Abstract | ||
---|---|---|
This paper describes a pioneer study on prosodic control for Cantonese text-to-speech synthesis. We attempt to establish a set of segment-level duration rules and context- dependent F0 profiles and apply them to a syllable-based concatenative speech synthesizer which uses TD-PSOLA as prosodic modification technique. The prosodic features are extracted by statistical characterization of a large amount of speech data. Subjective listening test shows that the micro-prosodic control results in a marginal but consistent improvement in perceptual naturalness. |
Year | Venue | Keywords |
---|---|---|
1999 | EUROSPEECH | micro-prosody,tts,cantonese,context dependent |
Field | DocType | Citations |
Speech synthesis,Listening test,Computer science,Naturalness,Speech recognition,Syllable,Text to speech synthesis,Natural language processing,Artificial intelligence,Perception | Conference | 7 |
PageRank | References | Authors |
1.38 | 2 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tan Lee | 1 | 476 | 74.69 |
Helen M. Meng | 2 | 1078 | 172.82 |
Wai H. Lau | 3 | 25 | 4.43 |
W. K. Lo | 4 | 10 | 1.90 |
Pak-chung Ching | 5 | 1366 | 139.74 |