponding voice keyword of the determination voice data
Information；
According to the voice key word information, the language identification of type corresponding with the voice data to be processed is determined
Support packet；
Packet is supported to convert the voice data to be processed according to the determining language identification, after being handled
Voice conversion data.
It is described according to the voice key word information in a kind of wherein optional embodiment, it determines with described wait locate
The language identification of the corresponding type of the voice data of reason supports packet, comprising:
It supports to select and believe with voice keyword in packet in all types of language identifications using preset NB Algorithm
It ceases the highest language identification of matching degree and supports packet, the language identification as the voice data to be processed supports packet.
In a kind of wherein optional embodiment, it is described using preset NB Algorithm in all types of language
Identification is supported in packet, is selected and is supported to wrap with the highest language identification of voice key word information matching degree, as described to be processed
The language identification of voice data supports packet, comprising:
Determine that each keyword belongs to all types of language knowledges in voice key word information according to preset keyword vector table
The probability of packet is not supported；
Belong to the probability that all types of language identification supports packet according to keyword each in voice key word information, determine described in
Voice data to be processed belongs to all types of language identifications and supports the probability of packet, and it is described wait locate to select the highest conduct of probability
The language identification of the voice data of reason supports packet.
It is described that speech recognition is carried out to the voice data to be processed in a kind of wherein optional embodiment, with
Determine the corresponding voice key word information of the voice data, comprising:
The voice data is filtered according to the vocabulary packet prestored, determines the pass in the voice data to be processed
Keyword；
Determine profession belonging to the quantity of the different keywords occurred in the voice data to be processed, each keyword
Type, each keyword are at least one of the frequency of occurrence in the voice data, weighted value shared by each keyword；
Correspondingly, it is described according to the voice key word information, determine class corresponding with the voice data to be processed
The language identification of type supports packet, comprising: according to the quantity of the different keywords occurred in the voice data to be processed, each
Many types belonging to keyword, each keyword are in the frequency of occurrence in the voice data, weighted value shared by each keyword
At least one of, determine that the language identification of type corresponding with the voice data to be processed supports packet.
In a kind of wherein optional embodiment, the language identification supports that the type of packet includes: Medical Language identification
Support packet, customer service language identification that packet and meeting language identification is supported to support packet.
In a kind of wherein optional embodiment, it is described obtain treated voice conversion data after, the method
Further include:
The voice data to be processed and corresponding voice conversion process are associated storage.
It is described to receive voice data to be processed in a kind of wherein optional embodiment, comprising:
The interface of service platform is called, the voice number to be processed for being uploaded to the service platform from each client is received
According to.
On the other hand, the present invention provides a kind of processing units of voice data, comprising:
Receiving module, for receiving voice data to be processed；
Identification module, for carrying out speech recognition to the voice data to be processed, with the determination voice data pair
The voice key word information answered；
Language pack conversion module, for according to the voice key word information, the determining and voice data to be processed
The language identification of corresponding type supports packet；It is also used to support packet to the language to be processed according to the determining language identification
Sound data are converted, and treated voice conversion data is obtained.
In another aspect, the present invention provides a kind of electronic equipment, comprising: memory, the processing being connect with the memory
Device, and it is stored in the computer program that can be run on the memory and on the processor, which is characterized in that
The processor executes such as preceding described in any item methods when running the computer program.
Last aspect, the present invention provides a kind of readable storage medium storing program for executing, are stored thereon with computer program, and feature exists
In the computer program realizes method of any of claims 1-7 when being executed by processor.
Processing method, device and the readable storage medium storing program for executing of voice data provided by the invention receive voice number to be processed
According to, speech recognition is carried out to the voice data to be processed, with the corresponding voice key word information of the determination voice data,
According to the voice key word information, determine that the language identification of type corresponding with the voice data to be processed supports packet,
Packet is supported to convert the voice data to be processed according to the determining language identification, obtaining that treated, voice turns
Data are changed, the voice key word information of voice data to be processed are obtained by filtering, and never according to voice key word information
The language identification of same type supports packet is selected to support to wrap with the most matched language identification of voice data to be processed, thus using should
Language identification supports packet to handle voice data to be processed, and process is simple, is conducive to use.
Detailed description of the invention
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Fig. 1 be the present invention is based on network architecture schematic diagram；
Fig. 2 is a kind of flow diagram of the processing method for voice data that the embodiment of the present invention one provides；
Fig. 3 is a kind of flow diagram of the processing method of voice data provided by Embodiment 2 of the present invention；
Fig. 4 is a kind of structural schematic diagram of the processing unit for voice data that the embodiment of the present invention three provides；
Fig. 5 is a kind of hardware schematic of the processing unit for voice data that the embodiment of the present invention four provides.
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
With the development of electronic technology, development trend is become using paperless office, is handled official business by way of voice
It is one such mode.
It also needs to identify voice by the way of voice office, and due to the demand of different business, identify institute
The language used supports the type of packet also different.In the prior art, user needs the voice phase for selecting to input with oneself
After matched language supports packet, corresponding voice could be inputted, so that service platform supports packet to language according to the language of the selection
Sound is handled.
For above-mentioned the technical issues of referring to, the present invention provides a kind of processing methods of voice data, device and readable
Storage medium.It should be noted that processing method, device and readable storage medium storing program for executing that the application provides voice data can be used in
It is widely used in the application scenarios for needing to carry out office or intelligent data typing and storage using voice, these application scenarios packets
It includes but is not limited to: the voice record of meeting, medical case typing, voice customer service data inputting etc..
Fig. 1 be the present invention is based on network architecture schematic diagram, as shown in Figure 1, in the network architecture that is based on of the present invention
Including at least the processing unit 2 and terminal 3 of service platform 1, voice data.The service platform 1 can respectively with terminal 3 and voice
The processing unit 2 of data obtains through wireless communication to be connected and carries out data interaction.In addition, user can pass through terminal 3
The voice of input is uploaded to service platform 1, then is obtained and is handled from service platform by the processing unit 2 of the voice data
After store into service platform 1, for its subsequent use.Certainly, the processing unit 2 of voice data provided by the present application can be handled
Various types of voice data, correspondingly, all types of voice data can be uploaded in service platform 1 by user by terminal 3,
So that the processing unit 2 of voice data is handled.
Fig. 2 is a kind of flow diagram of the processing method for voice data that the embodiment of the present invention one provides.
As shown in Fig. 2, the processing method of the voice data includes:
Step 101 receives voice data to be processed.
Step 102 carries out speech recognition to the voice data to be processed, with the corresponding language of the determination voice data
Sound key word information.
Step 103, according to the voice key word information, determine type corresponding with the voice data to be processed
Language identification supports packet.
Step 104 supports packet to convert the voice data to be processed according to the determining language identification, obtains
Treated voice conversion data.
It should be noted that the executing subject of the processing method of voice data provided by the invention is concretely shown in Fig. 1
Voice data processing unit.
Specifically, the present invention provides a kind of processing method of voice data, firstly, user can will be real-time by terminal
The voice data obtained is acquired, or the voice data of typing in advance is uploaded in service platform, by the processing unit of voice data
The voice data to be processed is grabbed from service platform, or by receiving the voice number to be processed actively initiated by service platform
According to.
Then, the processing unit of voice data will carry out speech recognition to the voice data to be processed, to determine
The corresponding voice key word information of voice data is stated, and according to the voice key word information, the determining and language to be processed
The language identification of the corresponding type of sound data supports packet.
Specifically, unlike the prior art, in the present embodiment, since the processing unit of voice data can be right
The voice data of multiple types is handled, and the language identification for being deployed with multiple types in advance is supported packet, these language inside
Identification supports packet to include at least: Medical Language identification supports packet, customer service language identification that packet and meeting language identification is supported to support packet.
Wherein, which supports to can be used for carrying out text conversion for voice based on different specialized vocabularies in packet,
To obtain the data after more accurately converting.And by utilizing voice key word information, it can be from all types of language identification branch
It holds in packet, it is determining to support to wrap with the more matched language identification of the voice data to be processed, and identified.Voice therein
Key word information specifically may include the quantity of the different keywords occurred in voice data to be processed, belonging to each keyword
One or more information of the frequency of occurrence of many types, each keyword in the voice data etc..
And speech recognition is carried out to the voice data to be processed, it is crucial with the corresponding voice of the determination voice data
Word information, then specifically can include: the voice data is filtered according to the vocabulary packet prestored, determines the language to be processed
Keyword in sound data；Determine the quantity of the different keywords occurred in the voice data to be processed, each keyword
Affiliated many types, each keyword in the frequency of occurrence in the voice data, weighted value shared by each keyword extremely
It is one few；Correspondingly, it is described according to the voice key word information, determine type corresponding with the voice data to be processed
Language identification support packet, comprising: according to the quantity of the different keywords occurred in the voice data to be processed, Mei Geguan
Many types belonging to keyword, each keyword are in the frequency of occurrence in the voice data, weighted value shared by each keyword
At least one, determine that the language identification of corresponding with the voice data to be processed type is supported to wrap.Determination therein with
The language identification of the corresponding type of the voice data to be processed supports packet that the side that preset algorithm calculates comprehensive score can be used
Formula is realized.
Finally, the processing unit of voice data supports packet to the voice to be processed according to the determining language identification
Data are converted, and treated voice conversion data is obtained.
By taking medical scene as an example: clinician in the process of work, it is openable if desired to write documents, the users such as case history
Intelligent sound software or microphone switch are spoken in the effective range of microphone, which is uploaded to service platform by terminal,
So that the processing unit of voice data carries out it to identify and Medical Language identification is called to support packet automatically, voice is converted written
Word is simultaneously shown in document.These texts can carry out unified storage via service platform or carry out subsequent analysis.
The processing method for the voice data that the embodiment of the present invention one provides, by receiving voice data to be processed, to institute
It states voice data to be processed and carries out speech recognition, with the corresponding voice key word information of the determination voice data, according to institute
Predicate sound key word information determines that the language identification of type corresponding with the voice data to be processed supports packet, according to true
The fixed language identification supports packet to convert the voice data to be processed, the voice conversion that obtains that treated
According to obtaining the voice key word information of voice data to be processed by filtering, and according to voice key word information from inhomogeneity
The language identification of type supports packet is selected to support to wrap with the most matched language identification of voice data to be processed, to utilize the language
Identification supports packet to handle voice data to be processed, and process is simple, is conducive to use.
On the basis of example 1, in order to further increase the transfer admittance for voice data, Fig. 3 is the present invention
The flow diagram of the processing method for a kind of voice data that embodiment two provides, as shown in figure 3, the processing side of the voice data
Method includes:
Step 201, the interface for calling service platform receive and are uploaded to the to be processed of the service platform from each client
Voice data.
Step 202 carries out speech recognition to the voice data to be processed, with the corresponding language of the determination voice data
Sound key word information；
Step 203 supported in packet using preset NB Algorithm in all types of language identification, is selected and voice
The highest language identification of key word information matching degree supports packet, and the language identification as the voice data to be processed is supported
Packet.
Step 204 supports packet to convert the voice data to be processed according to the determining language identification, obtains
Treated voice conversion data.
The voice data to be processed and corresponding voice conversion process are associated storage by step 205, for clothes
Business platform is managed it.
Similarly with embodiment one, the executing subject of the processing method of voice data provided by the invention is concretely schemed
The processing unit of voice data shown in 1.
In the present embodiment, firstly, when user can acquire the voice data obtained or preparatory typing for real-time by terminal
Voice data be uploaded to after service platform, the processing unit of voice data can call the interface of service platform, and reception comes from
Each client is uploaded to the voice data to be processed of the service platform.Wherein, for the ease of the processing unit of voice data
Each voice data to be processed is grabbed and received, service platform will reserve unified interface, for the place of voice data
It manages device and calls voice data from the interface.
Then, the processing unit of voice data will carry out speech recognition to the voice data to be processed, to determine
The corresponding voice key word information of voice data is stated, and according to the voice key word information, the determining and language to be processed
The language identification of the corresponding type of sound data supports packet.
In the present embodiment, there is vocabulary packet in the processing unit of voice data, each vocabulary has profession belonging to it
(belonging to medical vocabulary or customer service vocabulary or meeting vocabulary) and corresponding weighted value.By utilizing these vocabulary packets to be processed
Voice data be filtered, determine the keyword occurred in the voice data to be processed.It counts and determines to be processed
Many types belonging to the quantity of the different keywords occurred in voice data, each keyword, each keyword are in the voice
Frequency of occurrence in data.
Then, language identification the most matched is obtained using these voice key word informations and preset algorithm to support to wrap.
Specifically, also prestoring preset keyword vector table in the processing unit of voice data, which is used for table
Show that each keyword belongs to the probability that all types of language identifications supports packet in voice key word information.The processing unit of voice data
Determine that each voice keyword occurred in voice key word information belongs to all types of language identifications using keyword vector table
Support the probability of packet.Then, the frequency of occurrence in conjunction with each voice keyword above-mentioned in entire voice data to be processed with
And the quantity of the voice keyword of entire voice data to be processed, determine that probability is highest as the voice to be processed
The language identification of data supports packet.I.e. the processing unit of voice data can increase it according to the word occurrence frequency of analytic language
Language supports packet weight, and the processing unit of voice data, which matches, adds up frequency of use, comprehensive to add up preferably to go out language support packet.
Further, since the processing unit of voice data can be handled the voice data of multiple types, it inside will be preparatory
It is deployed with the language identification support packet of multiple types, these language identifications support packet to include at least: Medical Language identification support packet,
Customer service language identification supports packet and meeting language identification to support packet.
Finally, the processing unit of voice data supports packet to the voice to be processed according to the determining language identification
Data are converted, after obtaining treated voice conversion data, also by the voice data to be processed and corresponding voice
Conversion process is stored, so that service platform is managed it.
The processing method of voice data provided by the invention, by receiving voice data to be processed, to described to be processed
Voice data carry out speech recognition, with the corresponding voice key word information of the determination voice data, closed according to the voice
Keyword information determines that the language identification of type corresponding with the voice data to be processed supports packet, according to determining
Language identification supports packet to convert the voice data to be processed, obtains treated voice conversion data, passed through
Filter obtains the voice key word information of voice data to be processed, and is known according to voice key word information from different types of language
It Zhi Chi not wrap to select and support to wrap with the most matched language identification of voice data to be processed, to support to wrap using the language identification
Voice data to be processed is handled, process is simple, is conducive to use.
Fig. 4 is a kind of structural schematic diagram of the processing unit for voice data that the embodiment of the present invention three provides, such as Fig. 4 institute
Show, the processing unit of the voice data includes:
Receiving module 10, for receiving voice data to be processed；
Identification module 20, for carrying out speech recognition to the voice data to be processed, with the determination voice data
Corresponding voice key word information；
Language pack conversion module 30, for according to the voice key word information, the determining and voice number to be processed
Packet is supported according to the language identification of corresponding type；It is also used to support packet to described to be processed according to the determining language identification
Voice data is converted, and treated voice conversion data is obtained.
In a kind of wherein optional embodiment, the identification module 20 is specifically used for:
It supports to select and believe with voice keyword in packet in all types of language identifications using preset NB Algorithm
It ceases the highest language identification of matching degree and supports packet, the language identification as the voice data to be processed supports packet.
In a kind of wherein optional embodiment, the identification module 20 is specifically used for:
Determine that each keyword belongs to all types of language knowledges in voice key word information according to preset keyword vector table
The probability of packet is not supported；
According to the probability of each voice keyword, determine that the voice data to be processed belongs to all types of language identification branch
The probability of packet is held, and selects the highest language identification as the voice data to be processed of probability and supports packet.
In a kind of wherein optional embodiment, the identification module 20 is specifically used for:
The voice data is filtered according to the vocabulary packet prestored, determines the pass in the voice data to be processed
Keyword；
Determine profession belonging to the quantity of the different keywords occurred in the voice data to be processed, each keyword
The frequency of occurrence of type, each keyword in the voice data；
Correspondingly, it is described according to the voice key word information, determine class corresponding with the voice data to be processed
The language identification of type supports packet, comprising: according to the quantity of the different keywords occurred in the voice data to be processed, each
The frequency of occurrence of many types belonging to keyword, each keyword in the voice data, the determining and language to be processed
The language identification of the corresponding type of sound data supports packet.
In a kind of wherein optional embodiment, the language identification supports that the type of packet includes: Medical Language identification
Support packet, customer service language identification that packet and meeting language identification is supported to support packet.
It further include storage unit in a kind of wherein optional embodiment, for obtaining treated voice described
After change data, the voice data to be processed and corresponding voice conversion process are stored, for service platform
It is managed.
In a kind of wherein optional embodiment, the receiving module 10 is specifically used for:
The interface of service platform is called, the voice number to be processed for being uploaded to the service platform from each client is received
According to.
The processing unit of voice data provided by the invention, by receiving voice data to be processed, to described to be processed
Voice data carry out speech recognition, with the corresponding voice key word information of the determination voice data, closed according to the voice
Keyword information determines that the language identification of type corresponding with the voice data to be processed supports packet, according to determining
Language identification supports packet to convert the voice data to be processed, obtains treated voice conversion data, passed through
Filter obtains the voice key word information of voice data to be processed, and is known according to voice key word information from different types of language
It Zhi Chi not wrap to select and support to wrap with the most matched language identification of voice data to be processed, to support to wrap using the language identification
Voice data to be processed is handled, process is simple, is conducive to use.
Fig. 5 is a kind of hardware schematic of the processing unit for voice data that the embodiment of the present invention four provides.Such as Fig. 5 institute
Show, the processing unit of the voice data includes: processor 42 and is stored on memory 41 and can run on processor 42
Computer program, processor 42 run the method for executing above-described embodiment when computer program.
The present invention also provides a kind of readable storage medium storing program for executing, including program, when it runs at the terminal, so that terminal executes
The method of any of the above-described embodiment.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of processing method of voice data characterized by comprising
Receive voice data to be processed；
Speech recognition is carried out to the voice data to be processed, with the corresponding voice keyword letter of the determination voice data
Breath；
According to the voice key word information, determine that the language identification of type corresponding with the voice data to be processed is supported
Packet；
Packet is supported to convert the voice data to be processed according to the determining language identification, the language that obtains that treated
Sound change data.
2. the processing method of voice data according to claim 1, which is characterized in that described according to the voice keyword
Information determines that the language identification of type corresponding with the voice data to be processed supports packet, comprising:
It supports to select and voice key word information in packet in all types of language identifications using preset NB Algorithm
Packet is supported with highest language identification is spent, and the language identification as the voice data to be processed supports packet.
3. the processing method of voice data according to claim 2, which is characterized in that described to utilize preset simple pattra leaves
This algorithm is supported in packet in all types of language identifications, is selected and is supported with the highest language identification of voice key word information matching degree
Packet, the language identification as the voice data to be processed support packet, comprising:
Determine that each keyword belongs to all types of language identification branch in voice key word information according to preset keyword vector table
Hold the probability of packet；
Belong to the probability that all types of language identifications supports packet according to keyword each in voice key word information, determines described wait locate
The voice data of reason belongs to the probability that all types of language identifications supports packet, and it is highest as described to be processed to select probability
The language identification of voice data supports packet.
4. the processing method of voice data according to claim 1, which is characterized in that described to the voice to be processed
Data carry out speech recognition, with the corresponding voice key word information of the determination voice data, comprising:
The voice data is filtered according to the vocabulary packet prestored, determines the key in the voice data to be processed
Word；
Determine professional class belonging to the quantity of the different keywords occurred in the voice data to be processed, each keyword
Type, each keyword are at least one of the frequency of occurrence in the voice data, weighted value shared by each keyword；
Correspondingly, it is described according to the voice key word information, determine type corresponding with the voice data to be processed
Language identification supports packet, comprising:
According to professional class belonging to the quantity of the different keywords occurred in the voice data to be processed, each keyword
Type, each keyword at least one of the frequency of occurrence in the voice data, weighted value shared by each keyword, determine with
The language identification of the corresponding type of the voice data to be processed supports packet.
5. the processing method of voice data according to claim 1, which is characterized in that the language identification supports the class of packet
Type includes: that Medical Language identification supports packet, customer service language identification that packet and meeting language identification is supported to support packet.
6. the processing method of voice data according to claim 1-5, which is characterized in that it is described handled after
Voice conversion data after, the method also includes:
The voice data to be processed and corresponding voice conversion process are associated storage.
7. the processing method of voice data according to claim 1-5, which is characterized in that the reception is to be processed
Voice data, comprising:
The interface of service platform is called, the voice data to be processed for being uploaded to the service platform from each client is received.
8. a kind of processing unit of voice data characterized by comprising
Receiving module, for receiving voice data to be processed；
Identification module, it is corresponding with the determination voice data for carrying out speech recognition to the voice data to be processed
Voice key word information；
Language pack conversion module, for according to the voice key word information, determination to be corresponding with the voice data to be processed
Type language identification support packet；It is also used to support packet to the voice number to be processed according to the determining language identification
According to being converted, the voice conversion data that obtains that treated.
9. a kind of electronic equipment characterized by comprising memory, the processor being connect with the memory, and it is stored in institute
State the computer program that can be run on memory and on the processor, which is characterized in that
Perform claim requires the described in any item methods of 1-7 when the processor runs the computer program.
10. a kind of readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the computer program is processed
Device realizes method of any of claims 1-7 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517309.2A CN109559744B (en) | 2018-12-12 | 2018-12-12 | Voice data processing method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517309.2A CN109559744B (en) | 2018-12-12 | 2018-12-12 | Voice data processing method and device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109559744A true CN109559744A (en) | 2019-04-02 |
| CN109559744B CN109559744B (en) | 2022-07-08 |
Family
ID=65870031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811517309.2A Active CN109559744B (en) | 2018-12-12 | 2018-12-12 | Voice data processing method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109559744B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223672A (en) * | 2019-05-16 | 2019-09-10 | 九牧厨卫股份有限公司 | A kind of multilingual audio recognition method of off-line type |
| CN110728981A (en) * | 2019-10-09 | 2020-01-24 | 北京达佳互联信息技术有限公司 | Interactive function execution method and device, electronic equipment and storage medium |
| CN111223496A (en) * | 2020-01-03 | 2020-06-02 | 广东电网有限责任公司 | Voice information classification method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730115A (en) * | 2013-12-27 | 2014-04-16 | 北京捷成世纪科技股份有限公司 | Method and device for detecting keywords in voice |
| CN105161104A (en) * | 2015-07-31 | 2015-12-16 | 北京云知声信息技术有限公司 | Voice processing method and device |
| CN106205610A (en) * | 2016-06-29 | 2016-12-07 | 联想(北京)有限公司 | A kind of voice information identification method and equipment |
| US20170061959A1 (en) * | 2015-09-01 | 2017-03-02 | Disney Enterprises, Inc. | Systems and Methods For Detecting Keywords in Multi-Speaker Environments |
| CN107766371A (en) * | 2016-08-19 | 2018-03-06 | 中兴通讯股份有限公司 | A kind of text message sorting technique and its device |
| CN108538286A (en) * | 2017-03-02 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of method and computer of speech recognition |
-
2018
- 2018-12-12 CN CN201811517309.2A patent/CN109559744B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730115A (en) * | 2013-12-27 | 2014-04-16 | 北京捷成世纪科技股份有限公司 | Method and device for detecting keywords in voice |
| CN105161104A (en) * | 2015-07-31 | 2015-12-16 | 北京云知声信息技术有限公司 | Voice processing method and device |
| US20170061959A1 (en) * | 2015-09-01 | 2017-03-02 | Disney Enterprises, Inc. | Systems and Methods For Detecting Keywords in Multi-Speaker Environments |
| CN106205610A (en) * | 2016-06-29 | 2016-12-07 | 联想(北京)有限公司 | A kind of voice information identification method and equipment |
| CN107766371A (en) * | 2016-08-19 | 2018-03-06 | 中兴通讯股份有限公司 | A kind of text message sorting technique and its device |
| CN108538286A (en) * | 2017-03-02 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of method and computer of speech recognition |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223672A (en) * | 2019-05-16 | 2019-09-10 | 九牧厨卫股份有限公司 | A kind of multilingual audio recognition method of off-line type |
| CN110223672B (en) * | 2019-05-16 | 2021-04-23 | 九牧厨卫股份有限公司 | Offline multi-language voice recognition method |
| CN110728981A (en) * | 2019-10-09 | 2020-01-24 | 北京达佳互联信息技术有限公司 | Interactive function execution method and device, electronic equipment and storage medium |
| CN111223496A (en) * | 2020-01-03 | 2020-06-02 | 广东电网有限责任公司 | Voice information classification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109559744B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10726833B2 (en) | System and method for rapid customization of speech recognition models | |
| CN1307589C (en) | Method and apparatus of managing information about a person | |
| JP6351562B2 (en) | Information processing system, reception server, information processing method, and program | |
| US9742912B2 (en) | Method and apparatus for predicting intent in IVR using natural language queries | |
| CN109559744A (en) | Processing method, device and the readable storage medium storing program for executing of voice data | |
| US8170866B2 (en) | System and method for increasing accuracy of searches based on communication network | |
| CN101593516B (en) | Method and system for speech synthesis | |
| CN104969288B (en) | The method and system of voice recognition system is provided based on voice recording daily record | |
| US8238525B2 (en) | Voice recognition server, telephone equipment, voice recognition system, and voice recognition method | |
| CN1573928A (en) | Semantic object synchronous understanding implemented with speech application language tags | |
| EP2153638A1 (en) | Automated attendant grammar tuning | |
| CN108010513B (en) | Voice processing method and device | |
| CN109981910A (en) | Business recommended method and apparatus | |
| US10255346B2 (en) | Tagging relations with N-best | |
| CN111696558A (en) | Intelligent outbound method, device, computer equipment and storage medium | |
| CN108509416A (en) | Sentence realizes other method and device, equipment and storage medium | |
| JP4837887B2 (en) | Pattern processing system specific to user groups | |
| CN109147146B (en) | Voice number taking method and terminal equipment | |
| CN109165180A (en) | A kind of method and system improving source of houses broker operating efficiency | |
| CN108417226A (en) | Speech comparison method, terminal and computer readable storage medium | |
| CN108920715B (en) | Intelligent auxiliary method, device, server and storage medium for customer service | |
| JP2015200860A (en) | Dictionary database management device, api server, dictionary database management method, and dictionary database management program | |
| CN111062729A (en) | Information acquisition method, device and equipment | |
| CN114067842B (en) | Customer satisfaction degree identification method and device, storage medium and electronic equipment | |
| US8589384B2 (en) | Methods and arrangements for employing descriptors for agent-customer interactions |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |