Year: 2024
Type: article
Abstract: In the past, the field of drum source separation faced significant challenges due to limited data availability, hindering the adoption of cutting-edge deep learning methods that have found success in other related audio applications. In this letter, we introduce StemGMD, a large- scale audio dataset of isolated single-instrument drum stems. Each audio clip is synthesized from MIDI recordings of expressive drum performances using ten real-sounding acoustic drum kits. Totaling 1224 h, StemGMD is the largest audio dataset of drums to date and the first to comprise isolated audio clips for every instrument in a canonical nine-piece drum kit. We leverage StemGMD to develop LarsNet, a novel deep drum source separation model. Through a bank of dedicated U-Nets, LarsNet can separate five stems from a stereo drum mixture faster than real-time and is shown to considerably outperform state-of-the-art nonnegative spectro-temporal factorization methods.
Source: Pattern Recognition Letters
Institution: Politecnico di Milano
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,610
Funder: European Commission
Award: G7205771190
OpenAlex ID: W4396634099