HMM-Based Speaker Emotional Recognition Technology for Speech Signal

Abstract:

In emotion classification of speech signals, the popular features employed are statistics of fundamental frequency, energy contour, duration of silence and voice quality. However, the performance of systems employing these features degrades substantially when more than two categories of emotion are to be classified. In this paper, a text independent method of emotion classification of speech is proposed. The proposed method makes use of short time log frequency power coefficients(LFPC) to represent the speech signals and a discrete Hidden Markov Model (HMM) as the classifier. The category labels used are, the archetypal emotions of anger, joy, sadness and neutral. Results show that the proposed system yields an average accuracy of 82.55%and the best accuracy of 94.4% in the classification of 4 emotions. Results also reveal that LFPC is a better choice as feature parameters for emotion classification than the traditional feature parameters.

• Periodical: Advanced Materials Research (Volumes 230-232)
• Pages: 261-265
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.230-232.261
• Online since: May 2011
• Authors: Yu Qiang Qin, Xue Ying Zhang
• Keywords: Emotional Feature Vector, HMM, Log Frequency Power Coefficients (LFPC), Speech Emotional Recognition

References

[1] Thomas F.Quatieri: Discrete-Time Speech Signal Processing : Principles and Practice[M]. Beijing: Publishing House of Electronics Industry(2004)468-488.

[2] D.Morrison, R.Wang, et al: Ensemble methods for spoken emotion recognition in call-centres, Speech communication 49 (2007) 98–112.

DOI: 10.1016/j.specom.2006.11.004

[3] Schuller R., Rigoll G., Lang M: Hidden Markov model-based speech emotion recognition, Porceeding of IEEE ICASSP Conference, Vol.2, 6-10(2003)pp.1-4.

DOI: 10.1109/icassp.2003.1202279

[4] C.-W. Hsu, C.-J. Lin: A comparison of methods for multi-class support vector machines, IEEE Transactions on Neural Networks(2002) pp.415-425.

DOI: 10.1109/72.991427

[5] M.Cernak, C.Wellekens: Emotional aspects of intrinsic speech variabilities in automatic speech recognition, in: International Conference on Speech and Computer (2006) p.405–408.

[6] M.Lugger, B.Yang: Psychological motivated multi-stage emotion classification exploiting voice quality features, in: F.Mihelic, J. Zibert (Eds.), Speech Recognition, In-Tech, (2008)Chapter22.

DOI: 10.5772/6383

[7] Y.Xu, S.Chuenwattanapranithi: Perceiving anger and joy in speech through the size code, in: Proceedings of the International Conference on Phonetic Sciences(2007) p.2105–2108.

[8] B.Schuller, D.Arsic, et al.: Emotion recognition in the noise applying large acoustic feature sets, in: Speech Prosody, Dresden(2006)pp.276-289.