Style embeddings computed from CLAP and a sound matching model align with human timbre similarity ratings better than plain embeddings, MFCC, and other pre-trained representations.
grass” versus “sand
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assessing the Alignment of Audio Representations with Timbre Similarity Ratings
Style embeddings computed from CLAP and a sound matching model align with human timbre similarity ratings better than plain embeddings, MFCC, and other pre-trained representations.