CN112466283A - Collaborative software voice recognition system - Google Patents
Collaborative software voice recognition system Download PDFInfo
- Publication number
- CN112466283A CN112466283A CN202011190095.XA CN202011190095A CN112466283A CN 112466283 A CN112466283 A CN 112466283A CN 202011190095 A CN202011190095 A CN 202011190095A CN 112466283 A CN112466283 A CN 112466283A
- Authority
- CN
- China
- Prior art keywords
- service
- file
- audio
- server
- voice recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 6
- 239000000872 buffer Substances 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 3
- 238000013467 fragmentation Methods 0.000 description 3
- 238000006062 fragmentation reaction Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
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
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/146—Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (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)
- Computer Vision & Pattern Recognition (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a collaborative software speech recognition system, which comprises: the system comprises a client, an automatic voice recognition platform and a server; the client side is provided with cooperative software, the cooperative software receives a request and classifies the request as follows: processing the recording, transcoding and parameter extraction by the client; the automatic voice recognition platform processes the voice recognition request and distributes a server for the voice recognition request according to a dynamic routing self-adaptive algorithm and calls the server; and the server receives the voice recognition request and starts a recognition service.
Description
Technical Field
The invention belongs to the technical field of electronic information, and particularly relates to a collaborative software voice recognition system.
Background
Speech recognition technology, also called Automatic Speech Recognition (ASR), is a technology that converts the vocabulary content in human Speech into computer-readable input, which in some scenarios can be understood as Speech converted into text. At present, a speech recognition technology is a relatively general technology in the field of artificial intelligence, and is generally used in an application scene as an auxiliary tool. For example, in a call center, a speech-to-text scenario, and a scenario in which real-time recognition of the entire speech process is required in simultaneous interpretation, are used, and the speech recognition requirements for frequent calls with high concurrence are not very high. Therefore, most of the existing voice recognition service architectures are single architecture modes, and one recognition service completes all the work of storage, transcoding and recognition.
With the development of voice recognition technology, the recognition accuracy and the recognition speed are continuously improved, the voice technology starts to be comprehensively applied in various industries, and voice recognition solutions under high concurrency scenes are urgently needed at present. In the daily communication of users in the cooperative software, the voice message is a message with very high use frequency, huge quantity and strong timeliness. And many exchanges are generated in the group, the number of participating users is very large, and the message repetition amount is large. In addition, the foreign language voice input method is also a rigid requirement in cooperative software, and requires that voice can be timely converted into characters to be provided for a message sender to correct.
Therefore, a method for solving the problem of cooperative software voice recognition and construction is needed, which organically combines the cooperative software use scene and the voice recognition use scene and solves the high concurrent voice recognition requirement under the scene.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present invention provides a collaborative software speech recognition system, which has the following technical scheme:
a collaborative software speech recognition system, the system comprising: the system comprises a client, an automatic voice recognition platform and a server;
the client side is provided with cooperative software, the cooperative software receives a request and classifies the request as follows: processing the recording, transcoding and parameter extraction by the client;
the automatic voice recognition platform processes the voice recognition request and distributes a server for the voice recognition request according to a dynamic routing self-adaptive algorithm and calls the server;
and the server receives the voice recognition request and starts a recognition service.
The automatic voice recognition platform is based on a micro-service architecture and comprises a micro-service gateway, a micro-service registration center and audio related services;
wherein the content of the first and second substances,
the micro service gateway receives the voice recognition request;
the micro service registration center analyzes the voice recognition request and distributes a server for the voice recognition request based on the dynamic routing self-adaptive algorithm;
and the micro service gateway pulls the server to call the server.
The micro-service registration center receives the load parameters of the servers, calculates the load value of each server, sorts the servers according to the load values, and selects the optimal server to process the voice recognition request.
And the cooperative software receives the voice recognition service, recognizes the audio file by using the acoustic parameters, extracts the MFCC parameters of the audio file to generate an audio parameter file, and sends the audio parameter file to the file service of the automatic voice recognition platform for storage.
The server receives the voice recognition request and initiates a recognition service, including,
the voice recognition request comprises a resource ID;
the server searches a corresponding identification result in a result cache server according to the resource ID, and if the identification is successful, the identification result is returned;
and when the identification fails, the server searches a corresponding audio parameter file in a file cache server according to the resource ID and distributes the audio parameter file to a corresponding automatic voice identification service queue according to the audio time of the audio file.
The audio-related services include file services and voice file recognition services;
the file service includes: file storage service and result caching service;
the voice file recognition service includes:
short audio file recognition service, medium audio file recognition service, long audio file recognition service, and real-time voice recognition service.
The identifying a service queue comprises: short audio file automatic speech recognition service, medium audio file automatic speech recognition service, and real-time automatic speech recognition service.
The medium audio file identification service fragments the audio parameter file by using a voice read point detection technology, the audio parameter file is processed by the short audio file identification service after the fragment, and the processing interface combines a plurality of identification results, returns the combined identification results to the cooperative software and stores the identification results and the corresponding resource ID into a buffer.
The server distributes the audio files with the time length exceeding 120 seconds and the audio files needing real-time identification to the real-time automatic voice identification service queue; distributing the audio files with the time length of more than 10 seconds and less than 120 seconds to an automatic voice recognition service queue of the medium audio files; and distributing the audio files with the duration less than 10 seconds to the short audio file automatic speech recognition service queue.
The invention has the following beneficial effects:
the invention provides a collaborative software voice recognition system. The system is designed by adopting a micro-service architecture, and different identification micro-services are designed according to the message length of a request, so that the real-time performance and the high reliability of the identification system under the condition of high concurrency are ensured.
Drawings
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
FIG. 1 is a general flow chart of a collaborative software speech recognition system according to an embodiment of the present invention;
FIG. 2 is a flow chart of dynamic routing adaptation for a collaborative software speech recognition system according to an embodiment of the present invention;
fig. 3 is a logic diagram of service partitioning for a cooperative software speech recognition system according to an embodiment of the present invention.
Detailed Description
The following detailed description of the cooperative software speech recognition system according to the present invention is provided in conjunction with the accompanying drawings and embodiments, which are provided for the purpose of illustration and are not intended to limit the scope of the invention.
A collaborative software speech recognition system, as shown in FIG. 1, includes a client and a speech recognition service platform
The voice recognition micro service platform comprises a micro service gateway, a micro service registration center and audio related services, wherein the audio related services comprise a file storage service, a result caching service, a short voice file recognition service, a medium voice file recognition service, a long voice file recognition service and a real-time voice recognition service, and the result caching service and the file storage service respectively correspond to different buffers.
In a preferred embodiment, the voice recognition micro-service platform is based on a spring cloud micro-service architecture, the micro-service gateway is implemented based on Zuul, and the micro-service registry is implemented based on Eurake.
In the system, a client divides voice service, wherein recording, transcoding and parameter extraction are realized by the client, voice recognition service is realized by using a self-service voice service platform, the client extracts MFCC parameters of an audio file of a user, and the process of extracting acoustic parameters is carried out at the client, so that the computing capacity of the client can be effectively utilized, the development and project cost of the server is reduced, the volume of files needing to be cached is reduced, and the cost of storing original voice is reduced.
The method comprises the steps that a client receives a voice recognition request and transmits the voice recognition request to an automatic voice recognition platform based on a micro-service architecture, a micro-service gateway distributes the voice recognition request to a micro-service registration center, the micro-service registration center recognizes the voice recognition request and distributes an optimal processor for the voice recognition request according to a dynamic routing self-adaption algorithm, as shown in fig. 2, a server reports a task state of a node every 2 seconds, and in one embodiment, the maximum service connection number C1 of the server A, the service connection number C2 which is currently processed, and the CPU utilization rate C3, the memory utilization rate C4 and the disk utilization rate C5 of the computing node serve as parameters for evaluating server load. And the micro service gateway calculates the Load value of each server according to the Load parameters and the weight of each parameter, wherein the server A is preset with a total connection weight of W1, a current connection weight of W2, a CPU weight of W3, a memory weight of W4 and a disk weight of W5, so that the Load value of the server is W1C 1-W2C 2-W3C 3-W4C 4-W5C 5, the micro service gateway sorts the Load values of the plurality of servers according to the size, divides the servers into intervals according to the sorting result, and selects one server in the optimal interval as a next calculation node each time. After the micro-service registration center selects the server, the micro-service gateway pulls the server to the micro-service registration center for calling.
In a preferred embodiment, the client distinguishes the real-time identification service and the audio file identification service according to the interaction behavior, and marks the voice identification service types corresponding to the audio file identification service according to the duration of the audio file, wherein the voice identification service types comprise a short audio file, a medium audio file and a long audio file.
In an optional embodiment, the micro service registry distinguishes real-time identification services and audio file identification services according to the interaction behavior, and marks the audio file identification services with corresponding voice identification service categories according to the duration of the audio files, wherein the voice identification service categories comprise short audio files, medium audio files and long audio files.
In an optional embodiment, the server distinguishes real-time identification services and audio file identification services according to the interaction behavior, and marks the voice identification service classes corresponding to the audio file identification services according to the duration of the audio file, wherein the voice identification service classes comprise short audio files, medium audio files and long audio files.
The three files respectively correspond to three duration intervals: the method comprises the steps that 0-10S, 10-120S and more than 120S are carried out, the three audio files correspond to a short audio file identification service, a medium audio file identification service and a long audio file identification service respectively, after a server receives a voice identification service request, as shown in figure 3, a result storage service is called firstly, an identification result is searched in the result storage server according to a resource ID transmitted by a client, the identification result is directly returned to the client after being hit, if the identification result does not exist, audio processing is carried out according to different audio file types, and an audio parameter file of the audio file is called from a file cache service according to the resource ID during processing. And for the short audio files smaller than 10s, the client or the server calls a short audio file identification service interface of the HTTP, and the short audio file identification service interface analyzes the corresponding audio parameter files. And for the medium audio file identification service, calling a medium audio identification service interface of HTTP, wherein the medium audio identification service segments the audio parameter file by using audio breakpoint detection (VAD), and numbers the segmented files, wherein each segment is independent, and the results do not influence each other. And putting the numbered fragments into an internal queue of the medium audio service, and identifying the voice of the fragments in the queue by using a thread pool. And sorting the fragmentation identification results according to the numbers, and combining all the fragmentation results according to the sequence and returning the combined fragmentation results to the client or the server. For long audio files exceeding 120s, the server calls the websocket service of the real-time identification service for processing. The server stores the processed identification result and the corresponding resource ID into the result storage server, so that the comparison of the identification result of the next time is facilitated.
Claims (9)
1. A collaborative software speech recognition system, the system comprising: the system comprises a client, an automatic voice recognition platform and a server;
the client side is provided with cooperative software, the cooperative software receives a request and classifies the request as follows: processing the recording, transcoding and parameter extraction by the client;
the automatic voice recognition platform processes the voice recognition request and distributes a server for the voice recognition request according to a dynamic routing self-adaptive algorithm and calls the server;
and the server receives the voice recognition request and starts a recognition service.
2. The system of claim 1,
the automatic voice recognition platform is based on a micro-service architecture and comprises a micro-service gateway, a micro-service registration center and audio related services;
wherein the content of the first and second substances,
the micro service gateway receives the voice recognition request;
the micro service registration center analyzes the voice recognition request and distributes a server for the voice recognition request based on the dynamic routing self-adaptive algorithm;
and the micro service gateway pulls the server to call the server.
3. The system of claim 2,
the micro-service registration center receives the load parameters of the servers, calculates the load value of each server, sorts the servers according to the load values, and selects the optimal server to process the voice recognition request.
4. The system of claim 1,
and the cooperative software receives the voice recognition service, recognizes the audio file by using the acoustic parameters, extracts the MFCC parameters of the audio file to generate an audio parameter file, and sends the audio parameter file to the file service of the automatic voice recognition platform for storage.
5. The system of claim 1,
the server receives the voice recognition request and initiates a recognition service, including,
the voice recognition request comprises a resource ID;
the server searches a corresponding identification result in a result cache server according to the resource ID, and if the identification is successful, the identification result is returned;
and when the identification fails, the server searches a corresponding audio parameter file in a file cache server according to the resource ID and distributes the audio parameter file to a corresponding automatic voice identification service queue according to the audio time of the audio file.
6. The system of claim 2,
the audio-related services include file services and voice file recognition services;
the file service includes: file storage service and result caching service;
the voice file recognition service includes:
short audio file recognition service, medium audio file recognition service, long audio file recognition service, and real-time voice recognition service.
7. The system of claim 5,
the identifying a service queue comprises: short audio file automatic speech recognition service, medium audio file automatic speech recognition service, and real-time automatic speech recognition service.
8. The system of claim 6,
the medium audio file identification service fragments the audio parameter file by using a voice read point detection technology, the audio parameter file is processed by the short audio file identification service after the fragment, and the processing interface combines a plurality of identification results, returns the combined identification results to the cooperative software and stores the identification results and the corresponding resource ID into a buffer.
9. The system of claim 1,
the server distributes the audio files with the time length exceeding 120 seconds and the audio files needing real-time identification to the real-time automatic voice identification service queue; distributing the audio files with the time length of more than 10 seconds and less than 120 seconds to an automatic voice recognition service queue of the medium audio files; and distributing the audio files with the duration less than 10 seconds to the short audio file automatic speech recognition service queue.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011190095.XA CN112466283B (en) | 2020-10-30 | 2020-10-30 | Cooperative software voice recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011190095.XA CN112466283B (en) | 2020-10-30 | 2020-10-30 | Cooperative software voice recognition system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112466283A true CN112466283A (en) | 2021-03-09 |
CN112466283B CN112466283B (en) | 2023-12-01 |
Family
ID=74834757
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011190095.XA Active CN112466283B (en) | 2020-10-30 | 2020-10-30 | Cooperative software voice recognition system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112466283B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115037904A (en) * | 2022-05-13 | 2022-09-09 | 广东润联信息技术有限公司 | Converged cloud video conference management platform and conference access method |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102546542A (en) * | 2010-12-20 | 2012-07-04 | 福建星网视易信息***有限公司 | Electronic system and embedded device and transit device of electronic system |
CN102571833A (en) * | 2010-12-15 | 2012-07-11 | 盛乐信息技术(上海)有限公司 | Distributed speech recognition system and distributed speech recognition method based on server cluster |
CN103325371A (en) * | 2013-06-05 | 2013-09-25 | 杭州网豆数字技术有限公司 | Voice recognition system and method based on cloud |
US20150162003A1 (en) * | 2013-12-10 | 2015-06-11 | Alibaba Group Holding Limited | Method and system for speech recognition processing |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
CN106356066A (en) * | 2016-08-30 | 2017-01-25 | 孟玲 | Speech recognition system based on cloud computing |
CN109462647A (en) * | 2018-11-12 | 2019-03-12 | 平安科技(深圳)有限公司 | Resource allocation methods, device and computer equipment based on data analysis |
CN110309350A (en) * | 2018-03-21 | 2019-10-08 | 腾讯科技(深圳)有限公司 | Recite processing method, system, device, medium and the electronic equipment of task |
CN111526208A (en) * | 2020-05-06 | 2020-08-11 | 重庆邮电大学 | High-concurrency cloud platform file transmission optimization method based on micro-service |
CN111785277A (en) * | 2020-06-29 | 2020-10-16 | 北京捷通华声科技股份有限公司 | Speech recognition method, speech recognition device, computer-readable storage medium and processor |
-
2020
- 2020-10-30 CN CN202011190095.XA patent/CN112466283B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102571833A (en) * | 2010-12-15 | 2012-07-11 | 盛乐信息技术(上海)有限公司 | Distributed speech recognition system and distributed speech recognition method based on server cluster |
CN102546542A (en) * | 2010-12-20 | 2012-07-04 | 福建星网视易信息***有限公司 | Electronic system and embedded device and transit device of electronic system |
CN103325371A (en) * | 2013-06-05 | 2013-09-25 | 杭州网豆数字技术有限公司 | Voice recognition system and method based on cloud |
US20150162003A1 (en) * | 2013-12-10 | 2015-06-11 | Alibaba Group Holding Limited | Method and system for speech recognition processing |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
CN106356066A (en) * | 2016-08-30 | 2017-01-25 | 孟玲 | Speech recognition system based on cloud computing |
CN110309350A (en) * | 2018-03-21 | 2019-10-08 | 腾讯科技(深圳)有限公司 | Recite processing method, system, device, medium and the electronic equipment of task |
CN109462647A (en) * | 2018-11-12 | 2019-03-12 | 平安科技(深圳)有限公司 | Resource allocation methods, device and computer equipment based on data analysis |
CN111526208A (en) * | 2020-05-06 | 2020-08-11 | 重庆邮电大学 | High-concurrency cloud platform file transmission optimization method based on micro-service |
CN111785277A (en) * | 2020-06-29 | 2020-10-16 | 北京捷通华声科技股份有限公司 | Speech recognition method, speech recognition device, computer-readable storage medium and processor |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115037904A (en) * | 2022-05-13 | 2022-09-09 | 广东润联信息技术有限公司 | Converged cloud video conference management platform and conference access method |
Also Published As
Publication number | Publication date |
---|---|
CN112466283B (en) | 2023-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102381214B1 (en) | Man-machine dialogue method, device and electronic equipment | |
US10242669B1 (en) | Enhanced transcription of audio data with punctuation markings based on silence durations | |
CN111916082B (en) | Voice interaction method, device, computer equipment and storage medium | |
US20120316875A1 (en) | Hosted speech handling | |
CN109417583B (en) | System and method for transcribing audio signal into text in real time | |
CN110381221B (en) | Call processing method, device, system, equipment and computer storage medium | |
US10170120B2 (en) | Call management system and its speech recognition control method | |
US9196250B2 (en) | Application services interface to ASR | |
US20150179165A1 (en) | System and method for caller intent labeling of the call-center conversations | |
CN111638948B (en) | Multi-channel high-availability big data real-time decision making system and decision making method | |
US20070124360A1 (en) | Systems and methods for processing audio using multiple speech technologies | |
JPH08195763A (en) | Voice communications channel of network | |
CN110942764B (en) | Stream type voice recognition method | |
CN110782341A (en) | Business collection method, device, equipment and medium | |
CN111402906B (en) | Speech decoding method, device, engine and storage medium | |
CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
CN110502631B (en) | Input information response method and device, computer equipment and storage medium | |
CN112466283B (en) | Cooperative software voice recognition system | |
EP3232436A2 (en) | Application services interface to asr | |
CN112714217A (en) | Telephone traffic quality inspection method, device, storage medium and server | |
CN116610794A (en) | Report processing method, report processing device, electronic equipment and storage medium | |
CN115798479A (en) | Method and device for determining session information, electronic equipment and storage medium | |
CN116939109A (en) | Call center equipment control system and method | |
CN114724562A (en) | Method, device and system for recognizing voice content | |
KR101002135B1 (en) | Transfer method with syllable as a result of speech recognition |
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 |