no code implementations • 13 Feb 2024 • Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas
A channel-number invariant loss is proposed to learn a unique feature representation regardless of the number of available microphones.
no code implementations • 24 Jul 2023 • Martin Lebourdais, Théo Mariotte, Marie Tahon, Anthony Larcher, Antoine Laurent, Silvio Montresor, Sylvain Meignier, Jean-Hugh Thomas
Voice activity and overlapped speech detection (respectively VAD and OSD) are key pre-processing tasks for speaker diarization.
no code implementations • 7 Jun 2023 • Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas
Pipeline systems rely on speech segmentation to extract speakers' segments and achieve robust speaker diarization.