{"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/few-shot-audio-classification","name":"Few-Shot Audio Classification","slug":"few-shot-audio-classification","description_markdown":"Few-shot classification for audio signals. Presents a unique challenge compared to other few-shot domains as we deal with temporal dependencies as well.\r\n\r\nLike other few-shot problems, few-shot audio classification can be tackled in a  variety of ways, from using supervised meta-learning on the same primary dataset, to pre-training on an external dataset and utilising linear readout. For this reason, results in each dataset leaderboard should be correctly tagged e.g. with \"Within Dataset Meta-Learning\" etc","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":5,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"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":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/few-shot-audio-classification-on","slug":"few-shot-audio-classification-on","dataset":"FSDKaggle2018","dataset_url":"/dataset/fsdkaggle2018","rows_in_archive":10,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MAML (CRNN)","paper_title":"MetaAudio: A Few-Shot Audio Classification Benchmark","paper_url":"/paper/metaaudio-a-few-shot-audio-classification","paper_date":"2022-04-05","arxiv_id":"2204.02121","code_links":[{"title":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","slug":"few-shot-audio-classification-on-birdclef","dataset":"BirdClef 2020  (Pruned)","dataset_url":"/dataset/birdclef-2020-pruned","rows_in_archive":10,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"Meta-Curvature (CRNN)","paper_title":"MetaAudio: A Few-Shot Audio Classification Benchmark","paper_url":"/paper/metaaudio-a-few-shot-audio-classification","paper_date":"2022-04-05","arxiv_id":"2204.02121","code_links":[{"title":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","slug":"few-shot-audio-classification-on-esc-50","dataset":"ESC-50","dataset_url":"/dataset/esc-50","rows_in_archive":10,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"Meta-Curvature (CRNN)","paper_title":"MetaAudio: A Few-Shot Audio Classification Benchmark","paper_url":"/paper/metaaudio-a-few-shot-audio-classification","paper_date":"2022-04-05","arxiv_id":"2204.02121","code_links":[{"title":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","slug":"few-shot-audio-classification-on-nsynth","dataset":"NSynth","dataset_url":"/dataset/nsynth","rows_in_archive":10,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"Meta-Curvature (CRNN)","paper_title":"MetaAudio: A Few-Shot Audio Classification Benchmark","paper_url":"/paper/metaaudio-a-few-shot-audio-classification","paper_date":"2022-04-05","arxiv_id":"2204.02121","code_links":[{"title":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","slug":"few-shot-audio-classification-on-voxceleb1","dataset":"VoxCeleb1","dataset_url":"/dataset/voxceleb1","rows_in_archive":10,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"Meta-Curvature (CRNN)","paper_title":"MetaAudio: A Few-Shot Audio Classification Benchmark","paper_url":"/paper/metaaudio-a-few-shot-audio-classification","paper_date":"2022-04-05","arxiv_id":"2204.02121","code_links":[{"title":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/few-shot-audio-classification-on-watkins","slug":"few-shot-audio-classification-on-watkins","dataset":"Watkins Marine Mammal Sounds","dataset_url":"/dataset/watkins-marine-mammal-sounds","rows_in_archive":5,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)","paper_title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","paper_url":"/paper/mt-slvr-multi-task-self-supervised-learning","paper_date":"2023-05-29","arxiv_id":"2305.17191","code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}],"syntology":null}},{"leaderboard":"/sota/few-shot-audio-classification-on-common-voice","slug":"few-shot-audio-classification-on-common-voice","dataset":"Common Voice","dataset_url":"/dataset/common-voice","rows_in_archive":3,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)","paper_title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","paper_url":"/paper/mt-slvr-multi-task-self-supervised-learning","paper_date":"2023-05-29","arxiv_id":"2305.17191","code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}],"syntology":null}},{"leaderboard":"/sota/few-shot-audio-classification-on-crema-d","slug":"few-shot-audio-classification-on-crema-d","dataset":"CREMA-D","dataset_url":"/dataset/crema-d","rows_in_archive":3,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)","paper_title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","paper_url":"/paper/mt-slvr-multi-task-self-supervised-learning","paper_date":"2023-05-29","arxiv_id":"2305.17191","code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}],"syntology":null}},{"leaderboard":"/sota/few-shot-audio-classification-on-speech","slug":"few-shot-audio-classification-on-speech","dataset":"Speech Command v2","dataset_url":null,"rows_in_archive":3,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"SimCLR (FSD50K, RN18)","paper_title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","paper_url":"/paper/mt-slvr-multi-task-self-supervised-learning","paper_date":"2023-05-29","arxiv_id":"2305.17191","code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}],"syntology":null}},{"leaderboard":"/sota/few-shot-audio-classification-on-speech-1","slug":"few-shot-audio-classification-on-speech-1","dataset":"Speech Accent Archive","dataset_url":"/dataset/speech-accent-archive","rows_in_archive":3,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"MT-SLVR (SimCLR + MLAP) w/ Parallel Adapters (FSD50K, RN18)","paper_title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","paper_url":"/paper/mt-slvr-multi-task-self-supervised-learning","paper_date":"2023-05-29","arxiv_id":"2305.17191","code_links":[{"title":"cheggan/mt-slvr","url":"https://github.com/cheggan/mt-slvr"}],"syntology":null}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449},{"url":"/dataset/esc-50","name":"ESC-50","full_name":"ESC-50","num_papers_in_archive":387},{"url":"/dataset/nsynth","name":"NSynth","full_name":"NSynth","num_papers_in_archive":138},{"url":"/dataset/crema-d","name":"CREMA-D","full_name":"CREMA-D","num_papers_in_archive":28},{"url":"/dataset/fsdkaggle2018","name":"FSDKaggle2018","full_name":"FSDKaggle2018","num_papers_in_archive":12},{"url":"/dataset/birdclef-2020-pruned","name":"BirdClef 2020  (Pruned)","full_name":"","num_papers_in_archive":3},{"url":"/dataset/speech-accent-archive","name":"Speech Accent Archive","full_name":"The Speech Accent Archive","num_papers_in_archive":2},{"url":"/dataset/watkins-marine-mammal-sounds","name":"Watkins Marine Mammal Sounds","full_name":"Watkins Marine Mammal Sound Database","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/few-shot-learning","name":"Few-Shot Learning"}],"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":8,"of":8,"of_with_code":5,"tagged_in_all":8,"counts":{"archive_papers_tagged":8,"with_a_code_link":5,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/acoustic-prompt-tuning-empowering-large","slug":"acoustic-prompt-tuning-empowering-large","title":"Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities","date":"2023-11-30","arxiv_id":"2312.00249","repositories_listed":2,"syntology":null},{"url":"/paper/episodic-fine-tuning-prototypical-networks","slug":"episodic-fine-tuning-prototypical-networks","title":"Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classification","date":"2024-10-04","arxiv_id":"2410.05302","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-transferability-of-large-scale-self","slug":"on-the-transferability-of-large-scale-self","title":"On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification","date":"2024-02-02","arxiv_id":"2402.01274","repositories_listed":1,"syntology":null},{"url":"/paper/mt-slvr-multi-task-self-supervised-learning","slug":"mt-slvr-multi-task-self-supervised-learning","title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","date":"2023-05-29","arxiv_id":"2305.17191","repositories_listed":1,"syntology":null},{"url":"/paper/metaaudio-a-few-shot-audio-classification","slug":"metaaudio-a-few-shot-audio-classification","title":"MetaAudio: A Few-Shot Audio Classification Benchmark","date":"2022-04-05","arxiv_id":"2204.02121","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaaudio-a-few-shot-audio-classification#ran","syntology_url":"https://syntology.ai/paper/2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"halluaudio-hallucinating-frequency-as","title":"HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classification","date":"2023-02-27","arxiv_id":"2302.14204","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-for-few-shot-audio","title":"Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining","date":"2021-02-16","arxiv_id":"2102.08074","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-few-shot-audio-classification","title":"A Study of Few-Shot Audio Classification","date":"2020-12-02","arxiv_id":"2012.01573","repositories_listed":0,"syntology":null}],"syntology_records":1,"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":1,"papers_where_code_ran_first_page":"/task/few-shot-audio-classification/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/few-shot-audio-classification/papers/ran/1","json":"/task/few-shot-audio-classification/papers/ran/1.json","rows":1}],"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":"59ec4565ec12b380440bef3920a89b89cea9ebcdf23ac035afa086747f99e325","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}