{"url":"/sota/environmental-sound-classification-on","task":{"name":"Environmental Sound Classification","url":"/task/environmental-sound-classification","note":null},"dataset":{"name":"UrbanSound8K","url":"/dataset/urbansound8k-1"},"category":"Audio","categories":["Audio"],"category_note":null,"description":"Classification of Environmental Sounds. Most often sounds found in Urban environments. Task related to noise monitoring.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"AudioCLIP","metrics":{"Accuracy":"90.07"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/audioclip-extending-clip-to-image-text-and","paper_url":"https://arxiv.org/abs/2106.13043v1","paper_title":"AudioCLIP: Extending CLIP to Image, Text and Audio","code":"https://github.com/iver56/audiomentations","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"MATPAC (SSL, linear eval)","metrics":{"Accuracy":"89.4"},"uses_additional_data":false,"paper_date":"2025-02-17","paper":"/paper/masked-latent-prediction-and-classification","paper_url":"https://arxiv.org/abs/2502.12031v1","paper_title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","code":"https://github.com/aurianworld/matpac","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"1DCNN","metrics":{"Accuracy":"89"},"uses_additional_data":true,"paper_date":"2019-04-18","paper":"/paper/end-to-end-environmental-sound-classification","paper_url":"http://arxiv.org/abs/1904.08990v1","paper_title":"End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network","code":"https://github.com/Logan97117/environmental_sound_classification_1DCNN","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}