Name
Abstract | ||
|---|---|---|
This paper describes a method for text-to-speech waveform synthesis based on the Analysis-by-Synthesis/Overlap-Add (ABS/OLA) sinusoidal model. This model has been shown in previous work to be a useful framework for pitch and time-scale modification of both speech and music signals. This paper explores some extensions of the original ABS/OLA formulation that attempt to overcome specific artifacts, including a phase dithering approach for unvoiced speech synthesis and an improved pitch... |
Year | Venue | Keywords |
|---|---|---|
1999 | EUROSPEECH | text to speech,analysis by synthesis,speech synthesis |
Field | DocType | Citations |
Pattern recognition,Computer science,Waveform,Speech recognition,Artificial intelligence,Sinusoidal model | Conference | 1 |
PageRank | References | Authors |
0.39 | 7 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Michael W. Macon | 1 | 334 | 25.79 |
| Mark A. Clements | 2 | 486 | 64.32 |