In this contribution we introduce speech emotion recognition by use of continuous hidden Markov models. Two methods are propagated and compared throughout the paper. Within the first method a global statistics framework of an utterance is classified by Gaussian mixture models using derived features of the raw pitch and energy contour of the speech signal. A second method introduces increased temporal complexity applying continuous hidden Markov models considering several states using low-level instantaneous features instead of global statistics. The paper addresses the design of working recognition engines and results achieved with respect to the alluded alternatives. A speech corpus consisting of acted and spontaneous emotion samples in German and English language is described in detail. Both engines have been tested and trained using this equivalent speech corpus. Results in recognition of seven discrete emotions exceeded 86% recognition rate. As a basis of comparison the similar judgment of human deciders classifying the same corpus at 79.8% recognition rate was analyzed.
[1]
Noam Amir,et al.
Classifying emotions in speech: a comparison of methods
,
2001,
INTERSPEECH.
[2]
Albino Nogueiras,et al.
Speech emotion recognition using hidden Markov models
,
2001,
INTERSPEECH.
[3]
B. Schuller,et al.
Towards intuitive speech interaction by the integration of emotional aspects
,
2002,
IEEE International Conference on Systems, Man and Cybernetics.
[4]
George N. Votsis,et al.
Emotion recognition in human-computer interaction
,
2001,
IEEE Signal Process. Mag..
[5]
Björn W. Schuller,et al.
Multimodal emotion recognition in audiovisual communication
,
2002,
Proceedings. IEEE International Conference on Multimedia and Expo.
[6]
T. S. Polzin,et al.
Verbal and non-verbal cues in the communication of emotions
,
2000,
2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).