Year: 2025
Type: conference-paper
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. Code and audio examples are available online1.
Institutions: Institut national de recherche en sciences et technologies du numérique, Centre Inria de l'Université Grenoble Alpes, ROBOTLEARN: Apprentissage, perception et commande pour des robots sociaux, Université Grenoble Alpes, CentraleSupélec, Institut polytechnique de Grenoble, Centre National de la Recherche Scientifique, GIPSA-Lab, Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
OpenAlex ID: W4406273203