Emotion speech recognition method based on natural language comprehension

A speech emotion recognition and emotion technology, applied in the field of speech emotion recognition based on natural language understanding, can solve problems such as low correlation between speech and emotion features, lack of natural speech emotion recognition, and inability to understand speech emotion signals, etc., to achieve Strong naturalness, high correlation, and reduced complexity

Active Publication Date: 2012-10-10
WUHAN UNIV OF SCI & TECH
View PDF3 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] To sum up, the following problems exist in the existing speech emotion recognition: the naturalness of speech emotion recognition is not strong; the correlation between speech and emotional features in emotional speech is not high, resulting in the inability to understand the overall speech emotion 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
  • Emotion speech recognition method based on natural language comprehension

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0022] A speech emotion recognition method based on natural speech understanding. The method as figure 1 Shown: First, the voice emotion signal is collected through the microphone, and the collected voice emotion signal is preprocessed and feature extracted. The preprocessing includes sampling and quantization, pre-emphasis, framing and windowing; feature extraction includes extracting the voice duration , Pitch frequency, prosodic characteristics of energy (amplitude), formant parameters, and sound quality characteristics of MEL frequency cepstral coefficient. Then calculate the degree of distortion of the collected speech emotion signal through syntactic emotion analysis, and obtain the emotion feature vector; then enter the training stage and the recognition stage respectively, and finally combine the emotion feature vector after the natural lang...

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 an emotion speech recognition method based on natural language comprehension. The technical scheme comprises firstly collecting emotion speech signals through a microphone, conducting pretreatment and feature extraction on the collected emotion speech signals, calculating distortion degree of the collected emotion speech signals through sentence structure emotional analysis, and determining an emotion feature vector; then respectively entering a training phase and a recognition phase; and finally conducting model matching between the emotion feature vector after the natural language comprehension and the emotion feature vector in an emotion speech base to obtain recognition results. The training phase firstly adopts emotion classification to classify the emotion feature vector, then conducts model train and finally builds the emotion speech base; and the recognition phase adopts semantic analysis and pragmatics analysis to conduct natural language comprehension on the emotion feature vector. The emotion speech recognition method is strong in naturalness of the emotion speech recognition, can integrally comprehend the emotion speech signals, and improves recognition rate of the emotion speech signals.

Description

technical field [0001] The invention belongs to the technical field of speech emotion recognition. Specifically, it relates to a speech emotion recognition method based on natural speech understanding. Background technique [0002] With the rapid development of computer network communication technology and multimedia technology, human-computer interaction technology has gradually become a very important aspect in the field of artificial intelligence, especially the rise of digital entertainment, the gradual popularization of smart home appliances and the increasing generalization of computers, making human The naturalness and intelligence of computer interaction are very important. The processing of emotional information is an important topic to improve the ability of human-computer interaction. Therefore, how to improve the adaptability of speech emotion recognition technology to the change of user's emotional state in human-computer interaction is increasingly urgent, so ...

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): G10L15/02G10L15/06
Inventor 吴怀宇罗鸣杜钊君
Owner WUHAN UNIV OF SCI & TECH
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