{"url":"/task/zero-shot-audio-classification","name":"Zero-shot Audio Classification","slug":"zero-shot-audio-classification","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":18,"papers_with_code":9,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/esc-50","name":"ESC-50","full_name":"ESC-50","num_papers_in_archive":387},{"url":"/dataset/vgg-sound","name":"VGG-Sound","full_name":"","num_papers_in_archive":211},{"url":"/dataset/urbansound8k-1","name":"UrbanSound8K","full_name":"UrbanSound8K","num_papers_in_archive":147}],"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":9,"of":9,"tagged_in_all":18,"items":[{"url":"/paper/languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","arxiv_id":"2305.05665","repositories_listed":3,"syntology":{"n":34,"n_ran":24,"n_unverified":10,"n_pointer_only":32}},{"url":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","arxiv_id":"2303.17395","repositories_listed":3,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/reclap-improving-zero-shot-audio","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","date":"2024-09-13","arxiv_id":"2409.09213","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-audio-language-models-through-self","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","date":"2024-08-17","arxiv_id":"2408.09269","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-emergent-audio","title":"Investigating the Emergent Audio Classification Ability of ASR Foundation Models","date":"2023-11-15","arxiv_id":"2311.09363","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-meta-information-for-audio-based","title":"Exploring Meta Information for Audio-based Zero-shot Bird Classification","date":"2023-09-15","arxiv_id":"2309.08398","repositories_listed":1,"syntology":null},{"url":"/paper/connecting-the-dots-between-audio-and-text","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","date":"2021-12-16","arxiv_id":"2112.08995","repositories_listed":1,"syntology":null},{"url":"/paper/sound-guided-semantic-image-manipulation","title":"Sound-Guided Semantic Image Manipulation","date":"2021-11-30","arxiv_id":"2112.00007","repositories_listed":1,"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"},"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"}}