Generating 120 candidate super-resolved audios and choosing the best by task-specific verifiers improves speech, music, and sound effects over single-sample diffusion output, at 120x compute.
Musicldm: Enhancing novelty in text-to-music generation using beat-synchronous mixup strategies
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.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Inference-time Scaling for Diffusion-based Audio Super-resolution
Generating 120 candidate super-resolved audios and choosing the best by task-specific verifiers improves speech, music, and sound effects over single-sample diffusion output, at 120x compute.