Features importance analysis for emotional speech classification
ACII'05 Proceedings of the First international conference on Affective Computing and Intelligent Interaction
Implementing emotion-based user-aware e-learning
CHI '09 Extended Abstracts on Human Factors in Computing Systems
Emotion-oriented eCommerce systems
WSEAS TRANSACTIONS on SYSTEMS
Hi-index | 0.00 |
Speech emotion recognition, as a vital part of affective human computer interaction, has become a new challenge to speech processing. In this paper, a hybrid of hidden Markov models (HMMs) and artificial neural network (ANN) has been proposed to classify emotions, combining advantage on capability to dynamic time warping of HMM and pattern recognition of ANN. HMMs, which export likelihood probabilities and optimal state sequences, have been used to model speech feature sequences, while ANN has been employed to make a decision. The recognition result of the hybrid classification has been compared with the isolated HMMs by two speech corpora, Germany database and Mandarin database, and the average recognition rates have reached 83.8% and 81.6% respectively.