GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech. (arXiv:2205.07211v2 [eess.AS] UPDATED)

Style transfer for out-of-domain (OOD) speech synthesis aims to generate
speech samples with unseen style (e.g., speaker identity, emotion, and prosody)
derived from an acoustic reference, while facing the following challenges: 1)
The highly dynamic style features in expressive voice are difficult to model
and transfer; and 2) the TTS models should be robust enough to handle diverse
OOD conditions that differ from the source data. This paper proposes
GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style
transfer of OOD …

arxiv speech style transfer text text-to-speech transfer