A family-of-models approach to HMM-based segmentation for unit selection speech synthesis

8th International Conference on Spoken Language Processing, ICSLP 2004

Volumn , Issue , 2004, Pages 1385-1388

  Kominek, John ^a   Black, Alan W ^a  

^a Carnegie Mellon University ^*  (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH SYNTHESIS;

ACOUSTIC MODEL; BOUNDARY POINTS; HMM-BASED; LISTENING TESTS; MULTIPLE ESTIMATES; SPEECH DATABASE; UNIT-SELECTION SPEECH SYNTHESIS;

SPEECH RECOGNITION;

EID: 85009091555     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Kominek, J., Bennet, C, Black A., Evaluating and Correcting Phoneme Segmentation for Unit Selection Synthesis, EuroSpeech 2003, Geneva, pp. 313-16.
2. Black, A., Lenzo, K., "Building voices in the Festival speech synthesis system," 2000. www.festvox.org/bsv.
3. Kominek, J., and Black, A., The CMU ARCTIC databases for speech synthesis, Technical Report CMU-LTI-03-177, Language Technologies Institute, Carnegie Mellon University, 2003. www.festvox.org/cmu-arctic
4. CMU, SphinxTrain: Building Acoustic Models for CMU Sphinx, http://www.speech.cs.cmu.edu/SphinxTrain.
5. Matousek, J., Tikelka, D., Psutka, J, Automatic Segmentation for Czech Concatenative Speech Synthesis Using Statistical Approach with Boundary-Specific Correction, EuroSpeech 2003, Geneva, pp. 301-04.
6. Nefti, S., Boeffard, O., Moudenc, T., Confidence Measures for Phonetic Segmenation of Continuous Speech, EuroSpeech 2003, Geneva, pp. 897-900.