Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
本文分析了ECAPA-TDNN嵌入的超球面几何特性，并通过两种几何正则化策略提高其均匀性和维度，从而改善零样本语音转换的鲁棒性。
0 citationsRead paper
Selected work
Representative Papers
Controlled oscillation modeling using port-Hamiltonian neural networks
This work addresses the limitations of data-driven methods in capturing conservation laws of dynamical systems, which hinder generalization and long-term prediction accuracy. Existing port-Hamiltonian neural networks (PHNNs) often compromise energy-preserving properties due to non-structure-preserving discretization schemes. To overcome this, we propose the first integration of a power-preserving second-order discrete gradient method into PHNNs, rigorously maintaining the port-Hamiltonian structure. Our approach further incorporates Jacobian regularization and explicit modeling of nonlinear dissipation. Experiments on the harmonic oscillator, Duffing oscillator, and self-sustained oscillator demonstrate that the proposed method significantly outperforms equivalent-order Runge–Kutta discretizations, achieving notable improvements in both energy conservation and trajectory prediction accuracy. We also provide a systematic evaluation of the impact of two equivalent port-Hamiltonian formulations.
0 citationsRead paper
Recent publications
Latest Papers
Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
本文分析了ECAPA-TDNN嵌入的超球面几何特性，并通过两种几何正则化策略提高其均匀性和维度，从而改善零样本语音转换的鲁棒性。
0 citationsRead paper
Controlled oscillation modeling using port-Hamiltonian neural networks
This work addresses the limitations of data-driven methods in capturing conservation laws of dynamical systems, which hinder generalization and long-term prediction accuracy. Existing port-Hamiltonian neural networks (PHNNs) often compromise energy-preserving properties due to non-structure-preserving discretization schemes. To overcome this, we propose the first integration of a power-preserving second-order discrete gradient method into PHNNs, rigorously maintaining the port-Hamiltonian structure. Our approach further incorporates Jacobian regularization and explicit modeling of nonlinear dissipation. Experiments on the harmonic oscillator, Duffing oscillator, and self-sustained oscillator demonstrate that the proposed method significantly outperforms equivalent-order Runge–Kutta discretizations, achieving notable improvements in both energy conservation and trajectory prediction accuracy. We also provide a systematic evaluation of the impact of two equivalent port-Hamiltonian formulations.
0 citationsRead paper