{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":52,"of":52,"of_with_code":23,"tagged_in_all":52,"counts":{"archive_papers_tagged":52,"with_a_code_link":23,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":52,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/convolutional-recurrent-neural-networks-for-1","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transfer-learning-for-music-classification#ran","syntology_url":"https://syntology.ai/paper/1703.09179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09179"}},"official":{"repos":["keunwoochoi/transfer_learning_music"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-level-deep-convolutional-neural","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sample-level-deep-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1703.01789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01789"}},"official":null}},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/moonbeam-a-midi-foundation-model-using-both#ran","syntology_url":"https://syntology.ai/paper/2505.15559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15559"}},"official":null}},{"url":"/paper/clamp-2-multimodal-music-information","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-learning-for-audio-based-music#ran","syntology_url":"https://syntology.ai/paper/1907.02670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02670"}},"official":{"repos":["kunimi00/ZSL_music_tagging"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-level-and-multi-scale-feature-1","slug":"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","slug":"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},{"url":null,"slug":"progressive-rock-music-classification","title":"Progressive Rock Music Classification","date":"2025-04-15","arxiv_id":"2504.10821","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-independent-deterministic","title":"EVolutionary Independent DEtermiNistiC Explanation","date":"2025-01-20","arxiv_id":"2501.16357","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-music-classification-and-generation","title":"Arabic Music Classification and Generation using Deep Learning","date":"2024-10-25","arxiv_id":"2410.19719","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-sub-genre-classification-for","title":"Benchmarking Sub-Genre Classification For Mainstage Dance Music","date":"2024-09-10","arxiv_id":"2409.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-era-recognition-using-supervised","title":"Music Era Recognition Using Supervised Contrastive Learning and Artist Information","date":"2024-07-07","arxiv_id":"2407.05368","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-hear-you-loud-and-clear","title":"Hearing-Loss Compensation Using Deep Neural Networks: A Framework and Results From a Listening Test","date":"2024-03-15","arxiv_id":"2403.10420","repositories_listed":0,"syntology":null},{"url":null,"slug":"significance-of-chirp-mfcc-as-a-feature-in","title":"Significance of Chirp MFCC as a Feature in Speech and Audio Applications","date":"2024-02-19","arxiv_id":"2402.12239","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-leveraging-pre-trained-self-supervised","title":"Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies","date":"2023-06-22","arxiv_id":"2306.12714","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectnet-end-to-end-audio-signal","title":"SpectNet : End-to-End Audio Signal Classification Using Learnable Spectrograms","date":"2022-11-17","arxiv_id":"2211.09352","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-music-representations-with-wav2vec-2","title":"Learning Music Representations with wav2vec 2.0","date":"2022-10-27","arxiv_id":"2210.15310","repositories_listed":0,"syntology":null},{"url":null,"slug":"iranian-modal-music-dastgah-detection-using","title":"Iranian Modal Music (Dastgah) detection using deep neural networks","date":"2022-03-29","arxiv_id":"2203.15335","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-with-positive-negative","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","date":"2022-03-17","arxiv_id":"2203.09129","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualizing-ensemble-predictions-of-music","title":"Visualizing Ensemble Predictions of Music Mood","date":"2021-12-14","arxiv_id":"2112.07627","repositories_listed":0,"syntology":null},{"url":null,"slug":"spliceout-a-simple-and-efficient-audio","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","date":"2021-09-30","arxiv_id":"2110.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-network-for-musical-instrument","title":"Deep Neural Network for Musical Instrument Recognition using MFCCs","date":"2021-05-03","arxiv_id":"2105.00933","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-audio-and-music-classification","title":"Multi-view Audio and Music Classification","date":"2021-03-03","arxiv_id":"2103.02420","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-self-supervised-pre-training-for","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","date":"2021-02-05","arxiv_id":"2102.03229","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-content-analysis","title":"Audio Content Analysis","date":"2021-01-01","arxiv_id":"2101.00132","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-midi-based-composer","title":"Large-Scale MIDI-based Composer Classification","date":"2020-10-28","arxiv_id":"2010.14805","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-style-classification-with-compared","title":"Music Style Classification with Compared Methods in XGB and BPNN","date":"2019-12-03","arxiv_id":"1912.01203","repositories_listed":0,"syntology":null},{"url":null,"slug":"lukthung-classification-using-neural-networks","title":"Lukthung Classification Using Neural Networks on Lyrics and Audios","date":"2019-08-23","arxiv_id":"1908.08769","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-learning-and-knowledge-transfer-in","title":"Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging","date":"2019-06-20","arxiv_id":"1906.08615","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-embedded-cnn-for-music-tagging","title":"Multi-scale Embedded CNN for Music Tagging (MsE-CNN)","date":"2019-06-16","arxiv_id":"1906.06746","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-music-classification-model-based-on-metric","title":"A Music Classification Model based on Metric Learning and Feature Extraction from MP3 Audio Files","date":"2019-05-30","arxiv_id":"1905.12804","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-classification-of-bit-representation","title":"Audio Classification of Bit-Representation Waveform","date":"2019-04-08","arxiv_id":"1904.04364","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-noisy-labels-on-deep","title":"The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging","date":"2017-06-07","arxiv_id":"1706.02361","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-multivariate-sequence","title":"Efficient multivariate sequence classification","date":"2014-09-29","arxiv_id":"1409.8211","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-fado-music-classification","title":"Automatic Fado Music Classification","date":"2014-06-17","arxiv_id":"1406.4447","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-representation-for-invariance-and","title":"A Deep Representation for Invariance And Music Classification","date":"2014-04-01","arxiv_id":"1404.0400","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/music-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/music-classification/papers/ran/1","json":"/task/music-classification/papers/ran/1.json","rows":4}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"e02e07021387fc82b53902b3ab418e208a5babcb91841820c602fea8fd5c5855","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}