Conference Papers Year : 2025

AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder

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 analysisresynthesis, pitch estimation, pitch modification, and speech enhancement. Code and audio examples are available online 1 .

Index Terms-Speech analysis/transformation/synthesis, masked autoencoder, pitch estimation and modification, speech enhancement.

Fichier principal
Vignette du fichier
2501.05332v1.pdf (1) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04891286 , version 1 (16-01-2025)

Identifiers

  • HAL Id : hal-04891286 , version 1

Cite

Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda. AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder. IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2025, Hyderabad, India. ⟨hal-04891286⟩
0 View
0 Download

Share

More