Tibetan speech emotion recognition method based on CNN and LSTM

Abstract

The invention discloses a Tibetan speech emotion recognition method based on CNN and LSTM, belonging to the technical field of speech emotion recognition. The method comprises the following steps: building a Tibetan speech emotion corpus; preprocessing Tibetan speech data in the Tibetan speech emotion corpus; performing feature extraction on the Tibetan speech data in the preprocessed Tibetan speech emotion corpus to obtain a Tibetan speech spectrum; training a Tibetan speech emotion recognition network according to the Tibetan speech spectrum to obtain a trained Tibetan speech emotion recognition network; and inputting Tibetan speech data needing to be recognized into the trained Tibetan speech emotion recognition network after being subjected to preprocessing and feature extraction so as to obtain a Tibetan speech emotion classification result corresponding to the Tibetan speech data. According to the Tibetan speech emotion recognition method based on the CNN and the LSTM, the problem of Tibetan speech emotion recognition is solved.

Description

technical field [0001] The invention belongs to the technical field of speech emotion recognition, in particular to a method for recognizing Tibetan speech emotion based on CNN and LSTM. Background technique [0002] Speech emotion recognition is a computer simulation of the process of human emotion perception and understanding. Its task is to extract the acoustic features expressing emotion from the collected voice signals, and find out the mapping relationship between these acoustic features and human emotions, and then through this Mapping relationship, identifying the input voice signal, to achieve the purpose of human-computer interaction, and Tibetan speech emotion recognition is a special case of speech emotion recognition, that is, using Tibetan speech with emotion as input, so that the computer can build the basis of the mapping relationship It recognizes Tibetan speech with emotion on the Internet to realize human-computer interaction. [0003] In recent years, wi...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned deficiencies in the prior art, a kind of Tibetan speech emotion recognition method based on CNN and LSTM provided by the present invention solves the problem for Tibetan speech emotion recognition question

Images