Name
Abstract | ||
|---|---|---|
We introduce Whistler, a trainable Text-to-Speech (TTS) system, that automatically learns the model parameters from a corpus. Both prosody parameters and concatenative speech units are derived through the use of probabilistic learning methods that have been successfully used for speech recognition. Whistler can produce synthetic speech that sounds very natural and resembles the acoustic and prosodic characteristics oi the original speaker. The underlying technologies used in Whistler can significantly facilitate the process of creating generic TTS systems for a new language, a new voice, or a new speech style. |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1109/ICSLP.1996.607289 | ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 |
Keywords | Field | DocType |
speech processing,loudspeakers,natural language processing,whistler,natural languages,probability,speech recognition,speech synthesis,text to speech,learning artificial intelligence | Speech corpus,Speech processing,Speech synthesis,Speech analytics,Computer science,Chinese speech synthesis,Speech recognition,Artificial intelligence,Natural language processing,VoxForge,Speech technology,Acoustic model | Conference |
Citations | PageRank | References |
40 | 8.98 | 7 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xuedong Huang | 1 | 1390 | 283.19 |
| A. Acero | 2 | 4390 | 478.73 |
| Jim Adcock | 3 | 40 | 8.98 |
| Hsiao-Wuen Hon | 4 | 1719 | 354.37 |
| John Goldsmith | 5 | 40 | 8.98 |
| Jingsong Liu | 6 | 40 | 8.98 |
| mike plumpe | 7 | 208 | 27.43 |