Injected audio watermarks can be detected in music generated by a fine-tuned MusicGen model; simple tones work best, and a neural watermark requires dozens of repeated embeddings.
Simple and controllable music generation.Advances in Neural Information Processing Systems, 36, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Watermarking Training Data of Music Generation Models
Injected audio watermarks can be detected in music generated by a fine-tuned MusicGen model; simple tones work best, and a neural watermark requires dozens of repeated embeddings.