Harmonic wave feature extracting method for irrelevant speech emotion recognition of speaker

A speech emotion recognition, speaker-independent technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of missing dynamic characteristics of speech signals

Active Publication Date: 2013-08-21
DEEPBLUE TECH (SHANGHAI) CO LTD
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such feature extraction methods lose the dynamic characteristics of the speech signal

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
  • Harmonic wave feature extracting method for irrelevant speech emotion recognition of speaker
  • Harmonic wave feature extracting method for irrelevant speech emotion recognition of speaker
  • Harmonic wave feature extracting method for irrelevant speech emotion recognition of speaker

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0023] The harmonic feature extraction method for speaker-independent speech emotion recognition of the present invention, its flow structure is shown in Figure 1, including feature extraction based on harmonic coefficient model, model training and recognition output based on support vector machine, etc. module. The harmonic feature extraction method includes the following steps: (1) constructing a harmonic coefficient model based on Fourier series; (2) extracting the harmonic coefficient characteristic parameters of the speech signal according to the harmonic coefficient model constructed in step ...

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 harmonic wave feature extracting method for irrelevant speech emotion recognition of a speaker. The harmonic wave feature extracting method comprises the following steps of (1) constructing a harmonic coefficient model based on a Fourier series, (2) extracting the characteristic parameters of the harmonic coefficients of speech signals to form characteristic vectors according to the constructed harmonic coefficient model, (3) inputting the characteristic vectors to a support vector machine (SVM) disaggregated model as data input, carrying out an irrelevant speech emotion recognition test of the speaker, and (4) outputting the effect of the characteristic parameters of the harmonic coefficients on the irrelevant speech emotion recognition of the speaker after training and testing. According to the harmonic wave feature extracting method for the irrelevant speech emotion recognition of the speaker, the characteristic parameters of the harmonic coefficients are applied to the irrelevant speech emotion recognition of the speaker, and a recognition rate is greatly improved.

Description

technical field [0001] The invention relates to a speech signal processing method, in particular to a harmonic feature extraction method for speaker-independent speech emotion recognition. Background technique [0002] With the continuous development of pattern recognition and emotional computing theory, the use of computers to automatically recognize the speaker's emotional state and changes from speech signals, that is, speech emotion recognition technology, has attracted the attention of many scholars. Speech, as an important medium of human communication, is the most basic way to transmit information between people. Speech signals not only convey the actual semantic content, but also contain rich emotional information. [0003] The research of speech emotion recognition has important practical significance for increasing the intelligence and humanization of computers, developing new man-machine environments, and promoting the development of psychology and other discipli...

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): G10L15/02
Inventor 王坤侠安宁李廉
Owner DEEPBLUE TECH (SHANGHAI) 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