New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer

Speech Communication

Volumn 48, Issue 10, 2006, Pages 1227-1242

  Latorre, Javier ^a   Iwano, Koji ^a   Furui, Sadaoki ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Cross language synthesis; Multilingual; Phone mapping; Polyglot synthesis; Voice adaptation

Indexed keywords

FORMAL LANGUAGES; MAPPING; MARKOV PROCESSES; SPEECH COMMUNICATION; SPEECH PRODUCTION AIDS; TELEPHONE;

ADAPTABLE SYNTHESIZER; MONOLINGUAL SYNTHESIZERS; POLYGLOT SYNTHESIS; SPEECH DATA; VOICE ADAPTATION;

SPEECH SYNTHESIS;

EID: 33748468338     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2006.05.003     Document Type: Article

References (24)

1. Badino, L., Barolo, C., Quazza, S., 2004. A general approach to TTS reading of mixed-language texts. In: Proc. ICSLP, Jeju Island, Korea, pp. 849-852.
2. Black, A., Lenzo, K., 2004. Multilingual text-to-speech synthesis. In: Proc. ICASSP, Montreal, Canada, pp. 761-764.
3. Bonaventura, P., Gallochio, F., Micca, G., 1997. Multilingual speech recognition for flexible vocabularies. In: Proc. Eurospeech, Rhodes, Greece, pp. 355-358.
4. Campbell, N., 1998. Foreign-language speech synthesis. In: Proc. ESCA/COCOSDA Workshop on Speech Synthesis, Jenolan Caves, Australia.
5. Campbell, N., 2001. Talking foreign. Concatenative speech synthesis and the language barrier. In: Proc. Eurospeech, Aalborg, Denmark, pp. 337-340.
6. Dijkstra, J., Pols, L.C.W., van Son, R.J.J.H., 2004. Frisian TTS, an example of bootstrapping TTS for minority languages. In: Proc. 5th ISCA Speech Synthesis Workshop, Pittsburgh, USA, pp. 97-102.
7. Graddol D. The future of language. Science 303 (2004) 1329-1331
8. Imai S., 1983. Cepstral analysis synthesis on the Mel frequency scale. In: Proc. ICASP, Boston, USA, pp. 93-96.
9. Leggetter C.J., and Woodland P.C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 9 2 (1995) 171-185
10. Liu, C., Melnar, L., 2005. An automated linguistic knowledge-based cross-language transfer method for building acoustic models for a languages without native training data. In: Proc. Eurospeech, Lisbon, Portugal, pp. 1365-1368.
11. Mak, B., Barnard, E., 1996. Phone clustering using the Bhattacharyya distance. In: Proc. ICSLP, Philadelphia, USA, pp. 2005-2008.
12. Mashimo M., Toda, T., Kawanami, H., Kashioka, H., Shikano, K., Campbell, N., 2001. Evaluation of cross-language voice conversion based on GMM and STRAIGHT. In: Proc. Eurospeech, Aalborg, Denmark, pp. 361-364.
13. Masuko, T., Tokuda, K., Kobayashi, T., Imai, S., 1996. Speech synthesis using HMMs with dynamic features. In: Proc. ICASSP, Atlanta, USA, pp. 389-392.
14. Moberg, M., Pärssinen, K., Iso-Sipilä, J., 2004. Cross-lingual phoneme mapping for multilingual synthesis systems. In: Proc. ICSLP, Jeju Island, Korea, pp. 1029-1032.
15. Schultz, T., 2002. Globalphone: a multilingual speech and text database developed at Karlsruhe University. In: Proc. ICSLP, Denver, USA, pp. 345-348.
16. Schultz, T., Waibel, A., 2001. Experiments on cross-language acoustic modeling. In: Proc. Eurospeech, Aalborg, Denmark, pp. 2721-2724.
17. Shin, H., Bruno, R., 2003. Language use and English speaking ability. In USA Census 2000, US Census Bureau census.gov/prod/2003pubs/c2kbr-29.pdf.
18. Shinoda K., and Watanabe T. MDL-based context-dependent subword modeling for speech recognition. J. Acoust. Soc. Jpn. (English) 21 (2000) 79-86
19. Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T., 1998. Speaker adaptation for HMM-based speech synthesis system using MLLR. In: Proc. Third ESCA/COCOSDA Workshop on Speech Synthesis, Jenolan Caves, Autralia, pp. 273-276.
20. Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T., 2001. Text-to-speech synthesis with arbitrary speaker's voice from average voice. In: Proc. Eurospeech 2001, Aalborg, Denmark, pp. 345-348.
21. Tokuda, K., Masuko, T., Yamada, T., Kobayashi, T. Imai, S., 1995a. An algorithm for speech parameter generation from continuous mixture HMM with dynamic features. In: Proc. Eurospeech 1995, Madrid, Spain, pp. 757-760.
22. Tokuda, K., Masuko, T., Imai, S., 1995b. Speech parameter generation from continous mixture HMMs with dynamic features. In: Proc. ICASSP, Detroit, USA, pp. 660-663.
23. Traber, C., Huber, K., Nedir, K., Pfister, B., Keller, E., Zellner, B., 1999. From multilingual to polyglot speech synthesis. In: Proc. Eurospeech, Budapest, Hungary, pp. 835-838.
24. Yu, H., Schultz, T., 2003. Enhanced tree clustering with single pronunciation dictionary for conversational speech recognition. In Proc. Eurospeech, Geneva, Switzerland, pp. 1869-1872.