{"url":"/task/sound-classification","name":"Sound Classification","slug":"sound-classification","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":148,"papers_with_code":61,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/infantmarmosetsvox","name":"InfantMarmosetsVox","full_name":"InfantMarmosetsVox","num_papers_in_archive":3},{"url":"/dataset/audio-de-mosquitos-aedes-aegypti","name":"Audio de mosquitos Aedes Aegypti","full_name":"Wing beats","num_papers_in_archive":1}],"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":30,"of":61,"tagged_in_all":148,"items":[{"url":"/paper/deep-convolutional-neural-networks-and-data-1","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","date":"2016-08-15","arxiv_id":"1608.04363","repositories_listed":5,"syntology":null},{"url":"/paper/audioclip-extending-clip-to-image-text-and","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","date":"2021-06-24","arxiv_id":"2106.13043","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/buet-multi-disease-heart-sound-dataset-a","title":"BUET Multi-disease Heart Sound Dataset: A Comprehensive Auscultation Dataset for Developing Computer-Aided Diagnostic Systems","date":"2024-09-01","arxiv_id":"2409.00724","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-tracking-based-training-of","title":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","date":"2021-10-29","arxiv_id":"2111.00030","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-environmental-sound-classification","title":"End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network","date":"2019-04-18","arxiv_id":"1904.08990","repositories_listed":2,"syntology":null},{"url":"/paper/masked-conditional-neural-networks-for-1","title":"Masked Conditional Neural Networks for Environmental Sound Classification","date":"2018-05-25","arxiv_id":"1805.10004","repositories_listed":2,"syntology":null},{"url":"/paper/domain-adaptation-method-and-modality-gap","title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","date":"2025-06-04","arxiv_id":"2506.04376","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-differential-denoising-for","title":"Adaptive Differential Denoising for Respiratory Sounds Classification","date":"2025-06-03","arxiv_id":"2506.02505","repositories_listed":1,"syntology":null},{"url":"/paper/improving-respiratory-sound-classification","title":"Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles","date":"2025-05-28","arxiv_id":"2505.22027","repositories_listed":1,"syntology":null},{"url":"/paper/patient-aware-feature-alignment-for-robust","title":"Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses","date":"2025-05-28","arxiv_id":"2505.23834","repositories_listed":1,"syntology":null},{"url":"/paper/the-computation-of-generalized-embeddings-for","title":"The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive Learning","date":"2025-05-19","arxiv_id":"2505.12904","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-convolutional-dictionary","title":"Weakly Supervised Convolutional Dictionary Learning for Multi-Label Classification","date":"2025-03-11","arxiv_id":"2503.08573","repositories_listed":1,"syntology":null},{"url":"/paper/cycleguardian-a-framework-for-automatic","title":"CycleGuardian: A Framework for Automatic RespiratorySound classification Based on Improved Deep clustering and Contrastive Learning","date":"2025-02-02","arxiv_id":"2502.00734","repositories_listed":1,"syntology":null},{"url":"/paper/manikin-recorded-cardiopulmonary-sounds","title":"Manikin-Recorded Cardiopulmonary Sounds Dataset Using Digital Stethoscope","date":"2024-10-04","arxiv_id":"2410.03280","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-sound-classification-with-the","title":"Heterogeneous sound classification with the Broad Sound Taxonomy and Dataset","date":"2024-10-01","arxiv_id":"2410.00980","repositories_listed":1,"syntology":null},{"url":"/paper/bts-bridging-text-and-sound-modalities-for","title":"BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification","date":"2024-06-10","arxiv_id":"2406.06786","repositories_listed":1,"syntology":null},{"url":"/paper/eat-self-supervised-pre-training-with","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","date":"2024-01-07","arxiv_id":"2401.03497","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/self-supervised-learning-for-few-shot-bird","title":"Self-Supervised Learning for Few-Shot Bird Sound Classification","date":"2023-12-25","arxiv_id":"2312.15824","repositories_listed":1,"syntology":null},{"url":"/paper/stethoscope-guided-supervised-contrastive","title":"Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification","date":"2023-12-15","arxiv_id":"2312.09603","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-spectrogram-transformer-for","title":"Multi-View Spectrogram Transformer for Respiratory Sound Classification","date":"2023-11-16","arxiv_id":"2311.09655","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-fine-tuning-using-generated","title":"Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance","date":"2023-11-11","arxiv_id":"2311.06480","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/astfsonn-a-unified-framework-based-on-time","title":"AsTFSONN: A Unified Framework Based on Time-Frequency Domain Self-Operational Neural Network for Asthmatic Lung Sound Classification","date":"2023-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","arxiv_id":"2305.14032","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/face-fast-accurate-and-context-aware-audio","title":"Face: Fast, Accurate and Context-Aware Audio Annotation and Classification","date":"2023-03-07","arxiv_id":"2303.03666","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-classification-to-improve-the","title":"Unsupervised classification to improve the quality of a bird song recording dataset","date":"2023-02-15","arxiv_id":"2302.07560","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-for-audio-visual-sound-event","title":"A dataset for Audio-Visual Sound Event Detection in Movies","date":"2023-02-14","arxiv_id":"2302.07315","repositories_listed":1,"syntology":null},{"url":"/paper/epic-sounds-a-large-scale-dataset-of-actions","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","date":"2023-02-01","arxiv_id":"2302.00646","repositories_listed":1,"syntology":null},{"url":"/paper/xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","repositories_listed":1,"syntology":null},{"url":"/paper/effective-audio-classification-network-based","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","date":"2022-11-05","arxiv_id":"2211.02940","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-contrastive-learning-for-3","title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","date":"2022-10-27","arxiv_id":"2210.16192","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}