{"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":"/paper/yourmt3-multi-instrument-music-transcription","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","arxiv_id":"2407.04822","date":"2024-07-05","proceeding":null,"authors":["Sungkyun Chang","Emmanouil Benetos","Holger Kirchhoff","Simon Dixon"],"abstract":"Multi-instrument music transcription aims to convert polyphonic music recordings into musical scores assigned to each instrument. This task is challenging for modeling as it requires simultaneously identifying multiple instruments and transcribing their pitch and precise timing, and the lack of fully annotated data adds to the training difficulties. This paper introduces YourMT3+, a suite of models for enhanced multi-instrument music transcription based on the recent language token decoding approach of MT3. We enhance its encoder by adopting a hierarchical attention transformer in the time-frequency domain and integrating a mixture of experts. To address data limitations, we introduce a new multi-channel decoding method for training with incomplete annotations and propose intra- and cross-stem augmentation for dataset mixing. Our experiments demonstrate direct vocal transcription capabilities, eliminating the need for voice separation pre-processors. Benchmarks across ten public datasets show our models' competitiveness with, or superiority to, existing transcription models. Further testing on pop music recordings highlights the limitations of current models. Fully reproducible code and datasets are available with demos at \\url{https://github.com/mimbres/YourMT3}.","url_abs":"https://arxiv.org/abs/2407.04822v3","url_pdf":"https://arxiv.org/pdf/2407.04822v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"yourmt3-multi-instrument-music-transcription","repo_url":"https://github.com/mimbres/yourmt3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"drum-transcription","task_name":"Drum Transcription"},{"task_slug":"drum-transcription-in-music-dtm","task_name":"Drum Transcription in Music (DTM)"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"multi-instrument-music-transcription","task_name":"Multi-instrument Music Transcription"},{"task_slug":"music-transcription","task_name":"Music Transcription"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"moe","method_name":"MoE"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"perceiver-io","method_name":"Perceiver IO"},{"method_slug":"rmsnorm","method_name":"RMSNorm"},{"method_slug":"rope","method_name":"Rotary Embeddings"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[{"slug":"yourmt3-dataset","name":"YourMT3 Dataset","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-instrument-music-transcription-on","task":"Multi-instrument Music Transcription","dataset":"Slakh2100","model":"YourMT3+ (YPTF.MoE+M)","rank_in_archive_order":1,"of":5,"metrics":{"Multi F1":"74.84"},"uses_additional_data":false},{"leaderboard":"/sota/multi-instrument-music-transcription-on","task":"Multi-instrument Music Transcription","dataset":"Slakh2100","model":"MT3","rank_in_archive_order":2,"of":5,"metrics":{"Multi F1":"62"},"uses_additional_data":false},{"leaderboard":"/sota/multi-instrument-music-transcription-on","task":"Multi-instrument Music Transcription","dataset":"Slakh2100","model":"MT3 (colab)","rank_in_archive_order":4,"of":5,"metrics":{"Multi F1":"57.69"},"uses_additional_data":false},{"leaderboard":"/sota/multi-instrument-music-transcription-on-urmp","task":"Multi-instrument Music Transcription","dataset":"URMP","model":"YourMT3+ (YPTF.MoE+M)","rank_in_archive_order":1,"of":3,"metrics":{"Multi F1":"67.98"},"uses_additional_data":true},{"leaderboard":"/sota/multi-instrument-music-transcription-on-urmp","task":"Multi-instrument Music Transcription","dataset":"URMP","model":"MT3","rank_in_archive_order":3,"of":3,"metrics":{"Multi F1":"59"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-maestro","task":"Music Transcription","dataset":"MAESTRO","model":"YourMT3+ (YPTF.MoE+M) noPS","rank_in_archive_order":4,"of":9,"metrics":{"Onset F1":"96.98"},"uses_additional_data":true},{"leaderboard":"/sota/music-transcription-on-maestro","task":"Music Transcription","dataset":"MAESTRO","model":"YourMT3+ (YPTF.MoE+M)","rank_in_archive_order":6,"of":9,"metrics":{"Onset F1":"96.52"},"uses_additional_data":true},{"leaderboard":"/sota/music-transcription-on-maps","task":"Music Transcription","dataset":"MAPS","model":"YourMT3+ (YPTF.MoE+M, unseen) noPS","rank_in_archive_order":2,"of":6,"metrics":{"Onset F1":"88.73"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-maps","task":"Music Transcription","dataset":"MAPS","model":"YourMT3+ (YPTF+S, unseen)","rank_in_archive_order":4,"of":6,"metrics":{"Onset F1":"88.37"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-slakh2100","task":"Music Transcription","dataset":"Slakh2100","model":"YourMT3+ (YPTF.MoE+M)","rank_in_archive_order":1,"of":6,"metrics":{"Onset F1":"84.56","note-level F-measure-no-offset (Fno)":"0.8456"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-slakh2100","task":"Music Transcription","dataset":"Slakh2100","model":"PerceiverTF","rank_in_archive_order":2,"of":6,"metrics":{"Onset F1":"81.9","note-level F-measure-no-offset (Fno)":"0.819"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-slakh2100","task":"Music Transcription","dataset":"Slakh2100","model":"MT3 (colab)","rank_in_archive_order":3,"of":6,"metrics":{"Onset F1":"75.2","note-level F-measure-no-offset (Fno)":"0.752"},"uses_additional_data":false},{"leaderboard":"/sota/music-transcription-on-urmp","task":"Music Transcription","dataset":"URMP","model":"YourMT3+ (YPTF.MoE+M)","rank_in_archive_order":1,"of":3,"metrics":{"Onset F1":"81.79"},"uses_additional_data":true},{"leaderboard":"/sota/music-transcription-on-urmp","task":"Music Transcription","dataset":"URMP","model":"MT3","rank_in_archive_order":3,"of":3,"metrics":{"Onset F1":"77"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"mimbres/yourmt3","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"283aa9ede598a4d6bf30896e0a0cdbb98269457db5d80812aa453e153041b0e7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}