Improving TTS by higher agreement between predicted versus observed pronunciations
暂无分享,去创建一个
[1] Alan W. Black,et al. Evaluating and correcting phoneme segmentation for unit selection synthesis , 2003, INTERSPEECH.
[2] Corey Miller,et al. Pronunciation modeling in speech synthesis , 1998 .
[3] Wayne H. Ward,et al. Lexical tuning based on triphone confidence estimation , 1997, EUROSPEECH.
[4] Yeon-Jun Kim,et al. Automatic segmentation combining an HMM-based approach and spectral boundary correction , 2002, INTERSPEECH.
[5] Ann K. Syrdal,et al. The AT&t German text-to-speech system: realistic linguistic description , 2002, INTERSPEECH.
[6] Matthew J. Makashay,et al. Corpus-based techniques in the AT&t nextgen synthesis system , 2000, INTERSPEECH.
[7] Maxine Eskénazi,et al. Automatic generation of context-dependent pronunciations , 1997, EUROSPEECH.
[8] Hong-Goo Kang,et al. A perspective on the next challenges for TTS research , 2002, Proceedings of 2002 IEEE Workshop on Speech Synthesis, 2002..
[9] P. Ladefoged. A course in phonetics , 1975 .
[10] Andrej Ljolje,et al. Automatic Generation of Detailed Pronunciation Lexicons , 1996 .