AffectCodec applies block-diagonal projections in residual FSQ to explicitly allocate bits to emotion and acoustic subspaces, combined with emotion conditioning, yielding better emotion preservation at low bitrates with competitive acoustic quality.
Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A
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
-
AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ
AffectCodec applies block-diagonal projections in residual FSQ to explicitly allocate bits to emotion and acoustic subspaces, combined with emotion conditioning, yielding better emotion preservation at low bitrates with competitive acoustic quality.