The reviewed record of science sign in
Pith

arxiv: 2307.01233 · v1 · pith:3IXN6SWT · submitted 2023-07-03 · cs.SD · cs.LG· eess.AS

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

Reviewed by Pithpith:3IXN6SWTopen to challenge →

classification cs.SD cs.LGeess.AS
keywords speechrobustl2slip-to-speechsynthesiscontentfeaturesmodelnon-autoregressive
0
0 comments X
read the original abstract

Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces. Current state-of-the-art approaches primarily employ non-autoregressive sequence-to-sequence architectures to directly predict mel-spectrograms or audio waveforms from lip representations. We hypothesize that the direct mel-prediction hampers training/model efficiency due to the entanglement of speech content with ambient information and speaker characteristics. To this end, we propose RobustL2S, a modularized framework for Lip-to-Speech synthesis. First, a non-autoregressive sequence-to-sequence model maps self-supervised visual features to a representation of disentangled speech content. A vocoder then converts the speech features into raw waveforms. Extensive evaluations confirm the effectiveness of our setup, achieving state-of-the-art performance on the unconstrained Lip2Wav dataset and the constrained GRID and TCD-TIMIT datasets. Speech samples from RobustL2S can be found at https://neha-sherin.github.io/RobustL2S/

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.