FEW-SHOT DRUM TRANSCRIPTION IN POLYPHONIC MUSIC

Yu Wang, Justin Salamon, Mark Cartwright, Nicholas J. Bryan, Juan Pablo Bello

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations

Abstract

Data-driven approaches to automatic drum transcription (ADT) are often limited to a predefined, small vocabulary of percussion instrument classes. Such models cannot recognize out-of-vocabulary classes nor are they able to adapt to finer-grained vocabularies. In this work, we address open vocabulary ADT by introducing few-shot learning to the task. We train a Prototypical Network on a synthetic dataset and evaluate the model on multiple real-world ADT datasets with polyphonic accompaniment. We show that, given just a handful of selected examples at inference time, we can match and in some cases outperform a state-of-the-art supervised ADT approach under a fixed vocabulary setting. At the same time, we show that our model can successfully generalize to finer-grained or extended vocabularies unseen during training, a scenario where supervised approaches cannot operate at all. We provide a detailed analysis of our experimental results, including a breakdown of performance by sound class and by polyphony.

Original languageEnglish (US)
Title of host publicationProceedings of the 21st International Society for Music Information Retrieval Conference, ISMIR 2020
EditorsJulie Cumming, Jin Ha Lee, Brian McFee, Markus Schedl, Johanna Devaney, Johanna Devaney, Cory McKay, Eva Zangerle, Timothy de Reuse
PublisherInternational Society for Music Information Retrieval
Pages255-262
Number of pages8
ISBN (Electronic)9780981353708
StatePublished - 2020
Externally publishedYes
Event21st International Society for Music Information Retrieval Conference, ISMIR 2020 - Virtual, Online, Canada
Duration: Oct 11 2020Oct 16 2020

Publication series

NameProceedings of the 21st International Society for Music Information Retrieval Conference, ISMIR 2020

Conference

Conference21st International Society for Music Information Retrieval Conference, ISMIR 2020
Country/TerritoryCanada
CityVirtual, Online
Period10/11/2010/16/20

All Science Journal Classification (ASJC) codes

  • Music
  • Information Systems

Fingerprint

Dive into the research topics of 'FEW-SHOT DRUM TRANSCRIPTION IN POLYPHONIC MUSIC'. Together they form a unique fingerprint.

Cite this