Browse State-of-the-Art › Speaker Diarization
Speaker Diarization
93 papers with code · 12 benchmarks · 11 datasets archive 2025-07-28
Speaker Diarization is the task of segmenting and co-indexing audio recordings by speaker. The way the task is commonly defined, the goal is not to identify known speakers, but to co-index segments that are attributed to the same speaker; in other words, diarization implies finding speaker boundaries and grouping segments that belong to the same speaker, and, as a by-product, determining the number of distinct speakers. In combination with speech recognition, diarization enables speaker-attributed speech-to-text transcription.
Source: Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
15 leaderboard tables shown for this task, 12 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
11 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 328 · with a code link: 93 · where Syntology ran a sample: 14 (11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (14 of 328 tagged: 11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 4: papers 1 to 100 of 328, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
29 Nov 2021 9 repositories listedAudio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals.
-
28 Oct 2017 4 repositories listedFor many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications.
-
22 Jun 2023 3 repositories listedSpeech Emotion Recognition (SER) typically relies on utterance-level solutions.
-
2 Dec 2020 3 repositories listedDIHARD III was the third in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variability in recording equipment, noise conditions, and conversational domain.
-
20 May 2020 3 repositories listed Syntology community repositories only · 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 21 harvested samples)End-to-end speaker diarization for an unknown number of speakers is addressed in this paper.
-
16 May 2020 3 repositories listedSpeech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels.
-
4 Nov 2019 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)We introduce pyannote. audio, an open-source toolkit written in Python for speaker diarization.
-
29 Mar 2024 2 repositories listedWith 3D-Speaker-Toolkit, we establish a new benchmark for multimodal speaker analysis.
-
7 Jan 2024 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system.
-
7 Jun 2023 2 repositories listedIn order to tackle both clip-level and frame-level tasks, this paper proposes Audio Teacher-Student Transformer (ATST), with a clip-level version (named ATST-Clip) and a frame-level version (named ATST-Frame)…
-
8 Nov 2022 2 repositories listedDER is the primary metric to evaluate diarization performance while facing a dilemma: the errors in short utterances or segments tend to be overwhelmed by longer ones.
-
20 May 2022 2 repositories listedPaddleSpeech is an open-source all-in-one speech toolkit.
-
2 Apr 2022 2 repositories listedHowever, simulated mixtures do not resemble real conversations in many aspects.
-
28 Nov 2021 2 repositories listedIn this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set.
-
12 Oct 2021 2 repositories listedWe propose a system that combines SAD and a BERT model to perform speaker change detection and speaker role detection (SRD) by chunking ASR transcripts, i. e., SD with a defined number of speakers together with SRD.
-
8 Oct 2021 2 repositories listed Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations.
-
8 Apr 2021 2 repositories listedExperiments on multiple speaker diarization datasets conclude that our model can be used with great success on both voice activity detection and overlapped speech detection.
-
1 Dec 2020 2 repositories listedAutomatic Speech Recognition (ASR) systems are increasingly powerful and more accurate, but also more numerous with several options existing currently as a service (e. g.
-
25 Nov 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Speech activity detection and speaker diarization are used to extract segments from the videos that contain speech.
-
13 Sep 2019 2 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)Our method was even better than that of the state-of-the-art x-vector clustering-based method.
-
5 Jan 2019 2 repositories listedThe dataset contains temporally labeled face tracks in video, where each face instance is labeled as speaking or not, and whether the speech is audible.
-
23 Jun 2025 1 repository listedHowever, the high computational and memory costs of these models hinder their deployment in real-time and resource-constrained scenarios.
-
3 Jun 2025 1 repository listedIn speaker diarization, traditional clustering-based methods remain widely used in real-world applications.
-
16 May 2025 1 repository listedWe assess the impact of denoising on diarization accuracy and compare various voice activity detection (VAD) models, including self-supervised transformer-based frame-wise VAD models.
-
7 Jan 2025 1 repository listedUnlike traditional speech and audio segmentation, which mainly focuses on spectral changes in the input signal, e. g., phone segmentation, our approach tries to segment the spoken utterance into chunks with differing…
-
30 Dec 2024 1 repository listedBy leveraging diarization outputs as conditioning signals, DiCoW simplifies the workflow for multi-speaker ASR, improves generalization to unseen speakers and enables more reliable transcription in real-world…
-
1 Dec 2024 1 repository listedThis work introduces the first framework for reconstructing surgical dialogue from unstructured real-world recordings, which is crucial for characterizing teaching tasks.
-
24 Sep 2024 1 repository listedIn this paper, we propose to study the calibration of a powerset speaker diarization model, and explore some of its uses.
-
16 Sep 2024 1 repository listedOur method improves on node-specific fixed neighbor selection by allowing a variable number of neighbors, eliminating the need for external tuning data as the pruning parameters are derived directly from the affinity…
-
14 Sep 2024 1 repository listedIn this work, we explore using WavLM to alleviate the problem of data scarcity for neural diarization training.
-
13 Sep 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
10 Sep 2024 1 repository listed
-
25 Jul 2024 1 repository listed
-
12 Jun 2024 1 repository listed
-
7 Jun 2024 1 repository listed
-
4 Mar 2024 1 repository listed
-
30 Jan 2024 1 repository listed
-
23 Jan 2024 1 repository listed
-
7 Jan 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
7 Dec 2023 1 repository listed
-
19 Oct 2023 1 repository listed
-
25 Sep 2023 1 repository listed
-
17 Sep 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
15 Sep 2023 1 repository listed
-
14 Sep 2023 1 repository listed
-
28 Jun 2023 1 repository listed
-
13 Mar 2023 1 repository listed
-
8 Mar 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
8 Mar 2023 1 repository listed
-
24 Feb 2023 1 repository listed
-
20 Feb 2023 1 repository listed
-
27 Oct 2022 1 repository listed
-
25 Oct 2022 1 repository listed
-
24 Oct 2022 1 repository listed
-
17 Aug 2022 1 repository listed
-
28 Jul 2022 1 repository listed
-
24 Apr 2022 1 repository listed
-
5 Apr 2022 1 repository listed
-
31 Mar 2022 1 repository listed
-
30 Mar 2022 1 repository listed
-
29 Mar 2022 1 repository listed
-
18 Mar 2022 1 repository listed
-
23 Sep 2021 1 repository listed
-
14 Sep 2021 1 repository listed
-
14 Sep 2021 1 repository listed
-
9 Sep 2021 1 repository listed
-
20 Jun 2021 1 repository listed
-
19 May 2021 1 repository listed
-
19 Apr 2021 1 repository listed
-
6 Apr 2021 1 repository listed
-
5 Apr 2021 1 repository listed
-
23 Feb 2021 1 repository listed
-
22 Oct 2020 1 repository listed
-
21 Oct 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
10 Jun 2020 1 repository listed
-
8 Jun 2020 1 repository listed
-
2 Jun 2020 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
6 Apr 2020 1 repository listed Syntology official (archive's flag): 19 ran · 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 21 harvested samples)
-
5 Mar 2020 1 repository listed
-
24 Feb 2020 1 repository listed
-
14 Feb 2020 1 repository listed
-
11 Feb 2020 1 repository listed
-
4 Nov 2019 1 repository listed
-
3 Nov 2019 1 repository listed
-
12 Sep 2019 1 repository listed
-
23 Jul 2019 1 repository listed
-
1 Jul 2019 1 repository listed
-
18 Jun 2019 1 repository listed
-
28 Oct 2018 1 repository listed
-
10 Oct 2018 1 repository listed
-
6 Sep 2018 1 repository listed
-
1 Dec 2015 1 repository listed
-
Exploring Speaker Diarization with Mixture of Experts17 Jun 2025 0 repositories listed
-
M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset17 Jun 2025 0 repositories listed
-
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models16 Jun 2025 0 repositories listed
-
SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition15 Jun 2025 0 repositories listed
-
Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models6 Jun 2025 0 repositories listed
-
Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling5 Jun 2025 0 repositories listed
-
Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization30 May 2025 0 repositories listed
Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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