LightCAM: A Fast and Light Implementation of Context-Aware Masking based D-TDNN for Speaker Verification
This work addresses efficiency challenges for deploying speaker verification systems in industrial environments, representing an incremental improvement over existing D-TDNN with CAM methods.
The paper tackled the problem of high computational complexity and slow inference in speaker verification models by proposing LightCAM, a fast and lightweight architecture that achieved an EER of 0.83 and MinDCF of 0.0891 on VoxCeleb1-O, outperforming other mainstream methods.
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.