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
CN103258531AActive Publication Date: 2013-08-21DEEPBLUE TECH (SHANGHAI) CO LTD
4 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
DEEPBLUE TECH (SHANGHAI) CO LTD
Publication Date
2013-08-21

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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