{"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/instrument-recognition","name":"Instrument Recognition","slug":"instrument-recognition","description_markdown":null,"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":39,"papers_with_code":26,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":[{"leaderboard":"/sota/instrument-recognition-on-nsynth","slug":"instrument-recognition-on-nsynth","dataset":"NSynth","dataset_url":"/dataset/nsynth","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"M2D-CLAP","paper_title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","paper_url":"/paper/m2d2-exploring-general-purpose-audio-language","paper_date":"2025-03-28","arxiv_id":"2503.22104","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"syntology":null}},{"leaderboard":"/sota/instrument-recognition-on-openmic-2018","slug":"instrument-recognition-on-openmic-2018","dataset":"OpenMIC-2018","dataset_url":"/dataset/openmic-2018","rows_in_archive":5,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"DyMN-L","paper_title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","paper_url":"/paper/dynamic-convolutional-neural-networks-as","paper_date":"2023-10-24","arxiv_id":"2310.15648","code_links":[{"title":"fschmid56/efficientat","url":"https://github.com/fschmid56/efficientat"}],"syntology":null}},{"leaderboard":"/sota/instrument-recognition-on-irmas","slug":"instrument-recognition-on-irmas","dataset":"IRMAS","dataset_url":null,"rows_in_archive":1,"metrics":["F1-score","Precision","Recall"],"first_row_in_archive_order":{"model":"SVM","paper_title":"Predominant Musical Instrument Classification based on Spectral Features","paper_url":"/paper/predominant-musical-instrument-classification","paper_date":"2019-11-30","arxiv_id":"1912.02606","code_links":[{"title":"vntkumar8/musical-instrument-classification","url":"https://github.com/vntkumar8/musical-instrument-classification"}],"syntology":null}}],"datasets":[{"url":"/dataset/nsynth","name":"NSynth","full_name":"NSynth","num_papers_in_archive":138},{"url":"/dataset/kvasir-instrument","name":"Kvasir-Instrument","full_name":"","num_papers_in_archive":19},{"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}],"subtasks":[],"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":39,"of":39,"of_with_code":26,"tagged_in_all":39,"counts":{"archive_papers_tagged":39,"with_a_code_link":26,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":39,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/atst-audio-representation-learning-with","slug":"atst-audio-representation-learning-with","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","date":"2022-04-26","arxiv_id":"2204.12076","repositories_listed":4,"syntology":null},{"url":"/paper/nanonet-real-time-polyp-segmentation-in-video","slug":"nanonet-real-time-polyp-segmentation-in-video","title":"NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy","date":"2021-04-22","arxiv_id":"2104.11138","repositories_listed":3,"syntology":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/self-supervised-audio-teacher-student","slug":"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-training-of-audio-transformers-with","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-training-of-audio-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2110.05069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05069"}},"official":{"repos":["kkoutini/passt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-hierarchical-deep-learning-approach-for","slug":"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/masked-latent-prediction-and-classification","slug":"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/mirflex-music-information-retrieval-feature","slug":"mirflex-music-information-retrieval-feature","title":"MIRFLEX: Music Information Retrieval Feature Library for Extraction","date":"2024-11-01","arxiv_id":"2411.00469","repositories_listed":1,"syntology":null},{"url":"/paper/i-can-listen-but-cannot-read-an-evaluation-of","slug":"i-can-listen-but-cannot-read-an-evaluation-of","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","date":"2024-07-25","arxiv_id":"2407.18058","repositories_listed":1,"syntology":null},{"url":"/paper/a-stem-agnostic-single-decoder-system-for","slug":"a-stem-agnostic-single-decoder-system-for","title":"A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems","date":"2024-06-26","arxiv_id":"2406.18747","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-stem-agnostic-single-decoder-system-for#ran","syntology_url":"https://syntology.ai/paper/2406.18747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18747"}},"official":{"repos":["kwatcharasupat/query-bandit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-convolutional-neural-networks-as","slug":"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/transfer-learning-and-bias-correction-with","slug":"transfer-learning-and-bias-correction-with","title":"Transfer Learning and Bias Correction with Pre-trained Audio Embeddings","date":"2023-07-20","arxiv_id":"2307.10834","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/surgical-phase-and-instrument-recognition-how","slug":"surgical-phase-and-instrument-recognition-how","title":"Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits","date":"2023-06-29","arxiv_id":"2306.16879","repositories_listed":1,"syntology":null},{"url":"/paper/efficientleaf-a-faster-learnable-audio","slug":"efficientleaf-a-faster-learnable-audio","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","date":"2022-07-12","arxiv_id":"2207.05508","repositories_listed":1,"syntology":null},{"url":"/paper/chmusic-a-traditional-chinese-music-dataset","slug":"chmusic-a-traditional-chinese-music-dataset","title":"ChMusic: A Traditional Chinese Music Dataset for Evaluation of Instrument Recognition","date":"2021-08-19","arxiv_id":"2108.08470","repositories_listed":1,"syntology":null},{"url":"/paper/use-of-speaker-recognition-approaches-for","slug":"use-of-speaker-recognition-approaches-for","title":"Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument sounds","date":"2021-07-24","arxiv_id":"2107.11506","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-hierarchical-structures-for-few","slug":"leveraging-hierarchical-structures-for-few","title":"Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition","date":"2021-07-14","arxiv_id":"2107.07029","repositories_listed":1,"syntology":null},{"url":"/paper/receptive-field-regularization-techniques-for","slug":"receptive-field-regularization-techniques-for","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","date":"2021-05-26","arxiv_id":"2105.12395","repositories_listed":1,"syntology":null},{"url":"/paper/kvasir-instrument-diagnostic-and-therapeutic","slug":"kvasir-instrument-diagnostic-and-therapeutic","title":"Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy","date":"2020-10-23","arxiv_id":"2011.08065","repositories_listed":1,"syntology":null},{"url":"/paper/predominant-musical-instrument-classification","slug":"predominant-musical-instrument-classification","title":"Predominant Musical Instrument Classification based on Spectral Features","date":"2019-11-30","arxiv_id":"1912.02606","repositories_listed":1,"syntology":null},{"url":"/paper/augmentation-methods-on-monophonic-audio-for","slug":"augmentation-methods-on-monophonic-audio-for","title":"Augmentation Methods on Monophonic Audio for Instrument Classification in Polyphonic Music","date":"2019-11-28","arxiv_id":"1911.12505","repositories_listed":1,"syntology":null},{"url":"/paper/an-attention-mechanism-for-musical-instrument","slug":"an-attention-mechanism-for-musical-instrument","title":"An Attention Mechanism for Musical Instrument Recognition","date":"2019-07-09","arxiv_id":"1907.04294","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-convolutional-lstm-approach","slug":"weakly-supervised-convolutional-lstm-approach","title":"Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos","date":"2018-12-04","arxiv_id":"1812.01366","repositories_listed":1,"syntology":null},{"url":"/paper/deep-convolutional-neural-networks-for-6","slug":"deep-convolutional-neural-networks-for-6","title":"Deep convolutional neural networks for predominant instrument recognition in polyphonic music","date":"2016-05-31","arxiv_id":"1605.09507","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-instrument-recognition-in","slug":"automatic-instrument-recognition-in","title":"Automatic Instrument Recognition in Polyphonic Music Using Convolutional Neural Networks","date":"2015-11-17","arxiv_id":"1511.05520","repositories_listed":1,"syntology":null},{"url":null,"slug":"can-deepseek-v3-reason-like-a-surgeon-an","title":"Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery","date":"2025-03-29","arxiv_id":"2503.23130","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgraw-multi-agent-workflow-with-chain-of","title":"SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence","date":"2025-03-13","arxiv_id":"2503.10265","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-surgical-instrument","title":"Deep Learning for Surgical Instrument Recognition and Segmentation in Robotic-Assisted Surgeries: A Systematic Review","date":"2024-10-09","arxiv_id":"2410.07269","repositories_listed":0,"syntology":null},{"url":null,"slug":"pitvis-2023-challenge-workflow-recognition-in","title":"PitVis-2023 Challenge: Workflow Recognition in videos of Endoscopic Pituitary Surgery","date":"2024-09-02","arxiv_id":"2409.01184","repositories_listed":0,"syntology":null},{"url":null,"slug":"weaksurg-weakly-supervised-surgical","title":"WeakSurg: Weakly supervised surgical instrument segmentation using temporal equivariance and semantic continuity","date":"2024-03-14","arxiv_id":"2403.09551","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-refining-of-pseudo-labels-for-music","title":"Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data","date":"2023-07-24","arxiv_id":"2307.12576","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointist-simultaneous-improvement-of-multi","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","date":"2023-02-01","arxiv_id":"2302.00286","repositories_listed":0,"syntology":null},{"url":"/paper/jointist-joint-learning-for-multi-instrument","slug":"jointist-joint-learning-for-multi-instrument","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","date":"2022-06-22","arxiv_id":"2206.10805","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":"visual-attention-for-musical-instrument","title":"Visual Attention for Musical Instrument Recognition","date":"2020-06-17","arxiv_id":"2006.09640","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-variational-inference-for","title":"Cross-modal variational inference for bijective signal-symbol translation","date":"2020-02-10","arxiv_id":"2002.03862","repositories_listed":0,"syntology":null},{"url":null,"slug":"musical-instrument-recognition-using-their","title":"Musical Instrument Recognition Using Their Distinctive Characteristics in Artificial Neural Networks","date":"2017-05-14","arxiv_id":"1705.04971","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-scattering-transform-applied-to-note","title":"Deep scattering transform applied to note onset detection and instrument recognition","date":"2017-03-28","arxiv_id":"1703.09775","repositories_listed":0,"syntology":null}],"syntology_records":2,"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":2,"papers_where_code_ran_first_page":"/task/instrument-recognition/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/instrument-recognition/papers/ran/1","json":"/task/instrument-recognition/papers/ran/1.json","rows":2}],"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":"0c2c66ec31867ac0a603982321a12490fbeb1c8dcb9f2ff3f9fbcd5490438c39","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}