AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
2025-01-09Code Available1· sign in to hype
Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/samsad35/code-ancogenOfficialpytorch★ 13
Abstract
This article introduces AnCoGen, a novel method that leverages a masked autoencoder to unify the analysis, control, and generation of speech signals within a single model. AnCoGen can analyze speech by estimating key attributes, such as speaker identity, pitch, content, loudness, signal-to-noise ratio, and clarity index. In addition, it can generate speech from these attributes and allow precise control of the synthesized speech by modifying them. Extensive experiments demonstrated the effectiveness of AnCoGen across speech analysis-resynthesis, pitch estimation, pitch modification, and speech enhancement.