AN FO CONTOUR CONTROL MODEL FOR TOTALLY SPEAKER DRIVEN TEXT TO SPEECH SYSTEM

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  Kagoshima, Takehiko ^a   Morita, Masahiro ^a   Seto, Shigenobu ^a   Akamine, Masami ^a  

^a TOSHIBA CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION ERRORS; CODEBOOKS; CONTOUR CONTROL; CONTROL MODEL; HIGH QUALITY; JAPANESE SPEECH; NATURAL SPEECH; PROSODICS; SPEECH CORPORA; TEXT-TO-SPEECH SYSTEM;

SPEECH SYNTHESIS;

EID: 85128428330     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Hirai, T., Iwahashi, N., Higuchi, N., and Sagisaka, Y. "Automatic Extraction of Fundamental Frequency Control Rules Using Statistical Analysis," (in Japanese) Trans. IEICE vol. J78-D-II.no. 11, pp.1572-1580. Nov.,1995.
2. Huang, X., Accro, A., Hon, H., Ju, Y., Liu, J., Meredith, S., and Plumpe, M. "Recent improvements on Microsoft's trainable text-to-speech system - Whistler.'' Proc. IEEE ICASSP'96, pp.959-962, April 1996.
3. Akamine, M., and Kagoshima, T. "Analytic Generation of Synthesis Units by Closed Loop Training for Totally Speaker Driven Text to Speech System (TOS Drive TTS)," Proc. ICSLP'98. Nov. 1998.
4. Seto, S., Morita, M., Kagoshima, T., and Akaminc, M. "Automatic Rule Generation for Linguistic Features Analysis Using Inductive Learning Technique," Proc. ICSLP'98. Nov. 1998.
5. Shiga, Y., Hara, Y., and Nitta, T. "A Novel Segment-Concatenation Algorithm for a Cepstrum-Based Synthesizer." Proc. ICSLP'94, pp.1783-1786. Sep. 1994.