AffectCodec：用于表达性语音建模的情感保持神经语音编解码器
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
AI总结：
本文提出AffectCodec，通过情感引导的神经语音编解码器在保持语义忠实和语调自然的同时，保留情感信息，提升语音重建、情感识别和文本到语音生成的性能。
摘要：
神经语音编解码器为语音语言模型提供离散表示，但情感线索在量化过程中常被降质。现有编解码器主要优化声学重建，导致在表示层面未能充分建模情感表达性。我们提出一种情感引导的神经语音编解码器，能够在保持语义忠实和语调自然的同时显式保留情感信息。我们的框架结合情感-语义引导的潜在调制、关系保留的情感-语义蒸馏以及情感加权的语义对齐，以在压缩过程中保留情感显著线索。在语音重建、情感识别和下游文本到语音生成的广泛评估中，证明了在不牺牲内容准确性的情况下，提升了情感一致性和感知质量。
英文摘要：
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acoustic reconstruction, leaving emotion expressiveness insufficiently modeled at the representation level. We propose an emotion-guided neural speech codec that explicitly preserves emotional information while maintaining semantic fidelity and prosodic naturalness. Our framework combines emotion-semantic guided latent modulation, relation-preserving emotional-semantic distillation, and emotion-weighted semantic alignment to retain emotionally salient cues under compression. Extensive evaluations across speech reconstruction, emotion recognition, and downstream text-to-speech generation demonstrate improved emotion consistency and perceptual quality without sacrificing content accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
