SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
Abstract
Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources from orchestra recordings has not been extensively explored, largely due to a scarcity of comprehensive and clean (i.e bleed-free) multitrack datasets. In this paper, we introduce a novel multitrack dataset called SynthSOD, developed using a set of simulation techniques to create a realistic (i.e. using high-quality soundfonts), musically motivated, and heterogeneous training set comprising different dynamics, natural tempo changes, styles, and conditions. Moreover, we demonstrate the application of a widely used baseline music separation model trained on our synthesized dataset w.r.t to the well-known EnsembleSet, and evaluate its performance under both synthetic and real-world conditions.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2024
- DOI:
- 10.48550/arXiv.2409.10995
- arXiv:
- arXiv:2409.10995
- Bibcode:
- 2024arXiv240910995G
- Keywords:
-
- Electrical Engineering and Systems Science - Audio and Speech Processing;
- Computer Science - Machine Learning;
- Computer Science - Sound
- E-Print:
- Submitted to the OJSP - ICASSP 2025