发表机构
University of Sheffield（谢菲尔德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用神经受控微分方程实现连续时间声学建模，使隐藏状态随音素内容和时长演化，提升情感强度排序一致性并保持表达质量。
AI 中文摘要
文本到语音（TTS）模型通常通过使用预测的时长将音素级编码器状态扩展为帧级解码器输入，来解决文本与语音之间的对齐问题。虽然这种长度调节步骤在结构上解决了对齐问题，但时长的使用通常仅改变潜在状态出现的位置和频率，而不改变状态本身的值。本文提出了一种基于神经受控微分方程（CDE）的连续时间机制，用于TTS中的时长感知声学建模。我们将音素表示构建为时间参数化的控制路径，并使用神经声学向量场生成连续时间的隐藏状态，其值随语音内容和时长推导的时间信息而演化。生成的轨迹可以在离散点采样，并集成到标准声学解码器流程中。客观结果对比了CDE与典型循环模型。主观结果表明，基于CDE的模型（每步评估一个音素）可以提高合成语音与参考情感强度之间的秩次一致性，同时保持与强基线相当的情感表达质量。额外的半音素步长实验表明，时间分辨率改变了风格跟踪与绝对校准之间的权衡。这些结果将CDE定位为连续时间和时长感知的风格敏感TTS的一个有前景的设计空间。
英文摘要
Text-to-speech (TTS) models commonly address text--speech alignment by expanding phone-level encoder states to frame-level decoder inputs using predicted durations. While this length-regulation step resolves alignment structurally, this use of duration typically changes only where and how often latent states appear, not the values of the states themselves. This paper proposes a continuous-time mechanism for duration-aware acoustic modelling in TTS using neural controlled differential equations (CDEs). We formulate the phone representation as a temporally parameterised control path and use a neural acoustic vector field to produce a continuous-time hidden state whose values evolve with phonetic content and duration-derived timing. The resulting trajectory can be sampled at discrete points and integrated into a standard acoustic decoder pipeline. Objective results contrast CDEs and typical recurrent models. Subjective results suggest that CDE-based models evaluating one phone per step can improve rank-order agreement between synthesised and reference emotion intensity while maintaining comparable emotion-expression quality to a strong baseline. Additional experiments with half-phone step-sizes suggest that temporal resolution changes the trade-off between style tracking and absolute calibration. These results position CDEs as a promising design space for continuous-time and duration-aware style-sensitive TTS.
CommentsAccepted to IEEE Spoken Language Technology Workshop (SLT) 2026
