Papers › End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder...

End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors

20 May 2020arXiv:2005.09921archive 2025-07-28

Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu

End-to-end speaker diarization for an unknown number of speakers is addressed in this paper. Recently proposed end-to-end speaker diarization outperformed conventional clustering-based speaker diarization, but it has one drawback: it is less flexible in terms of the number of speakers. This paper proposes a method for encoder-decoder based attractor calculation (EDA), which first generates a flexible number of attractors from a speech embedding sequence. Then, the generated multiple attractors are multiplied by the speech embedding sequence to produce the same number of speaker activities. The speech embedding sequence is extracted using the conventional self-attentive end-to-end neural speaker diarization (SA-EEND) network. In a two-speaker condition, our method achieved a 2.69 % diarization error rate (DER) on simulated mixtures and a 8.07 % DER on the two-speaker subset of CALLHOME, while vanilla SA-EEND attained 4.56 % and 9.54 %, respectively. In unknown numbers of speakers conditions, our method attained a 15.29 % DER on CALLHOME, while the x-vector-based clustering method achieved a 19.43 % DER.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2005.09921")

Code

Syntology Ran 0 of 21 code samples harvested from 2 repositories linked to this paper; 21 have no recorded run.

By repository: community (archive-listed): 21 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hitachi-speech/EEND officialmentioned in papermentioned on GitHubMIT report
Yoshani/pytorch-sa-eend mentioned on GitHubpytorchMIT report
butspeechfit/diacorrect mentioned on GitHubpytorchMIT 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

21 samples harvested; 0 ran; 0 honoured the contract we drafted; 21 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

21unverified

Licence: 0 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

batch_pit_loss Yoshani/pytorch-sa-eend/eend/pytorch_backend/loss.py community (archive-listed) unverified MIT (permissive) · 89d4f325ff9c071b · report
calc_diarization_error Yoshani/pytorch-sa-eend/eend/pytorch_backend/loss.py community (archive-listed) unverified MIT (permissive) · 977833339e01af8c · report
get_input_dim Yoshani/pytorch-sa-eend/eend/feature.py community (archive-listed) unverified MIT (permissive) · 2f299371003065aa · report
get_rate butspeechfit/diacorrect/diacorrect/backend/updater.py community (archive-listed) unverified MIT (permissive) · acb2c2991cd415dd · report
load_sap butspeechfit/diacorrect/diacorrect/common_utils/dataset_correct.py community (archive-listed) unverified MIT (permissive) · 13bd5877d13d5e3e · report
load_segments Yoshani/pytorch-sa-eend/eend/kaldi_data.py community (archive-listed) unverified MIT (permissive) · 216dff0f296d027f · report
load_segments_hash Yoshani/pytorch-sa-eend/eend/kaldi_data.py community (archive-listed) unverified MIT (permissive) · 805c93ef8140e802 · report
load_segments_rechash Yoshani/pytorch-sa-eend/eend/kaldi_data.py community (archive-listed) unverified MIT (permissive) · 11ff0f39a6fdcd1e · report
load_segments_rechash butspeechfit/diacorrect/diacorrect/common_utils/kaldi_data.py community (archive-listed) unverified MIT (permissive) · 8972f961b497d9da · report
load_wav_scp butspeechfit/diacorrect/diacorrect/common_utils/dataset_correct.py community (archive-listed) unverified MIT (permissive) · fcdd1d00334209b8 · report
load_wav_scp butspeechfit/diacorrect/diacorrect/common_utils/kaldi_data.py community (archive-listed) unverified MIT (permissive) · 4e95cba0484da8ff · report
my_collate Yoshani/pytorch-sa-eend/eend/pytorch_backend/diarization_dataset.py community (archive-listed) unverified MIT (permissive) · 36210d944a56c3e1 · report
osd_loss butspeechfit/diacorrect/diacorrect/backend/losses.py community (archive-listed) unverified MIT (permissive) · c8758ad59f4753a7 · report
pit_loss Yoshani/pytorch-sa-eend/eend/pytorch_backend/loss.py community (archive-listed) unverified MIT (permissive) · 6c112a64bf8d5421 · report
pit_loss_multispk butspeechfit/diacorrect/diacorrect/backend/losses.py community (archive-listed) unverified MIT (permissive) · 61a0fbfaadc3465b · report
postprocess_output butspeechfit/diacorrect/diacorrect/infer.py community (archive-listed) unverified MIT (permissive) · 380ee6404a7f71ea · report
setup_optimizer butspeechfit/diacorrect/diacorrect/backend/updater.py community (archive-listed) unverified MIT (permissive) · 75294dcc89fb7683 · report
sigmoid_inverse butspeechfit/diacorrect/diacorrect/infer_sap.py community (archive-listed) unverified MIT (permissive) · d9d88d2aeb7d7679 · report
splice butspeechfit/diacorrect/diacorrect/common_utils/features.py community (archive-listed) unverified MIT (permissive) · bdec7a99af6edff5 · report
subsample Yoshani/pytorch-sa-eend/eend/feature.py community (archive-listed) unverified MIT (permissive) · 08f6950bcdfafc26 · report
vad_loss butspeechfit/diacorrect/diacorrect/backend/losses.py community (archive-listed) unverified MIT (permissive) · c54d0aa33d0eb502 · report

Tasks

ClusteringDecoderSpeaker Diarizationspeaker-diarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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