[Submitted on 1 Mar 2023 ( v1 ), last revised 17 Dec 2023 (this version, v3)] Title:ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations Download a PDF of the paper titled ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations, by Neil Shah and 5 other authors Download PDF HTML (experimental) Abstract:We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations.
