Efficient Adaptation of TTS Duration Model to New Speakers

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  Shih, Chilin ^a   Gu, Wentao ^a   van Santen, Jan P H ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DURATION MODELLING; SPEAKER SPECIFIC INFORMATIONS; SPEAKER VARIATION; TRAINING DATA;

EID: 0012306910     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Arslan, L. M., and Talkin, D. Voice conversion by codebook mapping of line spectral frequencies and excitation spectrum. In EuroSpeech'97 (Rhodes, Greece, 1997), vol. 3, pp. 1347-1350.
2. Buchsbaum, A. L., and van Santen, J. P. H. Selecting training text via greedy matroid covering. Tech. memo, AT&T Bell Laboratories, 1994.
3. Klatt, D. H. Interaction between two factors that influence vowel duration. JASA 54, 4 1973, 1102-1104.
4. Shih, C., and Ao, B. Duration study for the Bell Laboratories Mandarin text-to-speech system. In Progress in Speech Synthesis, J. van Santen, R. Sproat, J. Olive, and J. Hirschberg, Eds. Springer, New York, 1997.
5. van Santen, J. P. H. Assignment of segmental duration in text-to-speech synthesis. Computer Speech and Language 8, 2 1994, 95-128.
6. van Santen, J. P. H., and Olive, J. P. The analysis of contextual effects on segmental duration. Computer Speech and Language 4 1990, 359-391.
7. Verhasselt, J. P., and Martens, J.-P. A fast and reliable rate of speech detector. In ICLSP 96 (Philadelphia, 1996), vol. 4, pp. 2258-2261.