AI 中文总结
研究如何实现语音同步的三维声道运动，采用联合嵌入预测架构和强化学习/交叉熵方法，结合时长保持声学载体与校正的声道模型，在包含24个最小对刺激的评估中取得良好的自动语音识别等结果。
AI 中文摘要
现代神经语音系统能生成可理解的波形，但隐藏了产生声音的物理语音生成状态。生物力学声道模型虽能展现发音结构等，但直接物理波形合成不如现代神经声码器稳健。本文采用时长保持声学载体提供听觉波形，校正后的三维声道模型提供同步的颌、唇、舌等运动。通过联合嵌入预测架构（JEPA）风格表示和强化学习/交叉熵方法（RL/CEM）轨迹选择循环，使发音动作与声学载体及物理合理性约束对齐。评估包含12个3D录音，涵盖24个最小对刺激。在24词集上，载体取得了良好的自动语音识别（ASR）结果等多项指标。
英文摘要
Modern neural speech systems can generate intelligible waveforms, but they usually hide the physical speech-production state that produced the sound. Conversely, biomechanical vocal-tract models expose articulatory structure, contact behavior, airflow routing, and geometric constraints, but direct physical waveform synthesis remains less robust than modern neural vocoders. A duration-preserving acoustic carrier supplies the listening waveform, while a corrected three-dimensional vocal-tract model supplies synchronized jaw, lip, tongue, velum, laryngeal, oral-airflow, and nasal-airflow motion. A joint-embedding predictive architecture (JEPA)-style representation and a reinforcement learning/cross-entropy method (RL/CEM) trajectory-selection loop align articulatory actions to the acoustic carrier and to physical-plausibility constraints. The evaluation contains 12 3D recordings covering 24 minimal-pair stimuli. On the 24-word set, the carrier obtains good automatic speech recognition (ASR) results (an 8.33\% WER, a 4.17\% CER), a UTMOS score of 3.174, a mean JEPA score of 0.864, and a mean timbre-guard score of 0.947.
Commentspaper submitted to IEEE-SLT2026
