Papers › Neural Diarization with Non-autoregressive Intermediate Attractors

Neural Diarization with Non-autoregressive Intermediate Attractors

13 Mar 2023arXiv:2303.06806archive 2025-07-28

Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa

End-to-end neural diarization (EEND) with encoder-decoder-based attractors (EDA) is a promising method to handle the whole speaker diarization problem simultaneously with a single neural network. While the EEND model can produce all frame-level speaker labels simultaneously, it disregards output label dependency. In this work, we propose a novel EEND model that introduces the label dependency between frames. The proposed method generates non-autoregressive intermediate attractors to produce speaker labels at the lower layers and conditions the subsequent layers with these labels. While the proposed model works in a non-autoregressive manner, the speaker labels are refined by referring to the whole sequence of intermediate labels. The experiments with the two-speaker CALLHOME dataset show that the intermediate labels with the proposed non-autoregressive intermediate attractors boost the diarization performance. The proposed method with the deeper network benefits more from the intermediate labels, resulting in better performance and training throughput than EEND-EDA.

PaperPDFCode

Code

hitachi-speech/EEND officialmentioned in paperMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderSpeaker Diarizationspeaker-diarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

EEND

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections