Home Page

Bienvenue sur le site de l'axe IA du laboratoire IBISC

Ce site a pour objectif l'échange d'informations ainsi que l'animation de l'axe de recherche transversal IA du laboratoire.

Présentation durant l'AG du laboratoire IBISC du 15/01/2026 : slides

---

Agenda

  • Seminaire IA : mercredi 10 juin 2026, 13h00 en hybride (amphi Pelvoux BX-30)
    • Haoran Sun (Doctorant, dir. D. Fourer, H. Maaref)
    • Title: FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
    • Abstract: Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods suffer from quantization loss, leading to compromised speaker similarity and intelligibility, while diffusion models require complex training and high inference latency. To address these challenges, we propose FlowSE, a flow-matching-based model for SE. Flow matching learns a continuous transformation between noisy and clean speech distributions in a single pass, significantly reducing inference latency while maintaining high-quality reconstruction. Specifically, FlowSE trains on noisy mel spectrograms and optional character sequences, optimizing a conditional flow matching loss with ground-truth mel spectrograms as supervision. It implicitly learns speech's temporal-spectral structure and text-speech alignment. During inference, FlowSE can operate with or without textual information, achieving impressive results in both scenarios, with further improvements when transcripts are available. Extensive experiments demonstrate that FlowSE significantly outperforms state-of-the-art generative methods, establishing a new paradigm for generative-based SE and demonstrating the potential of flow matching to advance the field.

Actu IA
16 juillet 2025 - IA @ UEVE

24 mars 2025 - journée dédiée aux usages de l’IA générative en recherche à l'Université Paris-Saclay