Saved in:
Bibliographic Details
Main Authors: Shi, Jiacheng, Du, Hongfei, Song, Xinyuan, Hong, Y. Alicia, Zhang, Yanfu, Gao, Ye
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11098
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914555393736704
author Shi, Jiacheng
Du, Hongfei
Song, Xinyuan
Hong, Y. Alicia
Zhang, Yanfu
Gao, Ye
author_facet Shi, Jiacheng
Du, Hongfei
Song, Xinyuan
Hong, Y. Alicia
Zhang, Yanfu
Gao, Ye
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11098
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Shi, Jiacheng
Du, Hongfei
Song, Xinyuan
Hong, Y. Alicia
Zhang, Yanfu
Gao, Ye
Sound
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.
title AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
topic Sound
url https://arxiv.org/abs/2605.11098