CN107147564A - Real-time speech recognition error correction system and identification error correction method based on cloud server - Google Patents
Real-time speech recognition error correction system and identification error correction method based on cloud server Download PDFInfo
- Publication number
- CN107147564A CN107147564A CN201710319312.2A CN201710319312A CN107147564A CN 107147564 A CN107147564 A CN 107147564A CN 201710319312 A CN201710319312 A CN 201710319312A CN 107147564 A CN107147564 A CN 107147564A
- Authority
- CN
- China
- Prior art keywords
- text
- error correction
- client
- viewing area
- cloud server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
-
- 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
-
- 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
- G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a kind of Real-time speech recognition error correction system based on cloud server and identification error correction method, including the first client, the second client, cloud server, voice send button, duration viewing area, text editing button, progress bar viewing area, sender's text viewing area, sender's head portrait viewing area, recipient's text viewing area and recipient's head portrait viewing area.The present invention makes voice communication more convenient, and word can be directly generated by sending voice, and sender can change text, while cloud server can carry out error correction, improves audio identification efficiency.
Description
Technical field
Taken the present invention relates to voice instant messaging field and cloud computing field of speech recognition, more particularly to a kind of high in the clouds that is based on
The Real-time speech recognition error correction system and identification error correction method of business device.
Background technology
Instant messaging form at this stage mainly has text and voice, and the voice communication development based on mobile terminal is more fast
Speed, the communication given people brings facility, but simple voice communication has its drawback, and sometimes people are inconvenient to answer language
Sound, at the same it is more inconvenient when reviewing information, so voice communication needs new upgrading, while speech recognition technology flies now
The development of speed, the precision for converting speech into text constantly improves, still, speech recognition or some mistakes, can influence to use
Experience at family.
The content of the invention
The purpose of the present invention：A kind of Real-time speech recognition error correction system based on cloud server and identification error correction side are provided
Method, can carry out speech recognition and error correction in voice instant messaging, and update speech recognition system according to text error correction, effectively change
The experience of kind user.
To achieve these goals, the technical scheme is that：
A kind of Real-time speech recognition error correction system based on cloud server, including the first client, the second client, high in the clouds clothes
Business device, voice send button, duration viewing area, text editing button, sender's text viewing area, sender's head portrait
Viewing area, recipient's text viewing area and recipient's head portrait viewing area；The first described client and the second visitor
Family end is bi-directionally connected with described cloud server respectively, and described voice send button, duration viewing area are separately positioned on
In the first described client and the second client；Described text editing button, sender's text viewing area and hair
The person's of sending head portrait viewing area is separately positioned in the first described client, described recipient's text viewing area and is connect
Receipts person's head portrait viewing area is separately positioned in the second described client.
A kind of identification error correction method of the Real-time speech recognition error correction system based on cloud server, this method at least includes
Following steps：
Step 1：Voice send button is clicked on, the first client receives voice and is recorded as voice document, unclamp voice transmission and press
Button, the first client sends voice document to cloud server.
Step 2：Voice document is resolved to text by cloud server, and text is sent to by cloud server
Voice document and text are sent to the second client by one client, cloud server.
Step 3：Sender checks that text has inerrancy, if text is wrong, clicks on text editing button simultaneously
Error correction is carried out according to text, the text after error correction can be shown in sender's text display area, and by after error correction
Text is sent to cloud server.
Step 4：Cloud server updates speech recognition system according to the text after error correction, and by the text after renewal
File is sent to the second client, and completion once communicates.
Step 5：Click recipient's text viewing area, the second client terminal playing voice document,
The identification error correction method of the above-mentioned Real-time speech recognition error correction system based on cloud server, wherein, in described step
In rapid 2, sender's text viewing area of the first described client shows the text that cloud server is passed back, single
Sender's text viewing area is hit, the first client plays voice document automatically, and the second described client receives text
After file, text can be shown in described recipient's text viewing area.
The identification error correction method of the above-mentioned Real-time speech recognition error correction system based on cloud server, wherein, described
Step 3 in, send error correction after text after, described text editing button automatic hidden.
The identification error correction method of the above-mentioned Real-time speech recognition error correction system based on cloud server, wherein, described
Step 4 in, the second client is received after the text after error correction, the text after error correction can recipient's text text
Part viewing area is shown.
The identification error correction method of the above-mentioned Real-time speech recognition error correction system based on cloud server, wherein, it is described
First client and the second client can recognize the duration of voice document, and be shown in duration viewing area.
The present invention makes voice communication more convenient, and word can be directly generated by sending voice, and sender can change
Text, while cloud server can carry out error correction, improves audio identification efficiency.
Brief description of the drawings
Fig. 1 is the principle of Real-time speech recognition error correction system and identification error correction method of the present invention based on cloud server
Figure.
Embodiment
Embodiments of the invention are further illustrated below in conjunction with accompanying drawing.
Refer to shown in accompanying drawing 1, a kind of Real-time speech recognition error correction system based on cloud server, including the first client
Hold the 1, second client 2, cloud server 3, voice send button 4, duration viewing area 5, text editing button 6, recipient
Head portrait viewing area 7, sender's text viewing area 8, sender's head portrait viewing area 9, recipient's text are shown
Region 10；The first described client 1 and the second client 2 are bi-directionally connected with described cloud server 3 respectively, described language
Sound send button 4, duration viewing area 5 are separately positioned in the first described client 1 and the second client 2；Described text
This Edit button 6, sender's text viewing area 8 and sender's head portrait viewing area 9 are separately positioned on described first
In client 1, described recipient's text viewing area 10 and recipient's head portrait viewing area 7 is separately positioned on described
In second client 2.
A kind of identification error correction method of the Real-time speech recognition error correction system based on cloud server, this method at least includes
Following steps：
Step 1：Voice send button 4 is clicked on, the first client 1 receives voice and is recorded as voice document, unclamp voice and send
Button 4, the first client 1 sends voice document to cloud server 3.
Step 2：Voice document is resolved to text by cloud server 3, and text is sent to by cloud server 3
Voice document and text are sent to the second client 2 by the first client 1, cloud server 3.
Step 3：Sender checks that text has inerrancy, if text is wrong, clicks on text editing button 6 simultaneously
Error correction is carried out according to text, the text after correction can be shown in sender's text display area, and by after error correction
Text is sent to cloud server 3.
Step 4：Cloud server 3 updates speech recognition system according to the text after error correction, and by the text after renewal
This document is sent to the second client 2, and completion once communicates.
Step 5：Recipient's text viewing area 10 is clicked, the second client 2 plays voice document.
In described step 2, sender's text viewing area 8 of the first described client 1 shows high in the clouds clothes
The text that business device 3 is passed back, clicks sender's text viewing area 8, and the first client 1 plays voice document automatically,
Second client 2 is received after text, and text can be shown in recipient's text viewing area 10.
In described step 3, after the text after sending error correction, the described automatic hidden of text editing button 6.
When the phonetic recognization rate of cloud server 3 is higher, user can be set on backstage hides text editing button 6,
So display interface can be more succinct, with long-press or can double-click sender's text viewing area 8 when needing modification, enter
Compose a piece of writing this editor.
In described step 4, the second client 2 is received after the text after error correction, the text after error correction
It can be shown in recipient's text viewing area 10.Described the first client 1 and the second client 2 can recognize voice document
Duration, and be shown in duration viewing area 5.
Likewise, the second client 2 can also send voice to the first client 1, two-way instant messaging is carried out.
When the first client 1 or the second client 2 send a voice messaging, and it is connected to what cloud server 3 was transmitted
After text, the second client 2 or the first client 1 have a corresponding group information and shown, including：Delivery header picture shows
Show region 9, sender's text viewing area 8, duration viewing area 5, text editing button 6.
When the first client 1 or the second client 2 receive the voice document and text of the transmission of cloud server 3
Afterwards, have and a corresponding group information is shown, including：Recipient's head portrait viewing area 7, recipient's text viewing area
10th, duration viewing area 5.
In the present invention, the first client 1 and the second client 2 are in same chat environment, and the first client 1 can be with
Voice document is sent, and is modified to passing the text after speech recognition back, can also receive what other client was sent
Voice document and text.Second client 2 can receive the voice document and text that other client is sent, can be with
Voice document is sent, and is modified to passing the text after speech recognition back.
Cloud server 3, which is mainly, receives the voice document that client is sent, and voice document is identified as into text,
Text is sent to the client of sender, voice document and text are sent to the client of recipient, and is connect
Amended text is received, and speech recognition is upgraded.
Voice can be received by pinning voice send button 4, stop receiving voice after release, and voice document is sent into cloud
Hold server 3；Duration viewing area 5 mainly shows the time of voice document, passes through numerical monitor；Recipient can be in recipient
The text passed back is seen in text viewing area 10, when needing to listen to voice document, only need to click recipient's text
Document display area domain 10, you can play voice document.
In summary, the present invention makes voice communication more convenient, and word, and sender can be directly generated by sending voice
Text can be changed, while cloud server can carry out error correction, audio identification efficiency is improved.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize
The equivalent structure transformation that present specification is made, or directly or indirectly with the technology neck for being attached to other Related products
Domain, is included within the scope of the present invention.
Claims (6)
1. a kind of Real-time speech recognition error correction system based on cloud server, it is characterised in that：Including the first client, second
Client, cloud server, voice send button, duration viewing area, text editing button, sender's text viewing area
Domain, sender's head portrait viewing area, recipient's text viewing area and recipient's head portrait viewing area；The first described visitor
Family end and the second client are bi-directionally connected with described cloud server respectively, described voice send button, duration viewing area
Domain is separately positioned in the first described client and the second client；Described text editing button, sender's text
Viewing area and sender's head portrait viewing area are separately positioned in the first described client, described recipient's text
Viewing area and recipient's head portrait viewing area are separately positioned in the second described client.
2. a kind of identification error correction of Real-time speech recognition error correction system based on cloud server applied to described in claim 1
Method, it is characterised in that：This method at least comprises the following steps：
Step 1：Voice send button is clicked on, the first client receives voice and is recorded as voice document, unclamp voice transmission and press
Button, the first client sends voice document to cloud server；
Step 2：Voice document is resolved to text by cloud server, and text is sent to the first visitor by cloud server
Voice document and text are sent to the second client by family end, cloud server；
Step 3：Sender checks that text has inerrancy, if text is wrong, clicks on text editing button and basis
Text carries out error correction, and the text after error correction can show in sender's text display area, and by the text after error correction
File is sent to cloud server；
Step 4：Cloud server updates speech recognition system according to the text after error correction, and by the text after renewal
The second client is sent to, completion once communicates；
Step 5：Click recipient's text viewing area, the second client terminal playing voice document.
3. the identification error correction method of the Real-time speech recognition error correction system according to claim 2 based on cloud server,
It is characterized in that：In described step 2, sender's text viewing area of the first described client shows high in the clouds clothes
The text that business device is passed back, clicks sender's text viewing area, the first client plays voice document automatically, described
The second client receive after text, text can be shown in described recipient's text viewing area.
4. the identification error correction method of the Real-time speech recognition error correction system according to claim 2 based on cloud server,
It is characterized in that：In described step 3, after the text after sending error correction, described text editing button automatic hidden
Hide.
5. the identification error correction method of the Real-time speech recognition error correction system according to claim 2 based on cloud server,
It is characterized in that：In described step 4, the second client is received after the text after error correction, the text text after error correction
Part can be shown in recipient's text viewing area.
6. the identification error correction method of the Real-time speech recognition error correction system according to claim 2 based on cloud server,
It is characterized in that：Described the first client and the second client can recognize the duration of voice document, and be shown in duration and show
Region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710319312.2A CN107147564A (en) | 2017-05-09 | 2017-05-09 | Real-time speech recognition error correction system and identification error correction method based on cloud server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710319312.2A CN107147564A (en) | 2017-05-09 | 2017-05-09 | Real-time speech recognition error correction system and identification error correction method based on cloud server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107147564A true CN107147564A (en) | 2017-09-08 |
Family
ID=59777332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710319312.2A Pending CN107147564A (en) | 2017-05-09 | 2017-05-09 | Real-time speech recognition error correction system and identification error correction method based on cloud server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107147564A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062955A (en) * | 2017-12-12 | 2018-05-22 | 深圳证券信息有限公司 | A kind of intelligence report-generating method, system and equipment |
| CN109922371A (en) * | 2019-03-11 | 2019-06-21 | 青岛海信电器股份有限公司 | Natural language processing method, equipment and storage medium |
| CN110390930A (en) * | 2018-04-15 | 2019-10-29 | 高翔 | A kind of method and system of audio text check and correction |
| CN111382297A (en) * | 2018-12-29 | 2020-07-07 | 杭州海康存储科技有限公司 | Method and device for reporting user data of user side |
| CN112530435A (en) * | 2019-09-19 | 2021-03-19 | 比亚迪股份有限公司 | Data transmission method, device and system, readable storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010129056A2 (en) * | 2009-05-07 | 2010-11-11 | Romulo De Guzman Quidilig | System and method for speech processing and speech to text |
| CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技（深圳）有限公司 | Speech recognition method and server |
| CN106384593A (en) * | 2016-09-05 | 2017-02-08 | 北京金山软件有限公司 | Voice information conversion and information generation method and device |
| CN106412032A (en) * | 2016-09-14 | 2017-02-15 | 安徽声讯信息技术有限公司 | Remote audio character transmission method and system |
-
2017
- 2017-05-09 CN CN201710319312.2A patent/CN107147564A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010129056A2 (en) * | 2009-05-07 | 2010-11-11 | Romulo De Guzman Quidilig | System and method for speech processing and speech to text |
| CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技（深圳）有限公司 | Speech recognition method and server |
| CN106384593A (en) * | 2016-09-05 | 2017-02-08 | 北京金山软件有限公司 | Voice information conversion and information generation method and device |
| CN106412032A (en) * | 2016-09-14 | 2017-02-15 | 安徽声讯信息技术有限公司 | Remote audio character transmission method and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062955A (en) * | 2017-12-12 | 2018-05-22 | 深圳证券信息有限公司 | A kind of intelligence report-generating method, system and equipment |
| CN110390930A (en) * | 2018-04-15 | 2019-10-29 | 高翔 | A kind of method and system of audio text check and correction |
| CN111382297A (en) * | 2018-12-29 | 2020-07-07 | 杭州海康存储科技有限公司 | Method and device for reporting user data of user side |
| CN111382297B (en) * | 2018-12-29 | 2024-05-17 | 杭州海康存储科技有限公司 | User side user data reporting method and device |
| CN109922371A (en) * | 2019-03-11 | 2019-06-21 | 青岛海信电器股份有限公司 | Natural language processing method, equipment and storage medium |
| CN109922371B (en) * | 2019-03-11 | 2021-07-09 | 海信视像科技股份有限公司 | Natural language processing method, apparatus and storage medium |
| CN112530435A (en) * | 2019-09-19 | 2021-03-19 | 比亚迪股份有限公司 | Data transmission method, device and system, readable storage medium and electronic equipment |
| CN112530435B (en) * | 2019-09-19 | 2024-04-16 | 比亚迪股份有限公司 | Data transmission method, device and system, readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107147564A (en) | Real-time speech recognition error correction system and identification error correction method based on cloud server | |
| JP6575658B2 (en) | Voice control of interactive whiteboard equipment | |
| US8170872B2 (en) | Incorporating user emotion in a chat transcript | |
| US20170085506A1 (en) | System and method of bidirectional transcripts for voice/text messaging | |
| CN106782545B (en) | System and method for converting audio and video data into character records | |
| US9070369B2 (en) | Real time generation of audio content summaries | |
| CN107657471B (en) | Virtual resource display method, client and plug-in | |
| TWI616868B (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
| CN108028042A (en) | The transcription of verbal message | |
| CN105009599B (en) | The automatic mark of Wonderful time | |
| CN108597518A (en) | A kind of minutes intelligence microphone system based on speech recognition | |
| TWI619115B (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
| US20120197770A1 (en) | System and method for real time text streaming | |
| US20150149560A1 (en) | System and method for relaying messages | |
| US20150046164A1 (en) | Method, apparatus, and recording medium for text-to-speech conversion | |
| CN104050221A (en) | Automatic note taking within a virtual meeting | |
| TW201624470A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
| US20150066935A1 (en) | Crowdsourcing and consolidating user notes taken in a virtual meeting | |
| CN109361527A (en) | Voice conferencing recording method and system | |
| CN106131317A (en) | Automatically the method and system with return information is play | |
| CN113055529A (en) | Recording control method and recording control device | |
| CN104023127A (en) | Short message processing method and device | |
| US9507849B2 (en) | Method for combining a query and a communication command in a natural language computer system | |
| CN109873744A (en) | A kind of language conversion equipment | |
| CN108055192A (en) | Group's generation method, apparatus and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170908 |
|
| WD01 | Invention patent application deemed withdrawn after publication |