Title :
Emotion Recognition through Speech Signal for Human-Computer Interaction
Author :
Lalitha, S. ; Patnaik, Sahruday ; Arvind, T.H. ; Madhusudhan, Vivek ; Tripathi, Shikha
Author_Institution :
Dept. of ECE, Amrita Vishwa Vidyapeetham, Bangalore, India
Abstract :
This paper aims at developing a Speaker Emotion Recognition (SER) system to recognize seven different emotions namely anger, boredom, fear, disgust, happiness, neutral and sadness with a generalized feature set in real-time. Continuous HMM and LIBSVM classifiers are considered in this paper. The choice of LIBSVM classifier provides better recognition rates for few emotions (Anger and Fear) compared to the Continuous HMM classifier used in the earlier work by Xiang Li. The Hilbert-Huang transform (HHT) and Teager Energy Operator (TEO) based features gives the advantage of self-adaptability and hence can be used for real time applications.
Keywords :
Hilbert transforms; hidden Markov models; human computer interaction; signal classification; speaker recognition; support vector machines; HHT; Hilbert-Huang transform; LIBSVM classifiers; continuous HMM classifier; generalized feature set; human-computer interaction; speaker emotion recognition system; speech signal; teager energy operator based features; Emotion recognition; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Speech; Speech recognition; Transforms; Empirical Mode Decomposition; Hilbert Huang Transform; Instantaneous Frequency; Intrinsic Mode Function; Speaker Emotion Recognition; TEO;
Conference_Titel :
Electronic System Design (ISED), 2014 Fifth International Symposium on
Print_ISBN :
978-1-4799-6964-7
DOI :
10.1109/ISED.2014.54
