{"url":"/task/music-tagging","name":"Music Tagging","slug":"music-tagging","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":35,"papers_with_code":22,"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/magnatagatune","name":"MagnaTagATune","full_name":"","num_papers_in_archive":65},{"url":"/dataset/emopia","name":"EMOPIA","full_name":"A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation","num_papers_in_archive":23},{"url":"/dataset/atd-dataset","name":"ATD-Dataset","full_name":"Auto-Tune Detection Dataset (ATD-Dataset)","num_papers_in_archive":1},{"url":"/dataset/piast","name":"PIAST","full_name":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","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":22,"of":22,"tagged_in_all":35,"items":[{"url":"/paper/convolutional-recurrent-neural-networks-for-1","title":"Convolutional Recurrent Neural Networks for Music Classification","date":"2016-09-14","arxiv_id":"1609.04243","repositories_listed":13,"syntology":null},{"url":"/paper/automatic-tagging-using-deep-convolutional","title":"Automatic tagging using deep convolutional neural networks","date":"2016-06-01","arxiv_id":"1606.00298","repositories_listed":11,"syntology":null},{"url":"/paper/transfer-learning-for-music-classification","title":"Transfer learning for music classification and regression tasks","date":"2017-03-27","arxiv_id":"1703.09179","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"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/audiolime-listenable-explanations-using","title":"audioLIME: Listenable Explanations Using Source Separation","date":"2020-08-02","arxiv_id":"2008.00582","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-aware-interpretable-multimodal-music","title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","date":"2025-05-22","arxiv_id":"2505.17233","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/muq-self-supervised-music-representation","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","date":"2025-01-02","arxiv_id":"2501.01108","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/piast-a-multimodal-piano-dataset-with-audio","title":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","date":"2024-11-04","arxiv_id":"2411.02551","repositories_listed":1,"syntology":null},{"url":"/paper/towards-training-music-taggers-on-synthetic","title":"Towards Training Music Taggers on Synthetic Data","date":"2024-07-02","arxiv_id":"2407.02156","repositories_listed":1,"syntology":null},{"url":"/paper/an-experimental-comparison-of-multi-view-self","title":"An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging","date":"2024-04-14","arxiv_id":"2404.09177","repositories_listed":1,"syntology":null},{"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/employing-crowdsourcing-for-enriching-a-music","title":"Employing Crowdsourcing for Enriching a Music Knowledge Base in Higher Education","date":"2023-06-12","arxiv_id":"2306.07310","repositories_listed":1,"syntology":null},{"url":"/paper/mulan-a-joint-embedding-of-music-audio-and","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","date":"2022-08-26","arxiv_id":"2208.12415","repositories_listed":1,"syntology":null},{"url":"/paper/s3t-self-supervised-pre-training-with-swin","title":"S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification","date":"2022-02-21","arxiv_id":"2202.10139","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-affective-representations-of-music","title":"Enhancing Affective Representations of Music-Induced EEG through Multimodal Supervision and latent Domain Adaptation","date":"2022-02-20","arxiv_id":"2202.09750","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-source-separation-by-steering","title":"Unsupervised Source Separation By Steering Pretrained Music Models","date":"2021-10-25","arxiv_id":"2110.13071","repositories_listed":1,"syntology":null},{"url":"/paper/codified-audio-language-modeling-learns","title":"Codified audio language modeling learns useful representations for music information retrieval","date":"2021-07-12","arxiv_id":"2107.05677","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/a-modulation-front-end-for-music-audio","title":"A Modulation Front-End for Music Audio Tagging","date":"2021-05-25","arxiv_id":"2105.11836","repositories_listed":1,"syntology":null},{"url":"/paper/melon-playlist-dataset-a-public-dataset-for","title":"Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging","date":"2021-01-30","arxiv_id":"2102.00201","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-metric-learning-for-tag-based","title":"Multimodal Metric Learning for Tag-based Music Retrieval","date":"2020-10-30","arxiv_id":"2010.16030","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-audio-signal-preprocessing","title":"A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging","date":"2017-09-06","arxiv_id":"1709.01922","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"}}