Synthetic Voice Datasets » History » Version 1

Version 1/2 - Next » - Current version
Brendan O'Connor, 2019-07-02 04:57 PM

Synthetic Voice Datasets

Emir discusses the work done in synthetic singing voice datasets by Matthew Awlett at Cereproc
  • Using the NUS sung and spoken labels corpus
  • Using 'copy-synthesis'
  • Parametric System
  • Question of what should be included in vocal singing datasets
  • Whisper, spoken word, voice-like instruments, breath, elongated decay of words, reverberated tails