Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Continuous voice recognition method and system

A speech recognition and speech technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of high error rate of text information

Pending Publication Date: 2018-11-20
CHONGQING YOUBANJIA TECH CO LTD
View PDF16 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is to provide a continuous speech recognition system to solve the problem of high error rate of text information recognized by speech information after users who cannot speak continuously input speech information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Continuous voice recognition method and system
  • Continuous voice recognition method and system
  • Continuous voice recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Such as figure 1 Shown: a continuous speech recognition system, including: including a user terminal and a server. The server and the user terminal communicate through the wireless communication module, and the wireless communication module can be selected from the existing DX-BT18 bluetooth communication module. The user terminal can be a robot, a mobile phone or other electronic devices that can be carried by the user.

[0028] User terminals include:

[0029] The voice collection module is used for collecting the voice information when the user speaks in real time, and sending the collected voice information to the server.

[0030] The analysis text information output module is used to receive the text information sent by the voice analysis module, and display the text information after receiving the text information.

[0031] The voice collection interruption module is used for the user to set the interruption of the voice collection when the pause time of the vo...

Embodiment 2

[0044] The difference between Embodiment 2 and Embodiment 1 is that in Embodiment 2, in order to enable the parsed text information to be output quickly, the voice information processing module arranges the voice information in the time list, and the user pauses The corresponding voice sequence is edited and combined with one voice information at the same time, and the combined voice information is analyzed, that is, the voice information edited and combined first is analyzed first, and the combined voice information is analyzed later. In addition, the analyzed text information can also be quickly corrected according to the existing speech error correction method, such as the speech recognition method disclosed by the publication number CN103021412A.

Embodiment 3

[0046] Such as image 3 As shown, the difference between Embodiment 3 and Embodiment 2 is that in Embodiment 3, the user terminal further includes:

[0047] The chat module is used for users to add friends and chat with friends in different chat interfaces. When a user chats with a friend, a friend corresponds to a chat interface. In the chat interface, the user can send voice messages and text messages, and the user's friends can also send text messages and voice messages.

[0048] The friend name remark module is used for the user to remark the name of each friend, and a friend corresponds to a name.

[0049] The voice continuous input jump module is used for the user to switch between multiple chat interfaces at the same time to realize chatting with different friends. After the user enters the friend name remarked on the friend name remark module through the voice collection module, the user chats with the friend When the interface is opened, the parsed text information ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of voice recognition technology and specifically relates to a continuous voice recognition method and system. The continuous voice recognition system includes a voice information processing module and a voice analyzing module. The voice information processing module is used for sorting voice information input intermittently by a user into a voice sequence according to voice information collection time in a time list and editing the voice sequence corresponding to a short part of the user, synthesizing the edited voice information to continuous voiceinformation and sending the synthesized continuous voice information to a voice analyzing module for voice recognition and analysis. The scheme provided by the invention is suitable for use by userscapable of speaking continuously and is also suitable for use by users incapable of speaking continuously.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a continuous speech recognition method and system. Background technique [0002] With the development of speech technology, automatic speech recognition technology has been widely used in various fields of life. Converting speech into text greatly facilitates people's daily needs, such as converting meeting recordings into text and sending them to participants as meeting minutes ; Convert the recordings of interviews with journalists into texts, and then edit them into press releases, etc. However, when converting speech information into text, errors often occur in the converted text. [0003] In order to convert speech information into text information, the Chinese patent document with the publication number CN107305541A discloses a speech recognition text segmentation method and device. The method includes: performing endpoint detection on the speech data to obtain ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L15/22G10L15/26G10L15/30
CPCG10L15/22G10L15/222G10L15/30G10L2015/223G10L15/26
Inventor 潘晓明
Owner CHONGQING YOUBANJIA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com