Salvato in:
Dettagli Bibliografici
Autori principali: Ahmed, Tawsif, Radonjic, Andrej, Rabby, Gollam
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.14293
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912448755269632
author Ahmed, Tawsif
Radonjic, Andrej
Rabby, Gollam
author_facet Ahmed, Tawsif
Radonjic, Andrej
Rabby, Gollam
contents We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative music modeling tasks such as text-music, music-captioning, singing-voice synthesis, melody reconstruction and cross-model retrieval. Past contributions focused on isolated and constrained factors whose core perspective was to create synthetic or re-recorded music corpus (e.g. GTSinger, M4Singer) and arbitrarily large-scale audio datasets (e.g. DISCO-10M and LAIONDISCO-12M) had been another focus for the community. Unfortunately, adoption of these datasets has been below substantial in the generative music community as these datasets fail to reflect real-world music and its flavour. Our dataset changes this narrative and provides a dataset that is constructed using actual popular music and world-renowned artists.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14293
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling
Ahmed, Tawsif
Radonjic, Andrej
Rabby, Gollam
Sound
Machine Learning
Audio and Speech Processing
We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative music modeling tasks such as text-music, music-captioning, singing-voice synthesis, melody reconstruction and cross-model retrieval. Past contributions focused on isolated and constrained factors whose core perspective was to create synthetic or re-recorded music corpus (e.g. GTSinger, M4Singer) and arbitrarily large-scale audio datasets (e.g. DISCO-10M and LAIONDISCO-12M) had been another focus for the community. Unfortunately, adoption of these datasets has been below substantial in the generative music community as these datasets fail to reflect real-world music and its flavour. Our dataset changes this narrative and provides a dataset that is constructed using actual popular music and world-renowned artists.
title SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2506.14293