Research/Projects

đź’° Fundings

  • (2024-2028) → CIEDS Project (FakeDetect) on multimodality for deep fake detection (Collaborator) (~150k€)
  • (2024) → HI! Project (DARHAM) on dataset of augmented reality headset for acoustic matching (P.I.) (~10k€)
  • (2023-2026) → ANR JCJC (SAROUMANE) on speaker diarization (P.I.) (~270k€)
  • (2022-2024) → HI! Project (MASTER-AI) on stochastic models for artificial intelligence (P.I.) (~10k€)

👨🏻‍🏫 Current Students

PhD Students

(2022 - 2025) → Louis BAHRMAN (dereverberation)

  • Topic: Speech/Audio dereverberation by hybrid deep neural modelling
  • Supervisors: GaĂ«l RICHARD & Mathieu FONTAINE (TĂ©lĂ©com Paris)

(2022 - 2025) → Elio GRUTTADAURIA (speaker diarization)

  • Topic: Online Multichannel Speaker Diarization and Localisation in the Wild
  • Supervisors: Slim ESSID & Mathieu FONTAINE (TĂ©lĂ©com Paris)

(2023 - 2026) → Anton EMELCHENKOV (anomaly detection)

  • Topic: Detecting outliers in locally stationary time series
  • Supervisors:
    • François ROUEFF, Mathieu FONTAINE & Yves GRENIER (TĂ©lĂ©com Paris)
    • HervĂ© MAHE (ValĂ©o)

(2023 - 2026) → Victor LETZELTER (sound analysis / automated driving)

  • Topic: Spatio-temporal analysis of sound scenes for assisted and automated driving
  • Supervisors:
    • GaĂ«l RICHARD & Mathieu FONTAINE (TĂ©lĂ©com Paris)
    • Patrick PEREZ (ValĂ©o)

(2023 - 2026) → Thomas SERRE (personalized speech enhancement)

  • Topic: Personalized Speech Enhancement in real-time through Deep Learning
  • Supervisors:
    • Slim ESSID & Mathieu FONTAINE (TĂ©lĂ©com Paris)
    • Eric BENHAIM (Orosound)

(2023 - 2026) → Louis LALAY (separation and dereverberation)

  • Topic: Joint separation and dereverberation of moving speakers
  • Supervisors:
    • Roland BADEAU & Mathieu FONTAINE (TĂ©lĂ©com Paris)

(2023 - 2026) → Sicheng MAO (speaker diarization)

  • Topic: Generative Models for speaker diarization
  • Supervisors:
    • Roland BADEAU & Mathieu FONTAINE (TĂ©lĂ©com Paris)
    • Anthony LARCHER (LIUM Le Mans)

👨🏻‍💻 Past Students

Interns & Research Engineers

  • Jean-Daniel PASCAL (Audio source separation), Eloi MASSOULIE (tracking of mobile sound sources), , Teysir BAOUEB (Audio diffusion model & GAN), Haocheng LIU (guided gradient descent through multivariate alpha-stable models), Polina BARABANSHCHIKOVA (RKHS and diffusion models), Wen YANG (forecasting demand for electric vehicle) and Liam KELLEY (Research Engineer on DARHAM project)

🧑🏻‍🔬 Others