发表机构
George Mason University（乔治梅森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
首次将混沌物理引入ETS合成，提出LyRIC激活与GLARE注意力，以更少参数大幅提升可懂度与频谱重建质量。
AI 中文摘要
肌电到语音（ETS）合成通常是一个非线性、混沌的动力学系统。然而，迄今为止，尚无先前工作研究ETS合成的混沌行为。相反，先前的工作严格依赖标准重建指标，并使用参数繁重的Transformer，这些模型系统地过度平滑了自然声学动力学。为弥合这一差距，我们首次提出一种受混沌启发的Lyapunov导出激活函数（LyRIC），并配以两种新颖的混沌损失函数，即Lyapunov指数正则化和多尺度去趋势波动分析，以显式捕获人类发声的确定性混沌。此外，我们引入了一个压缩的新型编码器GLAME，它协同了全局Mamba状态空间建模与局部GLARE注意力。我们在使用英语和普通话数据集的多语言、多说话人设置中全面进行了帧级声学评估。所提出的系统在客观可懂度上比既定基线提高了4.69倍（STOI：0.61对比0.13），在频谱重建上改善了2.08倍（LSD：1.08对比2.25）。重要的是，这一改进是在参数减少73.49%的情况下实现的（14.34M对比54.10M），为ETS合成建立了新的基线。据我们所知，这是首个证明将非线性混沌物理集成到神经网络中能为实时ETS合成产生优越且紧凑的归纳偏置的工作。
英文摘要
Electromyography-to-Speech (ETS) synthesis is typically a non-linear, chaotic dynamical system. However, no prior work has studied the chaotic behavior of ETS synthesis to date. Yet, prior works strictly rely on standard reconstruction metrics with parameter-heavy transformers that systematically over-smooth natural acoustic dynamics. To close this gap, for the first time, we propose a chaos-inspired Lyapunov-derived activation function (LyRIC) with two novel chaotic loss functions, Lyapunov Exponent Regularization and Multi-Scale Detrended Fluctuation Analysis, to explicitly capture the deterministic chaos of human phonation. In addition, we introduce a compressed novel encoder, GLAME, which synergizes global Mamba state-space modeling with localized GLARE attention. We comprehensively perform frame-level acoustic evaluation in a multilingual and multi-speaker setup using English and Mandarin datasets. The proposed system outperforms the established baseline with a 4.69x increase in objective intelligibility (STOI: 0.61 vs. 0.13) and a 2.08x improvement in spectral reconstruction (LSD: 1.08 vs. 2.25). Importantly, this improvement is achieved with 73.49% fewer parameters (14.34M vs. 54.10M), establishing a new baseline for ETS synthesis. To the best of our knowledge, this is the first work demonstrating that integrating non-linear chaotic physics into neural networks yields superior yet compact inductive biases for real-time ETS synthesis.
Comments27 pages, 12 figures, and 20 tables
