Speech emotion recognition with unsupervised feature learning

• Published in: Frontiers of information technology & electronic engineering Vol. 16; no. 5; pp. 358 - 366
• Main Authors: Huang, Zheng-wei, Xue, Wen-tao, Mao, Qi-rong
• Format: Journal Article
• Language: English
• Published: Hangzhou Zhejiang University Press 01.05.2015; Springer Nature B.V
• Subjects: Algorithms; Cluster analysis; Clustering; Cognitive tasks; Communications Engineering; Computer Hardware; Computer Science; Computer Systems Organization and Communication Networks; Electrical Engineering; Electronic engineering; Electronics and Microelectronics; Emotion recognition; Emotions; Feature recognition; Information technology; Instrumentation; Learning; Machine learning; Networks; Nodes; Performance enhancement; Performance evaluation; Speech; Speech recognition; Vector quantization; Unsupervised feature learning; Neural network; Affect computing; Speech emotion recognition
• ISSN: 2095-9184; 2095-9230
• DOI: 10.1631/FITEE.1400323

Emotion-based features are critical for achieving high performance in a speech emotion recognition （SER） system. In general, it is difficult to develop these features due to the ambiguity of the ground-truth. In this paper, we apply several unsupervised feature learning algorithms （including K-means clustering, the sparse auto-encoder, and sparse restricted Boltzmann machines）, which have promise for learning task-related features by using unlabeled data, to speech emotion recognition. We then evaluate the performance of the proposed approach and present a detailed analysis of the effect of two important factors in the model setup, the content window size and the number of hidden layer nodes. Experimental results show that larger content windows and more hidden nodes contribute to higher performance. We also show that the two-layer network cannot explicitly improve performance compared to a single-layer network.