CA-MHFA：一种用于基于SSL的说话人验证的上下文感知多头分解注意力池化
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification
AI总结：
本文提出轻量级框架CA-MHFA，通过分组可学习查询与共享键值融合上下文信息，有效建模局部时间依赖，在VoxCeleb上以更少参数超越复杂模型，并在多任务中展现强泛化能力。
摘要：
近年来，用于说话人验证（SV）的自监督学习（SSL）模型备受关注。然而，现有的基于SSL的SV系统通常难以捕捉局部时间依赖性，且在不同任务间的泛化能力较差。本文提出上下文感知多头分解注意力池化（CA-MHFA），这是一个融合了来自周围帧的上下文信息的轻量级框架。CA-MHFA利用分组的可学习查询来有效建模上下文依赖关系，同时通过在组间共享键和值来保持高效性。在VoxCeleb数据集上的实验结果表明，CA-MHFA在Vox1-O、Vox1-E和Vox1-H上分别实现了0.42%、0.48%和0.96%的EER，以更少的参数和更快的收敛速度超越了WavLM-TDNN等复杂模型。此外，CA-MHFA在包括情感识别和反欺骗在内的多个SSL模型和任务中展现出强大的泛化能力，突显了其鲁棒性和多功能性。
英文摘要：
Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years. However, existing SSL-based SV systems often struggle to capture local temporal dependencies and generalize across different tasks. In this paper, we propose context-aware multi-head factorized attentive pooling (CA-MHFA), a lightweight framework that incorporates contextual information from surrounding frames. CA-MHFA leverages grouped, learnable queries to effectively model contextual dependencies while maintaining efficiency by sharing keys and values across groups. Experimental results on the VoxCeleb dataset show that CA-MHFA achieves EERs of 0.42\%, 0.48\%, and 0.96\% on Vox1-O, Vox1-E, and Vox1-H, respectively, outperforming complex models like WavLM-TDNN with fewer parameters and faster convergence. Additionally, CA-MHFA demonstrates strong generalization across multiple SSL models and tasks, including emotion recognition and anti-spoofing, highlighting its robustness and versatility.
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。
