Corpus building for data-driven TTS systems

Proceedings of 2002 IEEE Workshop on Speech Synthesis

Volumn , Issue , 2002, Pages 199-202

  Zhu, Weibin ^a   Zhang, Wei ^a   Shi, Qin ^a   Chen, Fangxin ^a   Li, Haiping ^a   Ma, Xijun ^a   Shen, Liqin ^a  

^a IBM CHINA RESEARCH LAB   (China)

Author keywords

[No Author keywords available]

Indexed keywords

SPECIFICATIONS; SPEECH SYNTHESIS;

CONCATENATIVE SPEECH SYNTHESIS SYSTEMS; CONTEXT DEPENDENCES; NUMERICAL CRITERIA; PROSODIC EVENTS; PROSODY MODEL; SPEAKING STYLES; SPEECH CORPORA; SPEECH RECORDING;

SPEECH;

EID: 84966365378     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/WSS.2002.1224408     Document Type: Conference Paper

References (7)

1. Campbell, N., "Limitations to Concatenative Speech Synthesis", Proc. ICSLP'2000, Beijing
2. Donovan, R.E., Eide, E.M., "The IBM Trainable Speech Synthesis System", Proc. ICSLP'98, Sydney
3. Yang, Y.F.; Wang, B., "Acoustic Correlates of Hierarchical Prosodic Boundary in Mandarin", Proc. Speech Prosody 2002, Aix-en-Provence
4. Haiping Li, Fangxin Chen, Liqin Shen, "The Context Variation Unit Vector", Proc. ICSLP'2002, Denver
5. Silverman K., et al. "TOBI: A Standard for Labeling English Prosody", Proc. of ICSLP'92, 1992
6. Mixdorff, H., "Speech Technology, ToBI and Making Sense of Prosody", Proc. Speech Prosody 2002, Aix-en-Provence
7. Qin Shi, Xijun Ma, Weibin Zhu, Wei Zhang, Liqin Shen, "Statistic Prosody Structure Prediction Based on Annotated Corpus", Submitted to this workshop