Emotion recognition of musical instruments based on convolution long short time memory depth neural network

Abstract

Abstract In this paper, a method of emotion recognition for musical instruments based on convolution long short time memory depth neural network is proposed, and an emotion recognition music database composed of four musical instruments is established, including keyboard instruments, wind instruments, string instruments and percussion instruments. The emotional types of these four instruments are divided into happiness, anger, sadness and fear. Through the establishment of CLDNN model based musical instrument emotion recognition architecture, MFCCs, CNN and CFS are used for feature extraction and training. The experimental structure shows that the best classification effect is to use long-term memory (LSTM) and deep neural network (DNN) to extract and combine the emotional feature sets of musical instruments, which has the highest accuracy. Considering the dynamic changes of musical features in musical instruments, the modeling method is used to predict the emotional changes of musical instruments.