{"url":"/task/audio-tagging","name":"Audio Tagging","slug":"audio-tagging","description_markdown":"Audio tagging is a task to predict the tags of audio clips. Audio tagging tasks include music tagging, acoustic scene classification, audio event classification, etc.","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":81,"papers_with_code":49,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":10,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-tagging-on-audioset","slug":"audio-tagging-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":11,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"CAV-MAE (Audio-Visual)","paper_title":"Contrastive Audio-Visual Masked Autoencoder","paper_url":"/paper/contrastive-audio-visual-masked-autoencoder","paper_date":"2022-10-02","arxiv_id":"2210.07839","code_links":[{"title":"yuangongnd/cav-mae","url":"https://github.com/yuangongnd/cav-mae"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/vocalsound","name":"VocalSound","full_name":"","num_papers_in_archive":24},{"url":"/dataset/fsdkaggle2018","name":"FSDKaggle2018","full_name":"FSDKaggle2018","num_papers_in_archive":12},{"url":"/dataset/ssc","name":"SSC","full_name":"Spiking Speech Commands v0.2","num_papers_in_archive":7},{"url":"/dataset/chime-home","name":"CHiME-Home","full_name":"CHiME-Home","num_papers_in_archive":5},{"url":"/dataset/fsdkaggle2019","name":"FSDKaggle2019","full_name":"FSDKaggle2019","num_papers_in_archive":5},{"url":"/dataset/sonyc-ust-v2","name":"SONYC-UST-V2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/singa-pura","name":"SINGA:PURA","full_name":"SINGApore: Polyphonic URban Audio","num_papers_in_archive":2},{"url":"/dataset/meerkat-meerkat-kalahari-audio-transcripts","name":"MeerKAT: Meerkat Kalahari Audio Transcripts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sound-of-water-50","name":"Sound of Water 50","full_name":"Sound of Water 50","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":49,"tagged_in_all":81,"items":[{"url":"/paper/ast-audio-spectrogram-transformer","title":"AST: Audio Spectrogram Transformer","date":"2021-04-05","arxiv_id":"2104.01778","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/speech-denoising-with-deep-feature-losses","title":"Speech Denoising with Deep Feature Losses","date":"2018-06-27","arxiv_id":"1806.10522","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/musicnn-pre-trained-convolutional-neural","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","date":"2019-09-14","arxiv_id":"1909.06654","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/general-purpose-tagging-of-freesound-audio","title":"General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline","date":"2018-07-26","arxiv_id":"1807.09902","repositories_listed":3,"syntology":null},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/audio-classification-with-dilated-convolution","title":"Audio classification with Dilated Convolution with Learnable Spacings","date":"2023-09-25","arxiv_id":"2309.13972","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-audio-teacher-student","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","date":"2023-06-07","arxiv_id":"2306.04186","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/efficient-training-of-audio-transformers-with","title":"Efficient Training of Audio Transformers with Patchout","date":"2021-10-11","arxiv_id":"2110.05069","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/crnns-for-urban-sound-tagging-with","title":"CRNNs for Urban Sound Tagging with spatiotemporal context","date":"2020-08-24","arxiv_id":"2008.10413","repositories_listed":2,"syntology":null},{"url":"/paper/audio-tagging-with-noisy-labels-and-minimal","title":"Audio tagging with noisy labels and minimal supervision","date":"2019-06-07","arxiv_id":"1906.02975","repositories_listed":2,"syntology":null},{"url":"/paper/general-audio-tagging-with-ensembling","title":"General audio tagging with ensembling convolutional neural network and statistical features","date":"2018-10-30","arxiv_id":"1810.12832","repositories_listed":2,"syntology":null},{"url":"/paper/speech-denoising-convolutional-neural-network","title":"Speech Denoising Convolutional Neural Network trained with Deep Feature Losses.","date":"2018-06-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-gated-recurrent-neural-network","title":"Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging","date":"2017-02-24","arxiv_id":"1702.07787","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-feature-learning-based-on-deep","title":"Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging","date":"2016-07-13","arxiv_id":"1607.03681","repositories_listed":2,"syntology":null},{"url":"/paper/baseline-systems-and-evaluation-metrics-for","title":"Baseline Systems and Evaluation Metrics for Spatial Semantic Segmentation of Sound Scenes","date":"2025-03-28","arxiv_id":"2503.22088","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-label-propagation-a-model-size","title":"Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging","date":"2025-03-26","arxiv_id":"2503.21826","repositories_listed":1,"syntology":null},{"url":"/paper/solla-towards-a-speech-oriented-llm-that","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","date":"2025-03-19","arxiv_id":"2503.15338","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-performance-complexity-trade-offs","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","date":"2025-03-14","arxiv_id":"2503.11373","repositories_listed":1,"syntology":null},{"url":"/paper/masked-latent-prediction-and-classification","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","date":"2025-02-17","arxiv_id":"2502.12031","repositories_listed":1,"syntology":null},{"url":"/paper/lc-protonets-multi-label-few-shot-learning","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","date":"2024-09-17","arxiv_id":"2409.11264","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-ip-broadcasting-with-audio-tags","title":"Integrating IP Broadcasting with Audio Tags: Workflow and Challenges","date":"2024-07-22","arxiv_id":"2407.15423","repositories_listed":1,"syntology":null},{"url":"/paper/dass-distilled-audio-state-space-models-are","title":"DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners","date":"2024-07-04","arxiv_id":"2407.04082","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/perceptual-musical-features-for-interpretable","title":"Perceptual Musical Features for Interpretable Audio Tagging","date":"2023-12-18","arxiv_id":"2312.11234","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-convolutional-neural-networks-as","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","date":"2023-10-24","arxiv_id":"2310.15648","repositories_listed":1,"syntology":null},{"url":"/paper/audio-tagging-on-an-embedded-hardware","title":"Audio Tagging on an Embedded Hardware Platform","date":"2023-06-15","arxiv_id":"2306.09106","repositories_listed":1,"syntology":null},{"url":"/paper/e-panns-sound-recognition-using-efficient-pre","title":"E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks","date":"2023-05-30","arxiv_id":"2305.18665","repositories_listed":1,"syntology":null},{"url":"/paper/robust-cross-modal-knowledge-distillation-for","title":"Robust Cross-Modal Knowledge Distillation for Unconstrained Videos","date":"2023-04-16","arxiv_id":"2304.07775","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/zorro-the-masked-multimodal-transformer","title":"Zorro: the masked multimodal transformer","date":"2023-01-23","arxiv_id":"2301.09595","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ontology-aware-learning-and-evaluation-for","title":"Ontology-aware Learning and Evaluation for Audio Tagging","date":"2022-11-22","arxiv_id":"2211.12195","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}