Emotion speech recognition method based on natural language comprehension

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 ...

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

Images