Publication Details
Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?
Stafylakis Themos (OMILIA)
Landini Federico Nicolás (DCGM FIT BUT)
Diez Sánchez Mireia, M.Sc., Ph.D. (DCGM FIT BUT)
Silnova Anna, MSc., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
End-to-End Neural Diarization, Speaker Characteristic Information
In this paper, we apply the variational information bottleneck approach to end-to-end neural diarization with encoder-decoder attractors (EEND-EDA). This allows us to investigate what in- formation is essential for the model. EEND-EDA utilizes attrac- tors, vector representations of speakers in a conversation. Our analysis shows that, attractors do not necessarily have to con- tain speaker characteristic information. On the other hand, giv- ing the attractors more freedom to allow them to encode some extra (possibly speaker-specific) information leads to small but consistent diarization performance improvements. Despite ar- chitectural differences in EEND systems, the notion of attrac- tors and frame embeddings is common to most of them and not specific to EEND-EDA. We believe that the main conclu- sions of this work can apply to other variants of EEND. Thus, we hope this paper will be a valuable contribution to guide the community to make more informed decisions when designing new systems.
@INPROCEEDINGS{FITPUB13306,
author = "Lin Zhang and Themos Stafylakis and Nicol\'{a}s Federico Landini and Mireia S\'{a}nchez Diez and Anna Silnova and Luk\'{a}\v{s} Burget",
title = "Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?",
pages = "123--130",
booktitle = "Proceedings of Odyssey 2024: The Speaker and Language Recognition Workshop",
year = 2024,
location = "Qu\'{e}bec City, CA",
publisher = "International Speech Communication Association",
doi = "10.21437/odyssey.2024-18",
language = "english",
url = "https://www.fit.vut.cz/research/publication/13306"
}