{"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/transformer-based-approaches-for-automatic","title":"Transformer-Based Approaches for Automatic Music Transcription","arxiv_id":null,"date":"2021-02-12","proceeding":"Conference 2021 2","authors":["Christos Zonios"],"abstract":"Automatic Music Transcription (AMT) is the process of extracting information\r\nfrom audio into some form of music notation. In polyphonic music, this is a very\r\nhard problem for computers to solve as it requires significant prior knowledge and\r\nunderstanding of music language and the audio is subject to a multitude of variations\r\nin frequencies depending on many factors such as instrument materials, tuning, player\r\nperformance, recording equipment and others.\r\nTransformers are self-supervised models that have recently showed great promise\r\nas they use self-attention in order to learn contextual representations from unlabeled\r\ndata. They have surpassed state of the art (SOTA) performance in various Speech\r\nRecognition (SR), Natural Language Processing (NLP) and Computer Vision tasks.\r\nIn this work, we examine transformer-based approaches for performing AMT on\r\npiano recordings by learning audio and music language representations. Specifically,\r\nwe look at the popular SR model wav2vec2 as a solution to the former and the NLP\r\nmodel BERT in order to perform Music Language Modelling (MusicLM).\r\nWe propose a new pre-training approach for MusicLM transformers based on\r\nan appropriately defined transcription error correction task. In addition, three novel\r\nmodels for AMT are proposed and studied that appropriately integrate wav2vec2 and\r\nBERT transformers at various stages.\r\nWe conclude that a wav2vec2 encoder model pre-trained on speech audio is not\r\nable to surpass SOTA models using mel-scale spectrograms and convolutional network\r\nencoders without significant conditioning on music audio.\r\nviii\r\nWe show that a BERT transformer pre-trained on natural language has transfer\r\nlearning potential for MusicLM. We also examine the robustness of such a transformer\r\nfor performing MusicLM, and find that we are able to achieve interesting results when\r\ndoing Masked MusicLM and when replacing Recurrent Neural Networks with pretrained transformers in SOTA models for AMT.","url_abs":"https://www.cs.uoi.gr/wp-content/uploads/publications/MT-2021-18.pdf","url_pdf":"https://www.cs.uoi.gr/wp-content/uploads/publications/MT-2021-18.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":"transformer-based-approaches-for-automatic","repo_url":"https://github.com/MS-P3/code7/tree/main/wav2vec2_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"music-transcription","task_name":"Music Transcription"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"MS-P3/code7","kind":"listed","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":"94b834175e23786f57fc55c781ddcfb4f556381807a7095e735ffc7fb7d2ba0f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}