{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/towards-multi-instrument-drum-transcription","title":"Towards multi-instrument drum transcription","arxiv_id":"1806.06676","date":"2018-06-18","proceeding":null,"authors":["Richard Vogl","Gerhard Widmer","Peter Knees"],"abstract":"Automatic drum transcription, a subtask of the more general automatic music\ntranscription, deals with extracting drum instrument note onsets from an audio\nsource. Recently, progress in transcription performance has been made using\nnon-negative matrix factorization as well as deep learning methods. However,\nthese works primarily focus on transcribing three drum instruments only: snare\ndrum, bass drum, and hi-hat. Yet, for many applications, the ability to\ntranscribe more drum instruments which make up standard drum kits used in\nwestern popular music would be desirable. In this work, convolutional and\nconvolutional recurrent neural networks are trained to transcribe a wider range\nof drum instruments. First, the shortcomings of publicly available datasets in\nthis context are discussed. To overcome these limitations, a larger synthetic\ndataset is introduced. Then, methods to train models using the new dataset\nfocusing on generalization to real world data are investigated. Finally, the\ntrained models are evaluated on publicly available datasets and results are\ndiscussed. The contributions of this work comprise: (i.) a large-scale\nsynthetic dataset for drum transcription, (ii.) first steps towards an\nautomatic drum transcription system that supports a larger range of instruments\nby evaluating and discussing training setups and the impact of datasets in this\ncontext, and (iii.) a publicly available set of trained models for drum\ntranscription. Additional materials are available at\nhttp://ifs.tuwien.ac.at/~vogl/dafx2018","url_abs":"http://arxiv.org/abs/1806.06676v2","url_pdf":"http://arxiv.org/pdf/1806.06676v2.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":"towards-multi-instrument-drum-transcription","repo_url":"https://github.com/keunwoochoi/DrummerNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"drum-transcription","task_name":"Drum Transcription"},{"task_slug":"music-transcription","task_name":"Music Transcription"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}