The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911844343480320 |
|---|---|
| author | Uhlich, Stefan Fabbro, Giorgio Hirano, Masato Takahashi, Shusuke Wichern, Gordon Roux, Jonathan Le Chakraborty, Dipam Mohanty, Sharada Li, Kai Luo, Yi Yu, Jianwei Gu, Rongzhi Solovyev, Roman Stempkovskiy, Alexander Habruseva, Tatiana Sukhovei, Mikhail Mitsufuji, Yuki |
| author_facet | Uhlich, Stefan Fabbro, Giorgio Hirano, Masato Takahashi, Shusuke Wichern, Gordon Roux, Jonathan Le Chakraborty, Dipam Mohanty, Sharada Li, Kai Luo, Yi Yu, Jianwei Gu, Rongzhi Solovyev, Roman Stempkovskiy, Alexander Habruseva, Tatiana Sukhovei, Mikhail Mitsufuji, Yuki |
| contents | This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail CDXDB23, a new hidden dataset constructed from real movies that was used to rank the submissions. The paper also offers insights into the most successful approaches employed by participants. Compared to the cocktail-fork baseline, the best-performing system trained exclusively on the simulated Divide and Remaster (DnR) dataset achieved an improvement of 1.8 dB in SDR, whereas the top-performing system on the open leaderboard, where any data could be used for training, saw a significant improvement of 5.7 dB. A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_06981 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track Uhlich, Stefan Fabbro, Giorgio Hirano, Masato Takahashi, Shusuke Wichern, Gordon Roux, Jonathan Le Chakraborty, Dipam Mohanty, Sharada Li, Kai Luo, Yi Yu, Jianwei Gu, Rongzhi Solovyev, Roman Stempkovskiy, Alexander Habruseva, Tatiana Sukhovei, Mikhail Mitsufuji, Yuki Audio and Speech Processing Sound This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail CDXDB23, a new hidden dataset constructed from real movies that was used to rank the submissions. The paper also offers insights into the most successful approaches employed by participants. Compared to the cocktail-fork baseline, the best-performing system trained exclusively on the simulated Divide and Remaster (DnR) dataset achieved an improvement of 1.8 dB in SDR, whereas the top-performing system on the open leaderboard, where any data could be used for training, saw a significant improvement of 5.7 dB. A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail. |
| title | The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2308.06981 |