English

AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ

Sound 2026-05-25 v1

Abstract

Neural speech codecs have become the discrete interface between raw audio and speech language models, yet they remain optimized primarily for acoustic reconstruction fidelity, which leaves emotion-relevant cues vulnerable to being discarded during quantization, limiting the affective capacity of downstream models. We trace this degradation to two mechanisms: reconstruction-driven bit allocation under limited bitrate and cross-stream leakage in concatenation-based codecs, where acoustic gradients can overwrite nominally emotion-reserved dimensions. We propose AffectCodec, an emotion-preserving neural speech codec built on Block-Diagonal Residual Finite Scalar Quantization (BD-RFSQ). By imposing block-diagonal input and output projections over emotion and acoustic subspaces, BD-RFSQ transforms bit allocation from implicit and loss-driven to explicit and structurally guaranteed, while still preserving a flat token interface for downstream speech language models. AffectCodec further combines this structurally constrained quantizer with multi-granularity emotion conditioning and multi-rate training, enabling robust affect preservation at low bitrates. Experiments across multiple emotional speech benchmarks show that AffectCodec substantially improves emotion preservation, especially in the low-bitrate regime, while maintaining competitive acoustic quality and intelligibility. These results suggest that structurally protected quantization is an effective principle for preserving emotion-relevant information and may provide a general route toward attribute-aware neural speech compression.

Cite

@article{arxiv.2605.23373,
  title  = {AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ},
  author = {Zhaoyang Meng and Zhengyao Ma and Kecan Mao and Yingming Gao and Ya Li},
  journal= {arXiv preprint arXiv:2605.23373},
  year   = {2026}
}