An Experiment with Evaluation of Emotional Speech Conversion by Spectrograms

Přibil, J.; Přibilová, A.

doi:10.2478/v10048-010-0017-3

Abstract

The spectrogram is a useful tool for visual quality comparison of different types of emotional synthetic speech. This paper is focused on application of this method to evaluation of sentences after spectral and prosodic modifications for emotional speech conversion. Performed experiments with spectrogram evaluation for several male and female speakers and four emotional states (joy, sadness, anger, neutral state) are also described.

References

Möller, S., Jekosch, U., Mersdorf, J., Kraft, V. (2001). Auditory assessment of synthetized speech in application scenarios: two case studies. Speech Communication, 34, 229-246.10.1016/S0167-6393(00)00036-4
Search in Google Scholar
Audibert, N., Vincent, D., Aubergé, V., Rosec, O. (2006). Evaluation of expressive speech resynthesis. In LREC 2006: Workshop on Emotional Corpora. Genova, Italy, 37-40.
Search in Google Scholar
Gobl, C., Ní Chasaide, A. (2003). The role of voice quality in communicating emotion, mood and attitude. Speech Communication, 40, 189-212.10.1016/S0167-6393(02)00082-1
Search in Google Scholar
Tučková, J., Holub, J., Duběda, T. (2009). Technical and phonetic aspects of speech quality assessment: the case of prosody synthesis. In Esposito, A., Vích, R. (eds.) Cross-Modal Analysis of Speech, Gesture, Gaze and Facial Expressions. Lecture Notes in Artificial Intelligence 5641. Berlin Heidelberg: Springer-Verlag, 106-115.10.1007/978-3-642-03320-9_13
Search in Google Scholar
Přibilová, A., Přibil, J. (2006). Non-linear frequency scale mapping for voice conversion in text-to-speech system with cepstral description. Speech Communication, 48, 1691-1703.10.1016/j.specom.2006.08.001
Search in Google Scholar
Přibil, J., Přibilová, A. (2008). Application of expressive speech in TTS system with cepstral description. In Esposito, A. et. al (eds.) Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction 2007. Lecture Notes in Artificial Intelligence 5042. Berlin Heidelberg: Springer-Verlag, 201-213.10.1007/978-3-540-70872-8_15
Search in Google Scholar
Volaufová, J. (2005). Statistical methods in biomedical research and measurement science. Measurement Science Review, 5 (1), 1-10.
Search in Google Scholar
Hartung, J., Makambi, H. K, Arcac, D. (2001). An extended ANOVA F-test with applications to the heterogeneity problem in meta-analysis. Biometrical Journal, 43 (2), 135-146.10.1002/1521-4036(200105)43:2<135::AID-BIMJ135>3.0.CO;2-H
Search in Google Scholar
Welch, P. D. (1967). The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Transactions on Audio and Electroacoustics, AU-15, 70-73.10.1109/TAU.1967.1161901
Search in Google Scholar
Stoica, P., Moses, R. L. (1997). Introduction to Spectral Analysis. Prentice-Hall, 52-54
Search in Google Scholar
Slifka, J., Anderson, T. R. (1995). Speaker modification with LPC pole analysis. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Detroit, 644-647.10.1109/ICASSP.1995.479680
Search in Google Scholar
Přibilová, A., Přibil, J. (2009). Spectrum modification for emotional speech synthesis. In Esposito, A. et. al. (eds.) Multimodal Signals: Cognitive and Algorithmic Issues. Lecture Notes in Artificial Intelligence 5398. Berlin Heidelberg: Springer-Verlag, 232-241.10.1007/978-3-642-00525-1_23
Search in Google Scholar
Přibilová, A., Přibil, J. (2009). Harmonic model for female voice emotional synthesis. In Fierrez, J. et al. (eds.) Biometric ID Management and Multimodal Communication. Lecture Notes in Artificial Intelligence 5707. Berlin Heidelberg: Springer-Verlag, 49-56.10.1007/978-3-642-04391-8_6
Search in Google Scholar
Scherer, K. R. (2003). Vocal communication of emotions: review of research paradigms. Speech Communication, 40, 227-256.10.1016/S0167-6393(02)00084-5
Search in Google Scholar
Benesty, J., Sondhi, M. M., Huang, Y. (eds.) (2008). Springer Handbook of Speech Processing. Berlin Heidelberg: Springer-Verlag.10.1007/978-3-540-49127-9
Search in Google Scholar
Khuri, A. I., Mathew, T., Sinha, B. K. (1998). Statistical Tests for Mixed Models. New York: John Wiley & Sons.
Search in Google Scholar
Srinivasan, S., DeLiang, W. (2010). Robust speech recognition by integrating speech separation and hypothesis testing. Speech Communication, 52, 72-81.10.1016/j.specom.2009.08.008
Search in Google Scholar
Atassi, H., Smékal, Z. (2008). Real-time model for automatic vocal emotion recognition. In Proceedings of the 31st International Conference on Telecommunications and Signal Processing. Parádfürdö, Hungary, 21-25.
Search in Google Scholar

An Experiment with Evaluation of Emotional Speech Conversion by Spectrograms

Abstract

Paradigm

My account