Synthetic Voice Datasets » History » Version 2
Brendan O'Connor, 2019-07-03 10:34 AM
| 1 | 2 | Brendan O'Connor | h1. Synthetic Voice Dataset |
|---|---|---|---|
| 2 | 1 | Brendan O'Connor | |
| 3 | 1 | Brendan O'Connor | Emir discusses the work done in synthetic singing voice datasets by Matthew Awlett at Cereproc |
| 4 | 2 | Brendan O'Connor | * Speech Synthesis, as seen on https://www.youtube.com/watch?v=G-zyTlZQYpE |
| 5 | 1 | Brendan O'Connor | * Using the NUS sung and spoken labels corpus |
| 6 | 2 | Brendan O'Connor | * Using 'copy-synthesis' and parametric systems |
| 7 | 1 | Brendan O'Connor | * Question of what should be included in vocal singing datasets |
| 8 | 1 | Brendan O'Connor | > * Whisper, spoken word, voice-like instruments, breath, elongated decay of words, reverberated tails |