Diaper: End-to-end neural diarization with perceiver-based attractors

F Landini, T Stafylakis, L Burget - IEEE/ACM Transactions on …, 2024 - ieeexplore.ieee.org
Until recently, the field of speaker diarization was dominated by cascaded systems. Due to
their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to …

Transformer Attractors for Robust and Efficient End-To-End Neural Diarization

L Samarakoon, SJ Broughton… - 2023 IEEE Automatic …, 2023 - ieeexplore.ieee.org
End-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) is a
method to perform diarization in a single neural network. EDA handles the diarization of a …

Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?

L Zhang, T Stafylakis, F Landini, M Diez… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

Look Attentively to Hear: Audio-Visual Speaker Extraction

P Zexu - 2023 - search.proquest.com
Human has the inherent ability to selectively listen to a speaker in the presence of
interference speakers and background noise. Speaker extraction (SE) algorithm mimics …