LightCAM：一种基于上下文感知掩码的D-TDNN的快速轻量级实现
LightCAM: A Fast and Light Implementation of Context-Aware Masking based D-TDNN for Speaker Verification
AI总结：
针对TDNN计算复杂度高的问题，提出轻量级模型LightCAM，结合DSM和MFA优化D-TDNN，在VoxCeleb上取得更优性能且降低计算成本。
摘要：
传统时延神经网络（TDNN）以高计算复杂度和较慢的推理速度为代价取得了最先进的性能，使其难以在工业环境中实现。带有上下文感知掩码（CAM）模块的密集连接时延神经网络（D-TDNN）已被证明是降低复杂度同时保持系统性能的有效结构。本文提出了一种快速轻量级模型LightCAM，它进一步采用深度可分离卷积模块（DSM），并使用多尺度特征聚合（MFA）进行不同层次的特征融合。在VoxCeleb数据集上进行了大量实验，比较结果表明，它在VoxCeleb1-O上取得了0.83的EER和0.0891的MinDCF，优于其他主流说话人验证方法。此外，复杂度分析进一步表明，所提出的架构具有更低的计算成本和更快的推理速度。
英文摘要：
Traditional Time Delay Neural Networks (TDNN) have achieved state-of-the-art performance at the cost of high computational complexity and slower inference speed, making them difficult to implement in an industrial environment. The Densely Connected Time Delay Neural Network (D-TDNN) with Context Aware Masking (CAM) module has proven to be an efficient structure to reduce complexity while maintaining system performance. In this paper, we propose a fast and lightweight model, LightCAM, which further adopts a depthwise separable convolution module (DSM) and uses multi-scale feature aggregation (MFA) for feature fusion at different levels. Extensive experiments are conducted on VoxCeleb dataset, the comparative results show that it has achieved an EER of 0.83 and MinDCF of 0.0891 in VoxCeleb1-O, which outperforms the other mainstream speaker verification methods. In addition, complexity analysis further demonstrates that the proposed architecture has lower computational cost and faster inference speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
