Advanced search
1 file | 267.96 KB Add to list

Improving TTS synthesis for emotional expressivity by a prosodic parameterization of affect based on linguistic analysis

Author
Organization
Abstract
Several experiments have been carried out that revealed weaknesses of the current Text-To-Speech (TTS) systems in their emotional expressivity. Although some TTS systems allow XML-based representations of prosodic and/or phonetic variables, few publications considered, as a pre-processing stage, the use of intelligent text processing to detect affective information that can be used to tailor the parameters needed for emotional expressivity. This paper describes a technique for an automatic prosodic parameterization based on affective clues. This technique recognizes the affective information conveyed in a text and, accordingly to its emotional connotation, assigns appropriate pitch accents and other prosodic parameters by XML-tagging. This pre-processing assists the TTS system to generate synthesized speech that contains emotional clues. The experimental results are encouraging and suggest the possibility of suitable emotional expressivity in speech synthesis.
Keywords
speech synthesis, intelligent text processing, prosody, affect sensing

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 267.96 KB

Citation

Please use this url to cite or link to this publication:

MLA
Shaikh, Mostafa Al Masum, et al. “Improving TTS Synthesis for Emotional Expressivity by a Prosodic Parameterization of Affect Based on Linguistic Analysis.” International Conference on Speech Prosody, 5th, Proceedings, 2010.
APA
Shaikh, M. A. M., Ferreira Rebordao, A., & Hirose, K. (2010). Improving TTS synthesis for emotional expressivity by a prosodic parameterization of affect based on linguistic analysis. International Conference on Speech Prosody, 5th, Proceedings. Presented at the 5th International Conference on Speech Prosody (Speech Prosody 2010), Chicago, IL, USA.
Chicago author-date
Shaikh, Mostafa Al Masum, Antonio Ferreira Rebordao, and Keikichi Hirose. 2010. “Improving TTS Synthesis for Emotional Expressivity by a Prosodic Parameterization of Affect Based on Linguistic Analysis.” In International Conference on Speech Prosody, 5th, Proceedings.
Chicago author-date (all authors)
Shaikh, Mostafa Al Masum, Antonio Ferreira Rebordao, and Keikichi Hirose. 2010. “Improving TTS Synthesis for Emotional Expressivity by a Prosodic Parameterization of Affect Based on Linguistic Analysis.” In International Conference on Speech Prosody, 5th, Proceedings.
Vancouver
1.
Shaikh MAM, Ferreira Rebordao A, Hirose K. Improving TTS synthesis for emotional expressivity by a prosodic parameterization of affect based on linguistic analysis. In: International Conference on Speech Prosody, 5th, Proceedings. 2010.
IEEE
[1]
M. A. M. Shaikh, A. Ferreira Rebordao, and K. Hirose, “Improving TTS synthesis for emotional expressivity by a prosodic parameterization of affect based on linguistic analysis,” in International Conference on Speech Prosody, 5th, Proceedings, Chicago, IL, USA, 2010.
@inproceedings{817078,
  abstract     = {{Several experiments have been carried out that revealed weaknesses of the current Text-To-Speech (TTS) systems in their emotional expressivity. Although some TTS systems allow XML-based representations of prosodic and/or phonetic variables, few publications considered, as a pre-processing stage, the use of intelligent text processing to detect affective information that can be used to tailor the parameters needed for emotional expressivity. This paper describes a technique for an automatic prosodic parameterization based on affective clues. This technique recognizes the affective information conveyed in a text and, accordingly to its emotional connotation, assigns appropriate pitch accents and other prosodic parameters by XML-tagging. This pre-processing assists the TTS system to generate synthesized speech that contains emotional clues. The experimental results are encouraging and suggest the possibility of suitable emotional expressivity in speech synthesis.}},
  author       = {{Shaikh, Mostafa Al Masum and Ferreira Rebordao, Antonio and Hirose, Keikichi}},
  booktitle    = {{International Conference on Speech Prosody, 5th, Proceedings}},
  isbn         = {{9780557519316}},
  keywords     = {{speech synthesis,intelligent text processing,prosody,affect sensing}},
  language     = {{eng}},
  location     = {{Chicago, IL, USA}},
  pages        = {{4}},
  title        = {{Improving TTS synthesis for emotional expressivity by a prosodic parameterization of affect based on linguistic analysis}},
  year         = {{2010}},
}