LightCAM: A Fast and Light Implementation of Context-Aware Masking based D-Tdnn for Speaker Verification

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 …

art complexity computational context cost cs.cl cs.sd delay eess.as environment implementation industrial inference light making masking network networks neural network neural networks performance speaker speed state them verification