Spectrum Modification for Emotional Speech Synthesis

  • Anna Přibilová
  • Jiří Přibil
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5398)


Emotional state of a speaker is accompanied by physiological changes affecting respiration, phonation, and articulation. These changes are manifested mainly in prosodic patterns of F0, energy, and duration, but also in segmental parameters of speech spectrum. Therefore, our new emotional speech synthesis method is supplemented with spectrum modification. It comprises non-linear frequency scale transformation of speech spectral envelope, filtering for emphasizing low or high frequency range, and controlling of spectral noise by spectral flatness measure according to knowledge of psychological and phonetic research. The proposed spectral modification is combined with linear modification of F0 mean, F0 range, energy, and duration. Speech resynthesis with applied modification that should represent joy, anger and sadness is evaluated by a listening test.


emotional speech spectral envelope speech synthesis emotional voice conversion 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Scherer, K.R.: Vocal Communication of Emotion: A Review of Research Paradigms. Speech Communication 40, 227–256 (2003)CrossRefzbMATHGoogle Scholar
  2. 2.
    Nwe, T.L., Foo, S.W., De Silva, L.C.: Speech Emotion Recognition Using Hidden Markov Models. Speech Communication 41, 603–623 (2003)CrossRefGoogle Scholar
  3. 3.
    Ververidis, D., Kotropoulos, C.: Emotional Speech Recognition: Resources, Features, and Methods. Speech Communication 48, 1162–1181 (2006)CrossRefGoogle Scholar
  4. 4.
    Shami, M., Verhelst, W.: An Evaluation of the Robustness of Existing Supervised Machine Learning Approaches to the Classification of Emotions in Speech. Speech Communication 49, 201–212 (2007)CrossRefGoogle Scholar
  5. 5.
    Tóth, S.L., Sztahó, D., Vicsi, K.: Speech Emotion Perception by Human and Machine. In: Esposito, A., Bourbakis, N.G., Avouris, N., Hatzilygeroudis, I. (eds.) Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction. LNCS (LNAI), vol. 5042, pp. 213–224. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Murray, I.R., Arnott, J.L.: Applying an Analysis of Acted Vocal Emotions to Improve the Simulation of Synthetic Speech. Computer Speech and Language 22, 107–129 (2008)CrossRefGoogle Scholar
  7. 7.
    Bänziger, T., Scherer, K.R.: The Role of Intonation in Emotional Expressions. Speech Communication 46, 252–267 (2005)CrossRefGoogle Scholar
  8. 8.
    Vích, R.: Cepstral Speech Model, Padé Approximation, Excitation, and Gain Matching in Cepstral Speech Synthesis. In: Proceedings of Biosignal, Brno, pp. 77–82 (2000)Google Scholar
  9. 9.
    Fant, G.: Acoustical Analysis of Speech. In: Crocker, M.J. (ed.) Encyclopedia of Acoustics, pp. 1589–1598. John Wiley & Sons, Chichester (1997)CrossRefGoogle Scholar
  10. 10.
    Fant, G.: Speech Acoustics and Phonetics. Kluwer Academic Publishers, Dordrecht (2004)Google Scholar
  11. 11.
    Laroche, J.: Time and Pitch Scale Modification of Audio Signals. In: Kahrs, M., Brandenburg, K. (eds.) Applications of Digital Signal Processing to Audio and Acoustics, pp. 279–309. Kluwer Academic Publishers, Dordrecht (2001)Google Scholar
  12. 12.
    Morrison, D., Wang, R., De Silva, L.C.: Ensemble Methods for Spoken Emotion Recognition in Call-Centres. Speech Communication 49, 98–112 (2007)CrossRefGoogle Scholar
  13. 13.
    Dutilleux, P., Zölzer, U.: Filters. In: Zölzer, U. (ed.) DAFX – Digital Audio Effects, pp. 31–62. John Wiley & Sons, Chichester (2002)Google Scholar
  14. 14.
    Drioli, C., Tisato, G., Cosi, P., Tesser, F.: Emotions and Voice Quality: Experiments with Sinusoidal Modeling. In: Proceedings of Voice Quality, Geneva, pp. 127–132 (2003)Google Scholar
  15. 15.
    Hirose, K., Sato, K., Asano, Y., Minematsu, N.: Synthesis of F0 Contours Using Generation Process Model Parameters Predicted form Unlabeled Corpora: Application to Emotional Speech Synthesis. Speech Communication 46, 385–404 (2005)CrossRefGoogle Scholar
  16. 16.
    Navas, E., Hernáez, I., Luengo, I.: An Objective and Subjective Study of the Role of Semantics and Prosodic Features in Building Corpora for Emotional TTS. IEEE Transactions on Audio, Speech, and Language Processing 14, 1117–1127 (2006)CrossRefGoogle Scholar
  17. 17.
    Cabral, J.P., Oliveira, L.C.: EmoVoice: A System to Generate Emotions in Speech. In: Proceedings of Interspeech – ICSLP. pp. 1798–1801. Pittsburgh (2006)Google Scholar
  18. 18.
    Přibil, J., Přibilová, A.: Emotional Style Conversion in the TTS System with Cepstral Description. In: Esposito, A., Faundez-Zanuy, M., Keller, E., Marinaro, M. (eds.) COST Action 2102. LNCS (LNAI), vol. 4775, pp. 65–73. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  19. 19.
    Přibilová, A., Přibil, J.: Non-Linear Frequency Scale Mapping for Voice Conversion in Text-to-Speech System with Cepstral Description. Speech Communication 48, 1691–1703 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Anna Přibilová
    • 1
  • Jiří Přibil
    • 2
  1. 1.Department of Radio ElectronicsSlovak University of TechnologyBratislavaSlovakia
  2. 2.Institute of Photonics and ElectronicsAcademy of Sciences of the Czech RepublicPragueCzech Republic

Personalised recommendations