A combined cepstral distance method for emotional speech recognition. (7th July 2017)

• Record Type: Journal Article
• Authors: Quan, Changqin; Zhang, Bin; Sun, Xiao; Ren, Fuji
• Is Part Of: International journal of advanced robotic systems. Volume 14:Number 4(2017:Jul./Aug.)
• Publication Date: 2017-07-07
• Subjects: Cepstral distance -- emotional speech recognition -- two-group classification -- principal component analysis; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.1177/1729881417719836
• Languages: English
• ISSNs: 1729-8806

Abstract

Affective computing is not only the direction of reform in artificial intelligence but also exemplification of the advanced intelligent machines. Emotion is the biggest difference between human and machine. If the machine behaves with emotion, then the machine will be accepted by more people. Voice is the most natural and can be easily understood and accepted manner in daily communication. The recognition of emotional voice is an important field of artificial intelligence. However, in recognition of emotions, there often exists the phenomenon that two emotions are particularly vulnerable to confusion. This article presents a combined cepstral distance method in two-group multi-class emotion classification for emotional speech recognition. Cepstral distance combined with speech energy is well used as speech signal endpoint detection in speech recognition. In this work, the use of cepstral distance aims to measure the similarity between frames in emotional signals and in neutral signals. These features are input for directed acyclic graph support vector machine classification. Finally, a two-group classification strategy is adopted to solve confusion in multi-emotion recognition. In the experiments, Chinese mandarin emotion database is used and a large training set (1134 + 378 utterances) ensures a powerful modelling capability for predicting emotion. The experimental results show that cepstral distance increases the recognition rate of emotion sad and can balance the recognition results with eliminating the over fitting. And for the German corpus Berlin emotional speech database, the recognition rate between sad and boring, which are very difficult to distinguish, is up to 95.45%.