Bookmark Saya

Semantic Scholar Open Access 2023 643 sitasi

MusicLM: Generating Music From Text

A. Agostinelli Timo I. Denk Zalán Borsos Jesse Engel Mauro Verzetti +8 lainnya
Lihat Sumber DOI

Abstrak

We introduce MusicLM, a model generating high-fidelity music from text descriptions such as"a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.

Topik & Kata Kunci

Computer Science Engineering

Penulis (13)

A

A. Agostinelli

T

Timo I. Denk

Z

Zalán Borsos

J

Jesse Engel

M

Mauro Verzetti

A

Antoine Caillon

Q

Qingqing Huang

A

A. Jansen

A

Adam Roberts

M

M. Tagliasacchi

M

Matthew Sharifi

N

Neil Zeghidour

C

C. Frank

Format Sitasi

APA MLA BibTeX
Agostinelli, A., Denk, T.I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A. et al. (2023). MusicLM: Generating Music From Text. https://doi.org/10.48550/arXiv.2301.11325

Akses Cepat

Lihat di Sumber doi.org/10.48550/arXiv.2301.11325
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Total Sitasi
643×
Sumber Database
Semantic Scholar
DOI
10.48550/arXiv.2301.11325
Akses
Open Access ✓