From the 1 of 3 linked papers with an AI index.
3 papers
eess.AS2026
Investigating the Integration of Spatial Information in Foundation-Model-Based Speaker Diarization
Marc Deegen, Adrian Meise, Reinhold Haeb-Umbach
The paper evaluates how to combine spatial cues from multi‑channel audio with large pretrained single‑channel models for speaker diarization, finding that conditioning the diarizat…
eess.AS2026
On the Role of Spatial Features in Foundation-Model-Based Speaker Diarization
Marc Deegen, Tobias Gburrek, Tobias Cord-Landwehr +4
Recent advances in speaker diarization exploit large pretrained foundation models, such as WavLM, to achieve state-of-the-art performance on multiple datasets. Systems like DiariZe…
eess.AS2025
Spatio-spectral diarization of meetings by combining TDOA-based segmentation and speaker embedding-based clustering
Tobias Cord-Landwehr, Tobias Gburrek, Marc Deegen +1
We propose a spatio-spectral, combined model-based and data-driven diarization pipeline consisting of TDOA-based segmentation followed by embedding-based clustering. The proposed s…