Controllable neural text-to-speech synthesis using intuitive prosodic features

14 Sep 2020 Tuomo Raitio Ramya Rasipuram Dan Castellani

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide prosodic variation... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper