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

Device and method for acquiring speech recognition multi-information text

A text acquisition and multi-information technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem that valuable information cannot be realized

Active Publication Date: 2011-11-09
SHANGHAI GUOKE ELECTRONICS
View PDF7 Cites 68 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a voice recognition multi-information text acquisition device and method to solve the problem that the text information acquired by voice recognition technology in the prior art can only be pure text information, and many valuable texts in the voice The problem that the information cannot be realized in the text information after speech recognition

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
  • Device and method for acquiring speech recognition multi-information text
  • Device and method for acquiring speech recognition multi-information text
  • Device and method for acquiring speech recognition multi-information text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The plain text information and single-character pronunciation time generating module are used to convert the speech audio into plain text information through speech recognition, and are used to obtain the single-character pronunciation time in the speech audio, that is, the start time and end time of the single-character pronunciation, and then through the said The length of single word pronunciation time determines single word pronunciation speech rate. The pronunciation time of the single character is automatically obtained during the voice recognition process while converting the voice audio into plain text information.

[0033] The multi-information text generation module is used to integrate the information on the pronunciation and speech rate of a single character in the plain text information to generate multi-information text information.

[0034] According to the obtained single-character pronunciation and speech rate, the speech rate is expressed by changing t...

Embodiment 2

[0041] The plain text information and single-character pronunciation time generating module are used to convert the voice audio into plain text information through speech recognition, and are used to obtain the single-character pronunciation time in the voice audio, that is, the start time and end time of the single-character pronunciation, and then through the said The length of single word pronunciation time determines single word pronunciation speech rate. The pronunciation time of the single character is automatically obtained during the voice recognition process while converting the voice audio into plain text information.

[0042] The word pronunciation strength calculation module is used to calculate the word pronunciation strength according to the obtained word pronunciation time. The pronunciation strength of each character can be obtained by calculating the mean value of the pronunciation strength within the time period of the pronunciation of the single character by...

Embodiment 3

[0064] Step 1, convert the speech audio into plain text information through speech recognition, and obtain the pronunciation time of the single character in the speech audio at the same time, that is, the start time and end time of the pronunciation of the single character, and then determine the speech rate of the pronunciation of the single character through the length of the pronunciation time of the single character . The pronunciation time of the single character is automatically obtained during the voice recognition process while converting the voice audio into plain text information.

[0065] Step 2: Integrating the information on the pronunciation and speech rate of a single character in the plain text information to generate multi-information text information.

[0066] Embodiment Four

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 provides a device and a method for acquiring a speech recognition multi-information text. After a speech audio frequency is converted into pure text information by speech recognition, individual character pronunciation speed, individual character pronunciation strength and individual character pronunciation intonation in the speech audio frequency are integrated into the initially-generated pure text information in a certain expression way to generate multi-information text information. The device and the method for acquiring the speech recognition multi-information text can be widely used for information release platforms such as micro blogs, short messages, signature files and the like.

Description

technical field [0001] The invention relates to the technical field of computer speech recognition, in particular to a speech recognition multi-information text acquisition device and method. Background technique [0002] In the past two decades, speech recognition technology has made remarkable progress and has been widely used. It is estimated that in the next 10 years, speech recognition technology will enter various fields such as industry, home appliances, communications, automotive electronics, medical care, home services, and consumer electronics. [0003] The so-called speech recognition refers to the automatic understanding of human speech by computers or machines. For example, by using speech recognition, a computer or machine can be operated according to human speech, or human speech can be converted into characters. The main method used in speech recognition is to extract the physical characteristics such as the frequency spectrum of the emitted speech, and com...

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): G10L15/26G10L15/02G10L15/18
Inventor 张峰黄伟
Owner SHANGHAI GUOKE ELECTRONICS
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