{"url":"/task/music-information-retrieval","name":"Music Information Retrieval","slug":"music-information-retrieval","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":255,"papers_with_code":125,"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":26,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/fma","name":"FMA","full_name":"Free Music Archive","num_papers_in_archive":128},{"url":"/dataset/medleydb","name":"MedleyDB","full_name":"","num_papers_in_archive":47},{"url":"/dataset/rwc","name":"RWC","full_name":"Real World Computing Music Database","num_papers_in_archive":43},{"url":"/dataset/mtg-jamendo","name":"MTG-Jamendo","full_name":null,"num_papers_in_archive":39},{"url":"/dataset/urmp","name":"URMP","full_name":"University of Rochester Multi-Modal Musical Performance","num_papers_in_archive":38},{"url":"/dataset/guitarset","name":"GuitarSet","full_name":null,"num_papers_in_archive":31},{"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/ikala","name":"iKala","full_name":"","num_papers_in_archive":20},{"url":"/dataset/lakh-pianoroll-dataset","name":"Lakh Pianoroll Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/giantmidi-piano","name":"GiantMIDI-Piano","full_name":"","num_papers_in_archive":9},{"url":"/dataset/openmic-2018","name":"OpenMIC-2018","full_name":null,"num_papers_in_archive":8},{"url":"/dataset/youtube-100m","name":"YouTube-100M","full_name":"YouTube-100m","num_papers_in_archive":8},{"url":"/dataset/mssd","name":"MSSD","full_name":"Music Streaming Sessions Dataset","num_papers_in_archive":7},{"url":"/dataset/goodsounds","name":"GoodSounds","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/jazznet","name":"jazznet","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mumu","name":"MuMu","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cosian","name":"COSIAN","full_name":"a collection of singing voice annotation","num_papers_in_archive":3},{"url":"/dataset/fingerprint-dataset","name":"Fingerprint Dataset","full_name":"Neural Audio Fingerprint Dataset","num_papers_in_archive":2},{"url":"/dataset/cal10k","name":"CAL10K","full_name":"Computer Audition Lab 10000","num_papers_in_archive":1},{"url":"/dataset/guitar-techs","name":"Guitar-TECHS","full_name":"Guitar Tones/Techniques, Excerpts & Chords Dataset","num_papers_in_archive":1},{"url":"/dataset/haydn-annotation-dataset","name":"Haydn Annotation Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/niko-chord-progression-dataset","name":"Niko Chord Progression Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nlakh","name":"Nlakh","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/virtuoso-strings","name":"Virtuoso Strings","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cadenza-woodwind","name":"Cadenza Woodwind","full_name":"","num_papers_in_archive":0}],"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":125,"tagged_in_all":255,"items":[{"url":"/paper/music-artist-classification-with","title":"Music Artist Classification with Convolutional Recurrent Neural Networks","date":"2019-01-14","arxiv_id":"1901.04555","repositories_listed":6,"syntology":null},{"url":"/paper/mustango-toward-controllable-text-to-music","title":"Mustango: Toward Controllable Text-to-Music Generation","date":"2023-11-14","arxiv_id":"2311.08355","repositories_listed":4,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/revisiting-singing-voice-detection-a","title":"Revisiting Singing Voice Detection: a Quantitative Review and the Future Outlook","date":"2018-06-04","arxiv_id":"1806.01180","repositories_listed":4,"syntology":null},{"url":"/paper/midicaps-a-large-scale-midi-dataset-with-text","title":"MidiCaps: A large-scale MIDI dataset with text captions","date":"2024-06-04","arxiv_id":"2406.02255","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/neural-audio-fingerprint-for-high-specific","title":"Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning","date":"2020-10-22","arxiv_id":"2010.11910","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/giantmidi-piano-a-large-scale-midi-dataset","title":"GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music","date":"2020-10-11","arxiv_id":"2010.07061","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/rethinking-cnn-models-for-audio","title":"Rethinking CNN Models for Audio Classification","date":"2020-07-22","arxiv_id":"2007.11154","repositories_listed":3,"syntology":null},{"url":"/paper/optical-music-recognition-with-convolutional","title":"Optical Music Recognition with Convolutional Sequence-to-Sequence Models","date":"2017-07-16","arxiv_id":"1707.04877","repositories_listed":3,"syntology":null},{"url":"/paper/universal-music-representations-evaluating","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","date":"2025-06-20","arxiv_id":"2506.17055","repositories_listed":2,"syntology":null},{"url":"/paper/all-in-one-metrical-and-functional-structure","title":"All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio","date":"2023-07-31","arxiv_id":"2307.16425","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"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/a-data-driven-methodology-for-considering","title":"A Data-Driven Methodology for Considering Feasibility and Pairwise Likelihood in Deep Learning Based Guitar Tablature Transcription Systems","date":"2022-04-17","arxiv_id":"2204.08094","repositories_listed":2,"syntology":null},{"url":"/paper/nonnegative-tucker-decomposition-with-beta","title":"Nonnegative Tucker Decomposition with Beta-divergence for Music Structure Analysis of Audio Signals","date":"2021-10-27","arxiv_id":"2110.14434","repositories_listed":2,"syntology":null},{"url":"/paper/learning-sparse-analytic-filters-for-piano","title":"Learning Sparse Analytic Filters for Piano Transcription","date":"2021-08-23","arxiv_id":"2108.10382","repositories_listed":2,"syntology":null},{"url":"/paper/sequence-to-sequence-piano-transcription-with","title":"Sequence-to-Sequence Piano Transcription with Transformers","date":"2021-07-19","arxiv_id":"2107.09142","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/tracing-back-music-emotion-predictions-to","title":"Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities","date":"2021-06-14","arxiv_id":"2106.07787","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"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/learning-a-representation-for-cover-song","title":"Learning a Representation for Cover Song Identification Using Convolutional Neural Network","date":"2019-11-01","arxiv_id":"1911.00334","repositories_listed":2,"syntology":null},{"url":"/paper/machines-listening-to-music-the-role-of","title":"Improving Machine Hearing on Limited Data Sets","date":"2019-03-21","arxiv_id":"1903.08950","repositories_listed":2,"syntology":null},{"url":"/paper/singing-voice-separation-using-a-deep","title":"Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy","date":"2018-12-04","arxiv_id":"1812.01278","repositories_listed":2,"syntology":null},{"url":"/paper/crepe-a-convolutional-representation-for","title":"CREPE: A Convolutional Representation for Pitch Estimation","date":"2018-02-17","arxiv_id":"1802.06182","repositories_listed":2,"syntology":{"n":23,"n_ran":3,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/a-tutorial-on-deep-learning-for-music","title":"A Tutorial on Deep Learning for Music Information Retrieval","date":"2017-09-13","arxiv_id":"1709.04396","repositories_listed":2,"syntology":null},{"url":"/paper/a-hierarchical-deep-learning-approach-for","title":"A Hierarchical Deep Learning Approach for Minority Instrument Detection","date":"2025-06-26","arxiv_id":"2506.21167","repositories_listed":1,"syntology":null},{"url":"/paper/a-mamba-based-network-for-semi-supervised","title":"A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary Regularization","date":"2025-05-13","arxiv_id":"2505.08681","repositories_listed":1,"syntology":null},{"url":"/paper/learning-music-audio-representations-with","title":"Learning Music Audio Representations With Limited Data","date":"2025-05-09","arxiv_id":"2505.06042","repositories_listed":1,"syntology":null},{"url":"/paper/the-gigamidi-dataset-with-features-for","title":"The GigaMIDI Dataset with Features for Expressive Music Performance Detection","date":"2025-02-24","arxiv_id":"2502.17726","repositories_listed":1,"syntology":null},{"url":"/paper/musical-score-following-using-statistical","title":"Musical Score Following using Statistical Inference","date":"2025-02-06","arxiv_id":"2502.10426","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-gpt-s-ability-as-a-judge-in-music","title":"Exploring GPT's Ability as a Judge in Music Understanding","date":"2025-01-22","arxiv_id":"2501.13261","repositories_listed":1,"syntology":null},{"url":"/paper/text2playlist-generating-personalized","title":"Text2Playlist: Generating Personalized Playlists from Text on Deezer","date":"2025-01-10","arxiv_id":"2501.05894","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-dynamic-music-emotion","title":"Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-Learning","date":"2024-12-26","arxiv_id":"2412.19200","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"}}