基于分层解耦的无文本零样本语音情感迁移August 1, 2025·甄怡宁,王春玲,杨昊田,王少荣· 0 min readTypeConference paperPublication中国多媒体大会(ChinaMM 2025)StatusPeer-reviewedpublicationsLast updated on August 1, 2025Generative Models Speech Emotion ← TimeGazer: Temporal Modeling of Predictive Gaze Stabilization for AR Interaction October 1, 2025HiDe-Mamba:基于状态空间模型的点云层次去噪网络 July 1, 2025 →