[D66] MusicLM: Generating Music From Text

[René Oudeweg]

[The death of the professional musician /RO]

MusicLM: Generating Music From Text

https://google-research.github.io/seanet/musiclm/examples/
https://aitestkitchen.withgoogle.com/signup

MusicLM: Generating Music From Text


Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro 
Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, 
Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Christian Frank

Google Research

Abstract 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.