VAMPNET: MUSIC GENERATION VIA MASKED ACOUSTIC TOKEN MODELING

Hugo Flores García, Prem Seetharaman, Rithesh Kumar, Bryan Pardo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from the model by applying a variety of masking approaches (called prompts) during inference. VampNet is non-autoregressive, leveraging a bidirectional transformer architecture that attends to all tokens in a forward pass. With just 36 sampling passes, VampNet can generate coherent high-fidelity musical waveforms. We show that by prompting VampNet in various ways, we can apply it to tasks like music compression, inpainting, outpainting, continuation, and looping with variation (vamping). Appropriately prompted, VampNet is capable of maintaining style, genre, instrumentation, and other high-level aspects of the music. This flexible prompting capability makes VampNet a powerful music co-creation tool. Code 3 and audio samples 4 are available online.

Original languageEnglish (US)
Title of host publication24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Proceedings
EditorsAugusto Sarti, Fabio Antonacci, Mark Sandler, Paolo Bestagini, Simon Dixon, Beici Liang, Gael Richard, Johan Pauwels
PublisherInternational Society for Music Information Retrieval
Pages359-366
Number of pages8
ISBN (Electronic)9781732729933
StatePublished - 2023
Event24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Milan, Italy
Duration: Nov 5 2023Nov 9 2023

Publication series

Name24th International Society for Music Information Retrieval Conference, ISMIR 2023 - Proceedings

Conference

Conference24th International Society for Music Information Retrieval Conference, ISMIR 2023
Country/TerritoryItaly
CityMilan
Period11/5/2311/9/23

ASJC Scopus subject areas

  • Music
  • Information Systems

Fingerprint

Dive into the research topics of 'VAMPNET: MUSIC GENERATION VIA MASKED ACOUSTIC TOKEN MODELING'. Together they form a unique fingerprint.

Cite this