Statements (33)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
AI music generation model
|
| gptkbp:abilities |
generating high-fidelity music
generating music from text descriptions generating music in different genres generating music of varying lengths generating music with different instruments generating music with different moods generating music with different styles generating music with different tempos generating music with vocals |
| gptkbp:announced |
2023
|
| gptkbp:author |
Agostinelli, Enrico; Cornia, Marcello; et al.
|
| gptkbp:developedBy |
gptkb:Google_Research
|
| gptkbp:hasDemo |
yes
|
| https://www.w3.org/2000/01/rdf-schema#label |
MusicLM
|
| gptkbp:input |
text prompt
|
| gptkbp:notableFor |
high audio quality
text-to-music generation long-term coherence in generated music |
| gptkbp:notablePublication |
gptkb:MusicLM:_Generating_Music_From_Text
|
| gptkbp:openSource |
no
|
| gptkbp:output |
music audio
|
| gptkbp:paperAvailableAt |
gptkb:arXiv:2301.11325
|
| gptkbp:publishedIn |
2023
|
| gptkbp:relatedTo |
gptkb:Google_AI
gptkb:AudioLM text-to-image models music generation research |
| gptkbp:trainer |
large music dataset
|
| gptkbp:uses |
Transformer architecture
|
| gptkbp:website |
https://google-research.github.io/seanet/musiclm/
|
| gptkbp:bfsParent |
gptkb:Google_AI
|
| gptkbp:bfsLayer |
5
|