Statements (54)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
|
| gptkbp:announced |
2022
|
| gptkbp:architecture |
transformer-based
|
| gptkbp:arXivID |
2210.15424
|
| gptkbp:author |
gptkb:Rob_Clark
gptkb:Andrew_Senior gptkb:Heiga_Zen gptkb:Oriol_Vinyals gptkb:Andrew_Rosenberg gptkb:Yannis_Assael Alexander Gutkin Cheng-Zhi Anna Huang Damien Vincent Felix de Chaumont Quitry Florian B. Metze François Charton Manuel Norambuena Marco Tagliasacchi Matt Sharifi Matthew Sharifi Neil Zeghidour Olivier Pietquin Pedro J. Moreno Raphael Valle Yu Zhang Zalán Borsos |
| gptkbp:citation |
1000+
|
| gptkbp:compatibleWith |
text transcripts
|
| gptkbp:developedBy |
gptkb:Google_Research
|
| gptkbp:generation |
audio in the style of the input
coherent speech music continuations |
| https://www.w3.org/2000/01/rdf-schema#label |
AudioLM
|
| gptkbp:input |
audio
|
| gptkbp:language |
English
|
| gptkbp:memiliki_tugas |
speech synthesis
music generation audio generation |
| gptkbp:notablePublication |
AudioLM: a Language Modeling Approach to Audio Generation
|
| gptkbp:output |
audio
|
| gptkbp:preserves |
gptkb:public_speaker
style content speaker identity |
| gptkbp:relatedTo |
gptkb:EnCodec
gptkb:MusicLM gptkb:Wav2Vec Jukebox SoundStream |
| gptkbp:uses |
language modeling techniques
tokenization of audio |
| gptkbp:website |
https://google-research.github.io/seanet/audiolm
|
| gptkbp:bfsParent |
gptkb:MusicLM
|
| gptkbp:bfsLayer |
6
|