Simulation of Speaking Styles with Adapted Prosody
A problem of state-of-the-art TTS systems is that the produced speech did not always fits the actual speech task. An improvement can be achieved by considering speaking styles in synthetic speech. If the desired style deviates only slightly from the standard speech of the TTS system, as it is the case for different kinds of reading styles, it is proposed that the style can be simulated with adapted prosody. Therefore this investigation uses data driven algorithms for prosody generation. After training style simulation is done by switching to the appropriate style parameter set. First experiments show that the resulting speech quality is increased by the style adapted prosody.
KeywordsNews Story Speech Synthesis Rhythm Control Pitch Contour Synthetic Speech
Unable to display preview. Download preview PDF.
- 1.W. N. Campbell and S. D. Isard. Segment durations in a syllable frame. Journal of Phonetics, 19: 37–47, 1991.Google Scholar
- 2.Hartwig Eckert and John Laver. Menschen und ihre Stimmen. BELTZ Verlagsunion Psychologie, Weinheim, 1994.Google Scholar
- 3.Maxine Eskénazi. Trends in speaking styles research. In Proccedings of Eurospeech 1993, volume 1, pages 501–509, 1993.Google Scholar
- 4.H. Fujisaki, S. Ohno, and C. Wang.The Third ESCA/COCOSDA Workshop on Speech Synthesis, chapter A Command-Response Model for F0 Contour Generation in Multilingual Speech Synthesis. Jenolan, Australia, 1998.Google Scholar
- 5.Oliver Jokisch et al. Multi-level rhythm control for speech synthesis using hybrid data driven and rule-based approaches. In Proccedings of the International Conference of Spoken Language Processing, 1998.Google Scholar
- 6.Oliver Jokisch, Hansjörg Mixdorff, Hans Kruschke, and Ulrich Kordon. Learning the parameters of quantitative prosody models. In Proccedings of the International Conference of Spoken Language Processing, Beijing, 2000.Google Scholar
- 7.Gitta P.M. Laan and Dick R. van Bergem. The contribution of pitch contour, phonem durations and spectral features to the character of spontaneous and read aloud speech. In Proceedings of Eurospeech’93, volume 1, pages 569–572, Berlin, 1993.Google Scholar
- 8.Hansjörg Mixdorff. A novel approach to the fully automatic extraction of fujisaki model parameters. In Proceeding of the International Conference on Acoustics, Speech and Signal Processing, 2000.Google Scholar
- 9.PhonDat1. BAS corpora on CD-ROM. Institute of Phonetics and Speech Communication, Munich.Google Scholar
- 10.A.M. Uhlmann et al., editors. Meyers Neues Lexikon. VEB Bibliograhisches Institut Leipzig, ausgabe in acht banden edition, 1964.Google Scholar