Browse State-of-the-Art › Speaker Diarization

Speaker Diarization

93 papers with code · 12 benchmarks · 11 datasets archive 2025-07-28

Speech

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.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
CALLHOME (10 rows) TOLD TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization code — Compare
NIST-SRE 2000 (5 rows) x-vector (MCGAN) TitaNet: Neural Model for speaker representation with 1D... code 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 Compare
AMI Lapel (4 rows) TitaNet-M (NME-SC) TitaNet: Neural Model for speaker representation with 1D... code 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 Compare
AMI MixHeadset (4 rows) TitaNet-L (NME-SC) TitaNet: Neural Model for speaker representation with 1D... code 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 Compare
CH109 (4 rows) TitaNet-S (NME-SC) TitaNet: Neural Model for speaker representation with 1D... code 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 Compare
DIHARD (3 rows) pyannote (waveform) pyannote.audio: neural building blocks for speaker diarization code 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 Compare
ETAPE (3 rows) pyannote (waveform) pyannote.audio: neural building blocks for speaker diarization code 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 Compare
AMI (2 rows) pyannote (waveform) pyannote.audio: neural building blocks for speaker diarization code 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 Compare
CALLHOME-109 (2 rows) titanet-s TitaNet: Neural Model for speaker representation with 1D... code 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 Compare
AliMeeting (1 row) SOND Speaker Embedding-aware Neural Diarization: an Efficient Framework... code — Compare
DIHARD II (1 row) UIS-RNN-SML Supervised online diarization with sample mean loss for multi-domain data code — Compare
Hub5'00 CallHome (1 row) UIS-RNN Fully Supervised Speaker Diarization code — Compare
call_home_american_english_speech (0 rows) no rows in the archive — —
CALLHOME (NIST-SRE-2000 Disc8) (0 rows) no rows in the archive — —
DIHARD3-eval (0 rows) no rows in the archive — —

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.

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