Summary and Conclusions - Robust Emotion Recognition Using Spectral and Prosodic Features - page 105

spurious peaks are detected as the formants. Using an efficient formant detection
technique may improve emotion recognition performance further.

￿ Most of today's emotion recognition systems experience a high influence of

speaker specific information during emotion classification. In the present work,
we normalized the features to minimize speaker dependent information. This is
not proved to be an efficient method to nullify speaker specific information. An
efficient technique may be developed to remove speaker specific information from
the speech utterances.

References

1. S.G. Koolagudi, K.S. Rao, Emotion recognition from speech using sub-syllabic and pitch syn-
chronous spectral features. Int. J. Speech Technol. 15 , 495-511, (Springer, Dec 2012). doi: 10.
1007/s10772-012-9150-8
2. K.S. Rao, S.G. Koolagudi, R. R. Vempada, Emotion recognition from speech using global and
local prosodic features. Int. J. Speech Technol. 15 , (Springer, Aug 2012). doi: 10.1007/s10772-
012-9172-2
3. S.G. Koolagudi, K.S. Rao, Emotion recognition from speech using source, system and prosodic
features. Int. J. Speech Technol. 15 (3), 265-289, (Springer , 2012)
4. S.G. Koolagudi, K.S. Rao, Two stage emotion recognition based on speaking rate. Int. J. Speech
Technol. 14 , 35-48 (Mar 2011)
5. S.G. Koolagudi, A. Barthwal, S. Devliyal, K.S. Rao, Real life emotion classification from speech
using gaussian mixture models, in Communications in Computer and Information Science:
Contemporary Computing , ed. by M. Parashar, D. Kaushik, O. F. Rana, R. Samtaney, Y. Yang,
A. Zomaya, vol. 306 (Springer, New York, Aug 6-8 2012) pp. 250-261
6. S.G. Koolagudi, S. Devliyal, A. Barthwal, K.S. Rao, Emotion recognition from semi natural
speech using artificial neural networks and excitation source features, in Communications in
Computer and Information Science: Contemporary Computing , ed. by M. Parashar, D. Kaushik,
O. F. Rana, R. Samtaney, Y. Yang, A. Zomaya, vol. 306 (Springer, New York, Aug 6-8 2012),
pp. 273-282