Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer

doi:10.1049/cje.2020.00.080

	Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer
	Lin Long 1; Tan Liang 1,2
	2022
发表期刊	CHINESE JOURNAL OF ELECTRONICS
ISSN	1022-4653
卷号	31 期号:1 页码:155-167
摘要	Speech emotion recognition (SER) is the use of speech signals to estimate the state of emotion. At present, machine learning is one of the main research methods of SER, the test and training dataS of traditional machine learning all have the same distribution and feature space, but the data of speech is accessed from different environments and devices, with different distribution characteristics in real life. Thus, the traditional machine learning method is applied to the poor performance of SER. This paper proposes a multi-distributed SER method based on Mel frequency cepstogram (MFCC) and parameter transfer. The method is based on single-layer long short-term memory (LSTM), pre-trained inception-v3 network and multi-distribution corpus. The speech pre-processed MFCC is taken as the input of single-layer LSTM, and input to the pre-trained inception-v3 network. The features are extracted through the pre-trained inception-v3 model. Then the features are sent to the newly defined the fully connected layer and classification layer, let the parameters of the fully connected layer be fine-tuned, finally get the classification result. The experiment proves that the method can effectively complete the classification of multi-distribution speech emotions and is more effective than the traditional machine learning framework of SER.
关键词	Speech emotion recognition (SER) Machine learning Mel frequency cepstogram (MFCC) Parameter transfer Long short-term memory (LSTM) Inception-v3
DOI	10.1049/cje.2020.00.080
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61373162] ; Sichuan Science and Technology Support Project[2019YFG0183] ; Visual Computing and Virtual Reality Sichuan Provincial Key Laboratory Project[KJ201402]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000749672400018
出版者	WILEY
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19015
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tan Liang
作者单位	1.Sichuan Normal Univ, Sch Comp Sci, Chengdu 610101, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Lin Long,Tan Liang. Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer[J]. CHINESE JOURNAL OF ELECTRONICS,2022,31(1):155-167.
APA	Lin Long,&Tan Liang.(2022).Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer.CHINESE JOURNAL OF ELECTRONICS,31(1),155-167.
MLA	Lin Long,et al."Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer".CHINESE JOURNAL OF ELECTRONICS 31.1(2022):155-167.