MERIT trains disentangled heads for melody, rhythm, and timbre via conditional audio generation and stem separation, with evaluations showing each head responds strongly to its target dimension and near chance on others across synthetic and real audio.
Sonicverse: Multi-task learning for music feature-informed caption- ing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MERIT: Learning Disentangled Music Representations for Audio Similarity
MERIT trains disentangled heads for melody, rhythm, and timbre via conditional audio generation and stem separation, with evaluations showing each head responds strongly to its target dimension and near chance on others across synthetic and real audio.