SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915153545527296 |
|---|---|
| author | Garcia-Martinez, Jaime Diaz-Guerra, David Politis, Archontis Virtanen, Tuomas Carabias-Orti, Julio J. Vera-Candeas, Pedro |
| author_facet | Garcia-Martinez, Jaime Diaz-Guerra, David Politis, Archontis Virtanen, Tuomas Carabias-Orti, Julio J. Vera-Candeas, Pedro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10995 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation Garcia-Martinez, Jaime Diaz-Guerra, David Politis, Archontis Virtanen, Tuomas Carabias-Orti, Julio J. Vera-Candeas, Pedro Audio and Speech Processing Machine Learning Sound 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. |
| title | SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2409.10995 |