发表机构
The Hong Kong Polytechnic University; Baidu Inc.; The University of Hong Kong（香港理工大学; 百度公司; 香港大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对残差连接的信息流限制问题，提出流形约束超连接（mHC）方法，替换多种主干网络的残差连接后，在VoxCeleb1数据集上持续提升了说话人表示学习的性能。
AI 中文摘要
残差连接是深度说话人识别模型（如ECAPA-TDNN和ResNet）的基础，但标准恒等映射将信息流限制为单一路径，约束了表示能力。我们提出流形约束超连接（mHC），将残差路径重新表述为多流演化，其中信息通过双重随机矩阵混合。通过使用Sinkhorn-Knopp迭代，mHC通过保留信号强度和特征均值确保能量守恒，这能稳定梯度并缓解复杂网络中的信号退化。我们通过替换ECAPA-TDNN、ResNet-34、Res2Net和E-Res2Net等主干网络中的标准残差连接来评估mHC。在VoxCeleb1上的大量实验表明，mHC连接在所有架构中均持续提升性能，凸显了其对鲁棒说话人表示学习的有效性。
英文摘要
Residual connections are fundamental to deep speaker recogni- tion models, such as ECAPA-TDNN and ResNet. However, standard identity mapping limits information flow to a sin- gle path, constraining representation capacity. We introduce Manifold-Constrained Hyper-Connections (mHC), reformulat- ing residual paths as a multi-stream evolution where informa- tion is mixed through a doubly stochastic matrix. By employing Sinkhorn-Knopp iterations, mHC ensures energy conservation by preserving signal intensity and feature mean, which stabi- lizes gradients and mitigates signal degradation in complex net- works. We evaluate mHC by replacing standard residual con- nections in backbones including ECAPA-TDNN, ResNet-34, Res2Net, and E-Res2Net. Extensive experiments on VoxCeleb1 demonstrate that mHC connections consistently enhance per- formance across all architectures, highlighting its effectiveness for robust speaker representation learning.
CommentsAccepted to INTERSPEECH 2026
