{"url":"/task/music-classification","name":"Music Classification","slug":"music-classification","description_markdown":null,"categories":[{"name":"Music","url":"/area/music"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":52,"papers_with_code":23,"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":10,"subtasks":2,"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/atepp","name":"ATEPP","full_name":"Automatically Transcribed Expressive Piano Performances","num_papers_in_archive":9},{"url":"/dataset/giantmidi-piano","name":"GiantMIDI-Piano","full_name":"","num_papers_in_archive":9},{"url":"/dataset/js-fake-chorales","name":"JS Fake Chorales","full_name":"JS Fake Chorales","num_papers_in_archive":3},{"url":"/dataset/lyra-dataset","name":"Lyra Dataset","full_name":"A Dataset for Greek Traditional and Folk Music","num_papers_in_archive":2},{"url":"/dataset/melon","name":"MELON","full_name":"Melodic Design","num_papers_in_archive":1},{"url":"/dataset/mid-level-perceptual-musical-features","name":"Mid-level perceptual musical features","full_name":"","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},{"url":"/dataset/xmidi","name":"XMIDI","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/singer-identification","name":"Singer Identification"},{"url":"/task/vocal-technique-classification","name":"Vocal technique classification"}],"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":23,"of":23,"tagged_in_all":52,"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/toward-universal-text-to-music-retrieval","title":"Toward Universal Text-to-Music Retrieval","date":"2022-11-26","arxiv_id":"2211.14558","repositories_listed":3,"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/sample-level-deep-convolutional-neural","title":"Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms","date":"2017-03-06","arxiv_id":"1703.01789","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":2}},{"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/pre-training-music-classification-models-via","title":"Pre-training Music Classification Models via Music Source Separation","date":"2023-10-24","arxiv_id":"2310.15845","repositories_listed":2,"syntology":null},{"url":"/paper/clamp-contrastive-language-music-pre-training","title":"CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval","date":"2023-04-21","arxiv_id":"2304.11029","repositories_listed":2,"syntology":null},{"url":"/paper/speech-vgg-a-deep-feature-extractor-for","title":"Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing","date":"2019-10-22","arxiv_id":"1910.09909","repositories_listed":2,"syntology":null},{"url":"/paper/moonbeam-a-midi-foundation-model-using-both","title":"Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes","date":"2025-05-21","arxiv_id":"2505.15559","repositories_listed":1,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/clamp-2-multimodal-music-information","title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","date":"2024-10-17","arxiv_id":"2410.13267","repositories_listed":1,"syntology":null},{"url":"/paper/musicagent-an-ai-agent-for-music","title":"MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models","date":"2023-10-18","arxiv_id":"2310.11954","repositories_listed":1,"syntology":null},{"url":"/paper/audio-embeddings-as-teachers-for-music","title":"Audio Embeddings as Teachers for Music Classification","date":"2023-06-30","arxiv_id":"2306.17424","repositories_listed":1,"syntology":null},{"url":"/paper/symbolic-music-structure-analysis-with-graph","title":"Symbolic Music Structure Analysis with Graph Representations and Changepoint Detection Methods","date":"2023-03-24","arxiv_id":"2303.13881","repositories_listed":1,"syntology":null},{"url":"/paper/low-resource-music-genre-classification-with","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","date":"2022-11-02","arxiv_id":"2211.01317","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/music-classification-beyond-supervised","title":"Music Classification: Beyond Supervised Learning, Towards Real-world Applications","date":"2021-11-23","arxiv_id":"2111.11636","repositories_listed":1,"syntology":null},{"url":"/paper/midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-modality-agnostic-representations","title":"Exploring modality-agnostic representations for music classification","date":"2021-06-02","arxiv_id":"2106.01149","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-of-musical","title":"Contrastive Learning of Musical Representations","date":"2021-03-17","arxiv_id":"2103.09410","repositories_listed":1,"syntology":null},{"url":"/paper/receptive-field-regularized-cnns-for-music","title":"Receptive-Field Regularized CNNs for Music Classification and Tagging","date":"2020-07-27","arxiv_id":"2007.13503","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-learning-for-audio-based-music","title":"Zero-shot Learning for Audio-based Music Classification and Tagging","date":"2019-07-05","arxiv_id":"1907.02670","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/multi-level-and-multi-scale-feature-1","title":"Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification","date":"2017-06-21","arxiv_id":"1706.06810","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-deep-convolutional-neural-networks","title":"Explaining Deep Convolutional Neural Networks on Music Classification","date":"2016-07-08","arxiv_id":"1607.02444","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"}}