RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations

no code implementations • 3 Jul 2023 • Neha Sahipjohn, Neil Shah, Vishal Tambrahalli, Vineet Gandhi

Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces.

Speaker-Specific Lip to Speech Synthesis Speech Synthesis

MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting

no code implementations • 19 May 2023 • Neil Shah, Vishal Tambrahalli, Saiteja Kosgi, Niranjan Pedanekar, Vineet Gandhi

We present MParrotTTS, a unified multilingual, multi-speaker text-to-speech (TTS) synthesis model that can produce high-quality speech.

Speech Synthesis Text-To-Speech Synthesis

ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations

no code implementations • 1 Mar 2023 • Neil Shah, Saiteja Kosgi, Vishal Tambrahalli, Neha Sahipjohn, Niranjan Pedanekar, Vineet Gandhi

We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations.

Self-Supervised Learning Speech Synthesis +1