Method and system for achieving automatic voice classification

An automatic classification and speech technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of heavy manual workload and subjectivity of results, and achieve the effect of improving accuracy and reducing manual workload

Active Publication Date: 2016-03-23
IFLYTEK CO LTD
View PDF7 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The existing voice classification methods generally give the corresponding voice data types by manually listening to the

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 and system for achieving automatic voice classification
  • Method and system for achieving automatic voice classification
  • Method and system for achieving automatic voice classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0063] Such asfigure 1 Shown is the flow chart of the method for realizing automatic voice classification in the embodiment of the present invention, comprising the following steps:

[0064] Step 101, receiving speech data to be classified.

[0065] The voice data may be obtained from recordings, such as conference recordings, interview recordings, and the like.

[0066] Step 102, performing speech recognition on the to-be-classified speech data to obtain recognized text.

[0067] The specific recognition method is as follows: first, endpoint detection is performed on the speech data to obtain the starting point and the end point of the effective speech segment; then feature extraction is performed on the effec...

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 discloses a method and system for achieving automatic voice classification. The method includes the steps of receiving to-be-classified voice data, carrying out voice recognition on the to-be-classified voice data to obtain recognition texts, carrying out acoustic analysis on the to-be-classified voice data to obtain classification characteristics in acoustics, carrying out content analysis on the recognition texts to obtain classification characteristics in content, classifying the to-be-classified voice data by means of the classification characteristics in acoustics, the classification characteristics in content and a pre-built voice classification model to obtain the type of the to-be-classified voice data. By means of the method and system, workloads of workers can be reduced, and classification accuracy of the voice data is improved.

Description

technical field [0001] The invention relates to the field of voice signal processing, in particular to a method and system for realizing automatic voice classification. Background technique [0002] With the development of speech technology, automatic speech recognition technology has been widely used in various fields of life, and various practical speech recognition systems have emerged, such as speech transcription systems. However, due to different application requirements, speech recognition There are also various types of voice data, such as conference recordings and interview recordings in which many people speak. For different types of speech data, the content of the recognized text is quite different, and there are also many ways to display the recognized text. For example, the recognition result of the speech data of the dialogue type is "What are you eating at noon today? How about the beef noodles? It will take a long time to queue up." , you can queue up in adv...

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): G10L15/02G10L15/08G10L15/26
Inventor 胡尹潘青华高建清胡国平胡郁刘庆峰
Owner IFLYTEK CO LTD
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