Joint prosody prediction and unit selection for concatenative speech synthesis

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2, Issue , 2001, Pages 781-784

  Bulyko, I ^a   Ostendorf, M ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER APPLICATIONS; DATABASE SYSTEMS; SPEECH ANALYSIS; SPEECH PROCESSING; TRANSDUCERS;

CONCATENATIVE SPEECH SYNTHESIS; JOINT PROSODY PREDICTION; MEL FREQUENCY CEPSTRAL COEFFICIENT; WEIGHTED FINITE STATE TRANSDUCER;

SPEECH SYNTHESIS;

EID: 0034854347     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. The AT&T next-gen TTS system
2. Rapid unit selection from a large speech corpus for concatenative speech synthesis
3. Limited domain synthesis
4. Segment selection in the L&H Realspeak laboratory TTS system
5. Segment preselection in decision-tree based speech synthesis systems
6. Automatic generation of synthesis units for trainable text-to-speech systems
7. Unit selection in a concatenative speech synthesis system using a large speech database
8. The CU communicator: An architecture for dialogue systems
9. Prediction of abstract prosodic labels for speech synthesis
10. ToBI: A standard for labeling english prosody
11. Concept-to-Speech synthesis by phonological structure matching
12. Perceptually based automatic prosody labeling and prosodically enriched unit selection improve concatenative speech synthesis
13. A perceptual evaluation of distance measures for concatenative speech synthesis
14. Natural-sounding speech synthesis using variable-length units
15. A flexible, scalable finite-state transducer architecture for corpus-based concatenative speech synthesis