The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fabbro, Giorgio, Uhlich, Stefan, Lai, Chieh-Hsin, Choi, Woosung, Martínez-Ramírez, Marco, Liao, Weihsiang, Gadelha, Igor, Ramos, Geraldo, Hsu, Eddie, Rodrigues, Hugo, Stöter, Fabian-Robert, Défossez, Alexandre, Luo, Yi, Yu, Jianwei, Chakraborty, Dipam, Mohanty, Sharada, Solovyev, Roman, Stempkovskiy, Alexander, Habruseva, Tatiana, Goswami, Nabarun, Harada, Tatsuya, Kim, Minseok, Lee, Jun Hyung, Dong, Yuanliang, Zhang, Xinran, Liu, Jiafeng, Mitsufuji, Yuki
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917644284723200
author Fabbro, Giorgio
Uhlich, Stefan
Lai, Chieh-Hsin
Choi, Woosung
Martínez-Ramírez, Marco
Liao, Weihsiang
Gadelha, Igor
Ramos, Geraldo
Hsu, Eddie
Rodrigues, Hugo
Stöter, Fabian-Robert
Défossez, Alexandre
Luo, Yi
Yu, Jianwei
Chakraborty, Dipam
Mohanty, Sharada
Solovyev, Roman
Stempkovskiy, Alexander
Habruseva, Tatiana
Goswami, Nabarun
Harada, Tatsuya
Kim, Minseok
Lee, Jun Hyung
Dong, Yuanliang
Zhang, Xinran
Liu, Jiafeng
Mitsufuji, Yuki
author_facet Fabbro, Giorgio
Uhlich, Stefan
Lai, Chieh-Hsin
Choi, Woosung
Martínez-Ramírez, Marco
Liao, Weihsiang
Gadelha, Igor
Ramos, Geraldo
Hsu, Eddie
Rodrigues, Hugo
Stöter, Fabian-Robert
Défossez, Alexandre
Luo, Yi
Yu, Jianwei
Chakraborty, Dipam
Mohanty, Sharada
Solovyev, Roman
Stempkovskiy, Alexander
Habruseva, Tatiana
Goswami, Nabarun
Harada, Tatsuya
Kim, Minseok
Lee, Jun Hyung
Dong, Yuanliang
Zhang, Xinran
Liu, Jiafeng
Mitsufuji, Yuki
contents This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music source separation (MSS), i.e., training MSS models in the presence of errors in the training data. We propose a formalization of the errors that can occur in the design of a training dataset for MSS systems and introduce two new datasets that simulate such errors: SDXDB23_LabelNoise and SDXDB23_Bleeding. We describe the methods that achieved the highest scores in the competition. Moreover, we present a direct comparison with the previous edition of the challenge (the Music Demixing Challenge 2021): the best performing system achieved an improvement of over 1.6dB in signal-to-distortion ratio over the winner of the previous competition, when evaluated on MDXDB21. Besides relying on the signal-to-distortion ratio as objective metric, we also performed a listening test with renowned producers and musicians to study the perceptual quality of the systems and report here the results. Finally, we provide our insights into the organization of the competition and our prospects for future editions.
format Preprint
id arxiv_https___arxiv_org_abs_2308_06979
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
Fabbro, Giorgio
Uhlich, Stefan
Lai, Chieh-Hsin
Choi, Woosung
Martínez-Ramírez, Marco
Liao, Weihsiang
Gadelha, Igor
Ramos, Geraldo
Hsu, Eddie
Rodrigues, Hugo
Stöter, Fabian-Robert
Défossez, Alexandre
Luo, Yi
Yu, Jianwei
Chakraborty, Dipam
Mohanty, Sharada
Solovyev, Roman
Stempkovskiy, Alexander
Habruseva, Tatiana
Goswami, Nabarun
Harada, Tatsuya
Kim, Minseok
Lee, Jun Hyung
Dong, Yuanliang
Zhang, Xinran
Liu, Jiafeng
Mitsufuji, Yuki
Audio and Speech Processing
Sound
This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music source separation (MSS), i.e., training MSS models in the presence of errors in the training data. We propose a formalization of the errors that can occur in the design of a training dataset for MSS systems and introduce two new datasets that simulate such errors: SDXDB23_LabelNoise and SDXDB23_Bleeding. We describe the methods that achieved the highest scores in the competition. Moreover, we present a direct comparison with the previous edition of the challenge (the Music Demixing Challenge 2021): the best performing system achieved an improvement of over 1.6dB in signal-to-distortion ratio over the winner of the previous competition, when evaluated on MDXDB21. Besides relying on the signal-to-distortion ratio as objective metric, we also performed a listening test with renowned producers and musicians to study the perceptual quality of the systems and report here the results. Finally, we provide our insights into the organization of the competition and our prospects for future editions.
title The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2308.06979