Browse State-of-the-Art › Audio-Visual Active Speaker Detection
Audio-Visual Active Speaker Detection
13 papers with code · 2 benchmarks · 3 datasets archive 2025-07-28
Determine if and when each visible person in the video is speaking.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| AVA-ActiveSpeaker (20 rows) | LoCoNet+TalkNCE | TalkNCE: Improving Active Speaker Detection with Talk-Aware... | code | — | Compare |
| VPCD (1 row) | GSCMIA | Audio-Visual Activity Guided Cross-Modal Identity Association for... | code | — | Compare |
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
3 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.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 13 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 25 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, 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.
-
Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection14 Jul 2021 4 repositories listed Syntology official (archive's flag): 5 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 1 pointer-only (licence)Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers.
-
27 Mar 2022 3 repositories listed Syntology official (archive's flag): 2 ran · 3 ran (of which 1 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) · 5 pointer-only (licence)Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation.
-
19 Jan 2023 2 repositories listedThese two contexts are complementary to each other and can help infer the active speaker.
-
15 Jul 2022 2 repositories listedActive speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows.
-
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.
-
21 Jan 2025 1 repository listedActive Speaker Detection (ASD) aims to identify speaking individuals in complex visual scenes.
-
21 Sep 2023 1 repository listedThe goal of this work is Active Speaker Detection (ASD), a task to determine whether a person is speaking or not in a series of video frames.
-
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)Experimental results on the AVA-ActiveSpeaker dataset show that our framework achieves competitive mAP performance (94.
-
1 Dec 2022 1 repository listedActive speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality.
-
7 Jun 2021 1 repository listedSuccessful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers…
-
1 Jun 2021 1 repository listedActive speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers.
-
11 Jan 2021 1 repository listedActive speaker detection requires a solid integration of multi-modal cues.
-
20 May 2020 1 repository listedCurrent methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker.
-
An Efficient and Streaming Audio Visual Active Speaker Detection System13 Sep 2024 0 repositories listedThis paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames.
-
Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training1 Apr 2024 0 repositories listedAudio-visual active speaker detection (AV-ASD) aims to identify which visible face is speaking in a scene with one or more persons.
-
Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection3 Oct 2022 0 repositories listedAudio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications.
-
22 Jun 2022 0 repositories listedThis report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022.
-
6 Jan 2022 0 repositories listedAugmented reality devices have the potential to enhance human perception and enable other assistive functionalities in complex conversational environments.
-
Learning Spatial-Temporal Graphs for Active Speaker Detection2 Dec 2021 0 repositories listedWe address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between audio and visual data.
-
14 Oct 2021 0 repositories listedThe goal of this paper is to learn strong lip reading models that can recognise speech in silent videos.
-
5 Aug 2021 0 repositories listedWe introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD).
-
7 Jun 2021 0 repositories listedIt is now well established from a variety of studies that there is a significant benefit from combining video and audio data in detecting active speakers.
-
1 Jun 2021 0 repositories listedThis report presents a brief description of our method for the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2021.
-
25 Jun 2019 0 repositories listedThis report describes our submission to the ActivityNet Challenge at CVPR 2019.
-
1 Jun 2019 0 repositories listedThis report describes the approach underlying our submission to the active speaker detection task (task B-2) of ActivityNet Challenge 2019.
Syntology lines on 3 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