{"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/is-someone-speaking-exploring-long-term","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","arxiv_id":"2107.06592","date":"2021-07-14","proceeding":null,"authors":["Ruijie Tao","Zexu Pan","Rohan Kumar Das","Xinyuan Qian","Mike Zheng Shou","Haizhou Li"],"abstract":"Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechanism for inter-modality interaction, and a self-attention mechanism to capture long-term speaking evidence. The experiments demonstrate that TalkNet achieves 3.5% and 2.2% improvement over the state-of-the-art systems on the AVA-ActiveSpeaker dataset and Columbia ASD dataset, respectively. Code has been made available at: https://github.com/TaoRuijie/TalkNet_ASD.","url_abs":"https://arxiv.org/abs/2107.06592v2","url_pdf":"https://arxiv.org/pdf/2107.06592v2.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":"is-someone-speaking-exploring-long-term","repo_url":"https://github.com/TaoRuijie/TalkNet_ASD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-someone-speaking-exploring-long-term","repo_url":"https://github.com/jiang-yidi/ts-talknet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-someone-speaking-exploring-long-term","repo_url":"https://github.com/taoruijie/talknet-asd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-someone-speaking-exploring-long-term","repo_url":"https://github.com/zcxu-eric/Ego4d_TalkNet_ASD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-speaker-detection","task_name":"Active Speaker Detection"},{"task_slug":"audio-visual-active-speaker-detection","task_name":"Audio-Visual Active Speaker Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.06592","atlas_url":"https://app.syntology.ai/?focus=2107.06592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06592"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zcxu-eric/Ego4d_TalkNet_ASD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TaoRuijie/TalkNet_ASD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiang-yidi/ts-talknet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taoruijie/talknet-asd","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"listed":{"samples":2,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"8388af70b8314436","entry":"bb_intersection_over_union","repo":"taoruijie/talknet-asd","repo_kind":"listed","path":"demoTalkNet.py","file_url":"https://github.com/taoruijie/talknet-asd/blob/HEAD/demoTalkNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8388af70b8314436"}},{"code_sha256_prefix":"d464e211ddc0306e","entry":"face_similarity","repo":"jiang-yidi/ts-talknet","repo_kind":"listed","path":"data_prep/face_enroll_speech.py","file_url":"https://github.com/jiang-yidi/ts-talknet/blob/HEAD/data_prep/face_enroll_speech.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d464e211ddc0306e"}},{"code_sha256_prefix":"2e0a799ccbd489e7","entry":"compute_average_precision","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"utils/get_ava_active_speaker_performance.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/utils/get_ava_active_speaker_performance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e0a799ccbd489e7"}},{"code_sha256_prefix":"080a23995e2591f0","entry":"eq","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"utils/get_ava_active_speaker_performance.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/utils/get_ava_active_speaker_performance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"080a23995e2591f0"}},{"code_sha256_prefix":"f460ba227a983282","entry":"get_length","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"TalkSet/generate_TalkSet.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/TalkSet/generate_TalkSet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f460ba227a983282"}},{"code_sha256_prefix":"2699b09938d17ce7","entry":"init_args","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"utils/tools.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/utils/tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2699b09938d17ce7"}},{"code_sha256_prefix":"bdc52ecccc77b9e1","entry":"load_csv","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"utils/get_ava_active_speaker_performance.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/utils/get_ava_active_speaker_performance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdc52ecccc77b9e1"}},{"code_sha256_prefix":"32296f4ba3756725","entry":"read_LRS3_ST","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"TalkSet/generate_TalkSet.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/TalkSet/generate_TalkSet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32296f4ba3756725"}},{"code_sha256_prefix":"0d9dbc902b34db85","entry":"read_Vox_lines","repo":"TaoRuijie/TalkNet_ASD","repo_kind":"official","path":"TalkSet/generate_TalkSet.py","file_url":"https://github.com/TaoRuijie/TalkNet_ASD/blob/HEAD/TalkSet/generate_TalkSet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d9dbc902b34db85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}