{"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/audio-language-datasets-of-scenes-and-events","title":"Audio-Language Datasets of Scenes and Events: A Survey","arxiv_id":"2407.06947","date":"2024-07-09","proceeding":null,"authors":["Gijs Wijngaard","Elia Formisano","Michele Esposito","Michel Dumontier"],"abstract":"Audio-language models (ALMs) generate linguistic descriptions of sound-producing events and scenes. Advances in dataset creation and computational power have led to significant progress in this domain. This paper surveys 69 datasets used to train ALMs, covering research up to September 2024 (https://github.com/GLJS/audio-datasets). It provides a comprehensive analysis of datasets origins, audio and linguistic characteristics, and use cases. Key sources include YouTube-based datasets like AudioSet with over two million samples, and community platforms like Freesound with over 1 million samples. Through principal component analysis of audio and text embeddings, the survey evaluates the acoustic and linguistic variability across datasets. It also analyzes data leakage through CLAP embeddings, and examines sound category distributions to identify imbalances. Finally, the survey identifies key challenges in developing large, diverse datasets to enhance ALM performance, including dataset overlap, biases, accessibility barriers, and the predominance of English-language content, while highlighting opportunities for improvement.","url_abs":"https://arxiv.org/abs/2407.06947v2","url_pdf":"https://arxiv.org/pdf/2407.06947v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"audio-language-datasets-of-scenes-and-events","repo_url":"https://github.com/gljs/audio-datasets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.06947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06947"}},"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/gljs/audio-datasets","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":9,"samples":[{"code_sha256_prefix":"5bac5967fd93d5e9","entry":"collate_fn","repo":"gljs/audio-datasets","repo_kind":"official","path":"clap_text_categorize.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/clap_text_categorize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bac5967fd93d5e9"}},{"code_sha256_prefix":"4cdf7759da051799","entry":"create_structured_prompt","repo":"gljs/audio-datasets","repo_kind":"official","path":"clap_text_categorize.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/clap_text_categorize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cdf7759da051799"}},{"code_sha256_prefix":"de6c090d54c17797","entry":"has_dog","repo":"gljs/audio-datasets","repo_kind":"official","path":"get_dogs.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/get_dogs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de6c090d54c17797"}},{"code_sha256_prefix":"e0512ec2d59ef318","entry":"load_embeddings","repo":"gljs/audio-datasets","repo_kind":"official","path":"visualization/clap_evaluation_heatmap.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/visualization/clap_evaluation_heatmap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0512ec2d59ef318"}},{"code_sha256_prefix":"7eca3fa9771d39aa","entry":"process_labels","repo":"gljs/audio-datasets","repo_kind":"official","path":"visualization/calc_audioset_class_unique.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/visualization/calc_audioset_class_unique.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7eca3fa9771d39aa"}},{"code_sha256_prefix":"24169b0eea211c88","entry":"tardir","repo":"gljs/audio-datasets","repo_kind":"official","path":"make_tar_utils.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/make_tar_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24169b0eea211c88"}},{"code_sha256_prefix":"26acbfda39246b6a","entry":"compute_pairwise_similarities","repo":"gljs/audio-datasets","repo_kind":"official","path":"visualization/clap_evaluation_heatmap.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/visualization/clap_evaluation_heatmap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26acbfda39246b6a"}},{"code_sha256_prefix":"b8e022027ecb13b5","entry":"load_embeddings","repo":"gljs/audio-datasets","repo_kind":"official","path":"get_diff.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/get_diff.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8e022027ecb13b5"}},{"code_sha256_prefix":"32c255a9dc33cbfe","entry":"process_row","repo":"gljs/audio-datasets","repo_kind":"official","path":"dataset_to_files.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/dataset_to_files.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32c255a9dc33cbfe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}