{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ava-avd-audio-visual-speaker-diarization-in","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","arxiv_id":"2111.14448","date":"2021-11-29","proceeding":null,"authors":["Eric Zhongcong Xu","Zeyang Song","Satoshi Tsutsui","Chao Feng","Mang Ye","Mike Zheng Shou"],"abstract":"Audio-visual speaker diarization aims at detecting \"who spoke when\" using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are quite different from in-the-wild videos in many scenarios such as movies, documentaries, and audience sitcoms. To develop diarization methods for these challenging videos, we create the AVA Audio-Visual Diarization (AVA-AVD) dataset. Our experiments demonstrate that adding AVA-AVD into training set can produce significantly better diarization models for in-the-wild videos despite that the data is relatively small. Moreover, this benchmark is challenging due to the diverse scenes, complicated acoustic conditions, and completely off-screen speakers. As a first step towards addressing the challenges, we design the Audio-Visual Relation Network (AVR-Net) which introduces a simple yet effective modality mask to capture discriminative information based on face visibility. Experiments show that our method not only can outperform state-of-the-art methods but is more robust as varying the ratio of off-screen speakers. Our data and code has been made publicly available at https://github.com/showlab/AVA-AVD.","url_abs":"https://arxiv.org/abs/2111.14448v5","url_pdf":"https://arxiv.org/pdf/2111.14448v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/showlab/ava-avd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/zcxu-eric/ava-avd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/frenchkrab/is2023-powerset-diarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/pyannote/pyannote-audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/2023-MindSpore-1/ms-code-17/tree/main/AVA_hpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/MindSpore-paper-code-3/code1/tree/main/AVA_hpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/AVA_hpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/MindSpore-scientific/code-12/tree/main/AVA_cifar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ava-avd-audio-visual-speaker-diarization-in","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/6/AVA_cifar/src/RandAugment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"relation-network","task_name":"Relation Network"},{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.14448","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}