{"url":"/task/active-speaker-localization","name":"Active Speaker Localization","slug":"active-speaker-localization","description_markdown":"Active Speaker Localization (ASL) is the process of spatially localizing an active speaker (talker) in an environment using either audio, vision or both.","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5,"papers_with_code":0,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/active-speaker-localization-on-easycom","slug":"active-speaker-localization-on-easycom","dataset":"EasyCom","dataset_url":"/dataset/easycom","rows_in_archive":1,"metrics":["ASL mAP"],"first_row_in_archive_order":{"model":"AV (cor+eng+box)","paper_title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","paper_url":"/paper/egocentric-deep-multi-channel-audio-visual","paper_date":"2022-01-06","arxiv_id":"2201.01928","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/easycom","name":"EasyCom","full_name":"","num_papers_in_archive":22},{"url":"/dataset/tragic-talkers","name":"Tragic Talkers","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":0,"of":0,"tagged_in_all":5,"items":[],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}