{"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/metaaudio-a-few-shot-audio-classification","title":"MetaAudio: A Few-Shot Audio Classification Benchmark","arxiv_id":"2204.02121","date":"2022-04-05","proceeding":null,"authors":["Calum Heggan","Sam Budgett","Timothy Hospedales","Mehrdad Yaghoobi"],"abstract":"Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.","url_abs":"https://arxiv.org/abs/2204.02121v2","url_pdf":"https://arxiv.org/pdf/2204.02121v2.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":"metaaudio-a-few-shot-audio-classification","repo_url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-audio-classification","task_name":"Few-Shot Audio Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[{"slug":"birdclef-2020-pruned","name":"BirdClef 2020  (Pruned)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"Meta-Curvature (CRNN)","rank_in_archive_order":1,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"61.34 +- 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"SimpleShot Cl2N (CRNN)","rank_in_archive_order":2,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"57.66 +- 0.43"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"Meta-Baseline (CRNN)","rank_in_archive_order":3,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"57.28 +- 0.41"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"MAML (CRNN)","rank_in_archive_order":4,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"56.26 +- 0.45"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"Prototypical Networks (CRNN)","rank_in_archive_order":5,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"56.11 +- 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)","rank_in_archive_order":6,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"36.41 +- 0.42"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-birdclef","task":"Few-Shot Audio Classification","dataset":"BirdClef 2020  (Pruned)","model":"SimpleShot CL2N (AST ImageNet - No fine-tune)","rank_in_archive_order":7,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"33.04 +- 0.41"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"Meta-Curvature (CRNN)","rank_in_archive_order":1,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"76.17 +- 0.41"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"MAML (CRNN)","rank_in_archive_order":2,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":" 74.66 ± 0.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"Meta-Baseline (CRNN)","rank_in_archive_order":3,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"71.72 +- 0.38"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"Prototypical Networks (CRNN)","rank_in_archive_order":5,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"68.83 +- 0.38"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"SimpleShot CL2N (CRNN)","rank_in_archive_order":6,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"68.82 +-0.39"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)","rank_in_archive_order":7,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"64.48 +- 0.41"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-esc-50","task":"Few-Shot Audio Classification","dataset":"ESC-50","model":"SimpleShot CL2N (AST ImageNet - No fine-tune)","rank_in_archive_order":9,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"60.41 +- 0.41"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"MAML (CRNN)","rank_in_archive_order":1,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"43.45 +- 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"Meta-Curvature (CRNN)","rank_in_archive_order":2,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"43.18 +- 0.45"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"SimpleShot CL2N (CRNN)","rank_in_archive_order":3,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"42.05 +- 0.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"Meta-Baseline (CRNN)","rank_in_archive_order":4,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"40.27 +- 0.44"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"Prototypical Networks (CRNN)","rank_in_archive_order":5,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"39.44 +- 0.44"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)","rank_in_archive_order":7,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"38.78 +- 0.41"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on","task":"Few-Shot Audio Classification","dataset":"FSDKaggle2018","model":"SimpleShot CL2N (AST ImageNet - No fine-tune)","rank_in_archive_order":9,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"33.52 +- 0.39"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"Meta-Curvature (CRNN)","rank_in_archive_order":1,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"96.47 +-0.19"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"Prototypical Networks (CRNN)","rank_in_archive_order":2,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"95.23 +- 0.19"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"MAML (CRNN)","rank_in_archive_order":3,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"93.85 +- 0.24"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"Meta-Baseline (CRNN)","rank_in_archive_order":4,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"90.74 +- 0.25"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"SimpleShot CL2N (CRNN)","rank_in_archive_order":5,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"90.04 +- 0.27"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"SimpleShot CL2N Classifier (AST pre-trained w/ ImageNet - No fine-tune)","rank_in_archive_order":7,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"66.68 +- 0.41"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-nsynth","task":"Few-Shot Audio Classification","dataset":"NSynth","model":"SimpleShot CL2N Classifier (AST ImageNet & AudioSet - No fine-tune)","rank_in_archive_order":9,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"63.78 +- 0.42"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"Meta-Curvature (CRNN)","rank_in_archive_order":1,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"63.85 +- 0.44"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"MAML (CRNN)","rank_in_archive_order":2,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"60.89 +- 0.45"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"Prototypical Networks (CRNN)","rank_in_archive_order":3,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"59.64 +- 0.44"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"Meta-Baseline (CRNN)","rank_in_archive_order":4,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"55.54 +- 0.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"SimpleShot CL2N (CRNN)","rank_in_archive_order":5,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"48.50 +- 0.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)","rank_in_archive_order":8,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"28.79 +- 0.38"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-voxceleb1","task":"Few-Shot Audio Classification","dataset":"VoxCeleb1","model":"SimpleShot CL2N (AST ImageNet - No fine-tune)","rank_in_archive_order":9,"of":10,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"28.09 +- 0.37"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-watkins","task":"Few-Shot Audio Classification","dataset":"Watkins Marine Mammal Sounds","model":"SimpleShot CL2N (AST ImageNet - No fine-tune)","rank_in_archive_order":2,"of":5,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"55.40 ± 0.42"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-audio-classification-on-watkins","task":"Few-Shot Audio Classification","dataset":"Watkins Marine Mammal Sounds","model":"SimpleShot CL2N (AST ImageNet & AudioSet- No fine-tune)","rank_in_archive_order":4,"of":5,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"51.81 ± 0.42"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02121"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/cheggan/metaaudio-a-few-shot-audio-classification-benchmark","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"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":"c49351fe44ccebfd","entry":"my_collate","repo":"cheggan/metaaudio-a-few-shot-audio-classification-benchmark","repo_kind":"official","path":"Examples/MAML_ESC/MAML_Main.py","file_url":"https://github.com/cheggan/metaaudio-a-few-shot-audio-classification-benchmark/blob/HEAD/Examples/MAML_ESC/MAML_Main.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c49351fe44ccebfd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}