Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deegen, Marc, Gburrek, Tobias, Cord-Landwehr, Tobias, von Neumann, Thilo, Han, Jiangyu, Burget, Lukáš, Haeb-Umbach, Reinhold
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.02231
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914234043990016
author Deegen, Marc
Gburrek, Tobias
Cord-Landwehr, Tobias
von Neumann, Thilo
Han, Jiangyu
Burget, Lukáš
Haeb-Umbach, Reinhold
author_facet Deegen, Marc
Gburrek, Tobias
Cord-Landwehr, Tobias
von Neumann, Thilo
Han, Jiangyu
Burget, Lukáš
Haeb-Umbach, Reinhold
contents 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 DiariZen leverage these rich single-channel representations, but are limited to single-channel audio, preventing the use of spatial cues available in multi-channel recordings. This work analyzes the impact of incorporating spatial information into a state-of-the-art single-channel diarization system by evaluating several strategies for conditioning the model on multi-channel spatial features. Experiments on meeting-style datasets indicate that spatial information can improve diarization performance, but the overall improvement is smaller than expected for the proposed system, suggesting that the features aggregated over all WavLM layers already capture much of the information needed for accurate speaker discrimination, also in overlapping speech regions. These findings provide insight into the potential and limitations of using spatial cues to enhance foundation model-based diarization.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02231
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On the Role of Spatial Features in Foundation-Model-Based Speaker Diarization
Deegen, Marc
Gburrek, Tobias
Cord-Landwehr, Tobias
von Neumann, Thilo
Han, Jiangyu
Burget, Lukáš
Haeb-Umbach, Reinhold
Audio and Speech Processing
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 DiariZen leverage these rich single-channel representations, but are limited to single-channel audio, preventing the use of spatial cues available in multi-channel recordings. This work analyzes the impact of incorporating spatial information into a state-of-the-art single-channel diarization system by evaluating several strategies for conditioning the model on multi-channel spatial features. Experiments on meeting-style datasets indicate that spatial information can improve diarization performance, but the overall improvement is smaller than expected for the proposed system, suggesting that the features aggregated over all WavLM layers already capture much of the information needed for accurate speaker discrimination, also in overlapping speech regions. These findings provide insight into the potential and limitations of using spatial cues to enhance foundation model-based diarization.
title On the Role of Spatial Features in Foundation-Model-Based Speaker Diarization
topic Audio and Speech Processing
url https://arxiv.org/abs/2601.02231