Skip to Main content Skip to Navigation
Conference papers

DrumGAN: Synthesis of drum sounds with timbral feature conditioning using Generative Adversarial Networks

Abstract : Synthetic creation of drum sounds (e.g., in drum machines)is commonly performed using analog or digital synthesis,allowing a musician to sculpt the desired timbre modify-ing various parameters. Typically, such parameters controllow-level features of the sound and often have no musicalmeaning or perceptual correspondence. With the rise ofDeep Learning, data-driven processing of audio emergesas an alternative to traditional signal processing. This newparadigm allows controlling the synthesis process throughlearned high-level features or by conditioning a modelon musically relevant information. In this paper, we ap-ply a Generative Adversarial Network to the task of au-dio synthesis of drum sounds. By conditioning the modelon perceptual features computed with a publicly availablefeature-extractor, intuitive control is gained over the gen-eration process. The experiments are carried out on a largecollection of kick, snare, and cymbal sounds. We showthat, compared to a specific prior work based on a U-Netarchitecture, our approach considerably improves the qual-ity of the generated drum samples, and that the conditionalinput indeed shapes the perceptual characteristics of thesounds. Also, we provide audio examples and release thecode for reproducibility.1
Document type :
Conference papers
Complete list of metadata
Contributor : Gaël RICHARD Connect in order to contact the contributor
Submitted on : Friday, June 4, 2021 - 6:42:32 PM
Last modification on : Wednesday, April 13, 2022 - 5:32:02 PM
Long-term archiving on: : Sunday, September 5, 2021 - 6:03:43 PM


Files produced by the author(s)

J'avais téléchargé le mauvais fichier (le poster au lieu du papier). J'ai maintenant placé le bon document. Merci de l'avoir noté.


  • HAL Id : hal-03233337, version 1



Javier Nistal Hurlé, Stefan Lattner, Gael Richard. DrumGAN: Synthesis of drum sounds with timbral feature conditioning using Generative Adversarial Networks. 21 st International Society for Music Information Retrieval Conference (ISMIR), Aug 2020, Toronto, Canada. ⟨hal-03233337⟩



Record views


Files downloads