@inproceedings{shi-etal-2026-affectcodec,
    title = "{A}ffect{C}odec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling",
    author = "Shi, Jiacheng  and
      Du, Hongfei  and
      Song, Xinyuan  and
      Hong, Y. Alicia  and
      Zhang, Yanfu  and
      Gao, Ashley",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.442/",
    pages = "9102--9124",
    ISBN = "979-8-89176-395-1",
    abstract = "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."
}