Method for improving text and voice matching efficiency

A text and voice technology, applied in the field of improving the efficiency of text and voice matching, can solve the problems of inefficiency, low matching efficiency, error-prone, etc., and achieve high efficiency

Inactive Publication Date: 2008-05-28
陈健全
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are some programs that can help people match text and speech, but these programs require human intervention, that is, copying and pasting text by hand
The general steps are as follows: first listen to a piece of audio, look at the time, write down the time difference between the end of the audio and the beginning of the audio, then select, copy and paste the text, and insert the time after the text (such as the lyrics file format, "how are you doing? [ 00:21.18]"), which is tedious, inefficient, and error-prone
[0003] According to the research of the inventor, the reason for the low matching efficiency is human intervention. The two bottleneck steps of the existing method are to manually determine the end of the sentence and record the time difference , and actions such as selecting, copying, and pasting text

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
  • Method for improving text and voice matching efficiency
  • Method for improving text and voice matching efficiency
  • Method for improving text and voice matching efficiency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Using speech recognition software to analyze speech and audio files, the recognized text files and corresponding time stamps can be obtained. Generally speaking, when speech recognition software recognizes the voice of a non-specific person, the accuracy rate is often not high. For example, the speaker's pronunciation is not standard or the speech speed is relatively fast, resulting in inaccurate recognition of the text, which may be as low as 50%. , or even lower. The invention further compares and aligns the recognized text with the text provided by the user, and then matches the time stamp provided by the recognition software with the text provided by the user, that is, realizes the so-called automatic matching of text and voice. After actual testing, the accuracy of automatic matching is acceptable to users. The steps of the method of the present invention are specifically described as follows:

[0026] 1) Corresponding to the same voice and audio file, input the ...

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 a method of improving the efficiency of a text matching with voice matching, which includes the following steps: Step 1: a voice recognition software can be used for identifying an audio file to get a text with a timestamp; Step 2: the text with a timestamp is compared with a text input by a user; Step 3: the time-stamp of the text with a timestamp can be endowed to the text input by the user. With high efficiency, the method does not need the manual intervention and can match the voice and text files in a largebatch way.

Description

technical field [0001] The invention relates to a method for improving text and voice matching efficiency. Background technique [0002] When practicing foreign language listening, we need to know the corresponding text of the foreign language being played, so as to know the degree of our understanding. For example, the computer is playing a recording of "how are you dong?" Some people may only understand one or two words. If they don't see the text of "how are you dong?", they don't know what they understand. degree. There are some programs that can help people match text and speech, but these programs require human intervention, that is, manually copying and pasting text. The general steps are as follows: first listen to a piece of audio, look at the time, write down the time difference between the end of the audio and the beginning of the audio, then select, copy and paste the text, and insert the time after the text (such as the lyrics file format, "how are you doing? ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/08G10L15/26G10L15/00G10L15/28G10L13/00
Inventor 陈健全
Owner 陈健全
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap