{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/target-sound-extraction","name":"Target Sound Extraction","slug":"target-sound-extraction","description_markdown":"Target Sound Extraction is the task of extracting a sound corresponding to a given class from an audio mixture. The audio mixture may contain background noise with a relatively low amplitude compared to the foreground mixture components. The choice of the sound class is provided as input to the model in form of a string, integer, or a one-hot encoding of the sound class.","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":16,"papers_with_code":8,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":3,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/target-sound-extraction-on-audiocaps","slug":"target-sound-extraction-on-audiocaps","dataset":"AudioCaps","dataset_url":"/dataset/audiocaps","rows_in_archive":1,"metrics":["SDRi","SI-SDRi"],"first_row_in_archive_order":{"model":"CLAPSep","paper_title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","paper_url":"/paper/clapsep-leveraging-contrastive-pre-trained","paper_date":"2024-02-27","arxiv_id":"2402.17455","code_links":[{"title":"aisaka0v0/clapsep","url":"https://github.com/aisaka0v0/clapsep"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clapsep-leveraging-contrastive-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2402.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17455"}},"official":{"repos":["aisaka0v0/clapsep"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/target-sound-extraction-on-audioset","slug":"target-sound-extraction-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":1,"metrics":["SDRi","SI-SDRi"],"first_row_in_archive_order":{"model":"CLAPSep","paper_title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","paper_url":"/paper/clapsep-leveraging-contrastive-pre-trained","paper_date":"2024-02-27","arxiv_id":"2402.17455","code_links":[{"title":"aisaka0v0/clapsep","url":"https://github.com/aisaka0v0/clapsep"}],"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clapsep-leveraging-contrastive-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2402.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17455"}},"official":{"repos":["aisaka0v0/clapsep"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/target-sound-extraction-on-fsdsoundscapes","slug":"target-sound-extraction-on-fsdsoundscapes","dataset":"FSDSoundScapes","dataset_url":"/dataset/fsdsoundscapes","rows_in_archive":1,"metrics":["SI-SNRi"],"first_row_in_archive_order":{"model":"Waveformer","paper_title":"Real-Time Target Sound Extraction","paper_url":"/paper/real-time-target-sound-extraction","paper_date":"2022-11-04","arxiv_id":"2211.02250","code_links":[{"title":"vb000/waveformer","url":"https://github.com/vb000/waveformer"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-target-sound-extraction#ran","syntology_url":"https://syntology.ai/paper/2211.02250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02250"}},"official":{"repos":["vb000/waveformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/audiocaps","name":"AudioCaps","full_name":"","num_papers_in_archive":279},{"url":"/dataset/fsdsoundscapes","name":"FSDSoundScapes","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/streaming-target-sound-extraction","name":"Streaming Target Sound Extraction"}],"parent_tasks":[{"url":"/task/audio-source-separation","name":"Audio Source Separation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":16,"of":16,"of_with_code":8,"tagged_in_all":16,"counts":{"archive_papers_tagged":16,"with_a_code_link":8,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/dpm-tse-a-diffusion-probabilistic-model-for","slug":"dpm-tse-a-diffusion-probabilistic-model-for","title":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","date":"2023-10-06","arxiv_id":"2310.04567","repositories_listed":2,"syntology":null},{"url":"/paper/soloaudio-target-sound-extraction-with","slug":"soloaudio-target-sound-extraction-with","title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","date":"2024-09-12","arxiv_id":"2409.08425","repositories_listed":1,"syntology":null},{"url":"/paper/cross-attention-inspired-selective-state","slug":"cross-attention-inspired-selective-state","title":"Cross-attention Inspired Selective State Space Models for Target Sound Extraction","date":"2024-09-07","arxiv_id":"2409.04803","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 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) · 1 unverified","sample_list":"/paper/cross-attention-inspired-selective-state#ran","syntology_url":"https://syntology.ai/paper/2409.04803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04803"}},"official":{"repos":["WuDH2000/CrossMamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-all-variations-within-the-unified-mask","slug":"can-all-variations-within-the-unified-mask","title":"Can all variations within the unified mask-based beamformer framework achieve identical peak extraction performance?","date":"2024-07-22","arxiv_id":"2407.15310","repositories_listed":1,"syntology":null},{"url":"/paper/clapsep-leveraging-contrastive-pre-trained","slug":"clapsep-leveraging-contrastive-pre-trained","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","date":"2024-02-27","arxiv_id":"2402.17455","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clapsep-leveraging-contrastive-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2402.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17455"}},"official":{"repos":["aisaka0v0/clapsep"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-hearing-programming-acoustic-scenes","slug":"semantic-hearing-programming-acoustic-scenes","title":"Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables","date":"2023-11-01","arxiv_id":"2311.00320","repositories_listed":1,"syntology":null},{"url":"/paper/target-sound-extraction-with-variable-cross","slug":"target-sound-extraction-with-variable-cross","title":"Target Sound Extraction with Variable Cross-modality Clues","date":"2023-03-15","arxiv_id":"2303.08372","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-target-sound-extraction","slug":"real-time-target-sound-extraction","title":"Real-Time Target Sound Extraction","date":"2022-11-04","arxiv_id":"2211.02250","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-target-sound-extraction#ran","syntology_url":"https://syntology.ai/paper/2211.02250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02250"}},"official":{"repos":["vb000/waveformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"soundsculpt-direction-and-semantics-driven","title":"SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction","date":"2025-05-30","arxiv_id":"2506.00273","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-audio-only-data-for-text-queried","title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","date":"2024-09-20","arxiv_id":"2409.13152","repositories_listed":0,"syntology":null},{"url":null,"slug":"multichannel-to-multichannel-target-sound","title":"Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues","date":"2024-09-19","arxiv_id":"2409.12415","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-queried-target-sound-extraction","title":"Language-Queried Target Sound Extraction Without Parallel Training Data","date":"2024-09-14","arxiv_id":"2409.09398","repositories_listed":0,"syntology":null},{"url":null,"slug":"catse-a-context-aware-framework-for-causal","title":"CATSE: A Context-Aware Framework for Causal Target Sound Extraction","date":"2024-03-21","arxiv_id":"2403.14246","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-similarity-and-independence-aware","title":"Online Similarity-and-Independence-Aware Beamformer for Low-latency Target Sound Extraction","date":"2023-12-27","arxiv_id":"2312.16449","repositories_listed":0,"syntology":null},{"url":null,"slug":"soundbeam-target-sound-extraction-conditioned","title":"SoundBeam: Target sound extraction conditioned on sound-class labels and enrollment clues for increased performance and continuous learning","date":"2022-04-08","arxiv_id":"2204.03895","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-of-new-sound-classes-for","title":"Few-shot learning of new sound classes for target sound extraction","date":"2021-06-14","arxiv_id":"2106.07144","repositories_listed":0,"syntology":null}],"syntology_records":3,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/target-sound-extraction/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/target-sound-extraction/papers/ran/1","json":"/task/target-sound-extraction/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"4742e3bdff7ad96fe539d533b02dad37e72819f019c263dd159cf8a60d99b5fe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}