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 Awa...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-02
Main Authors: Cao, Di, Wang, Xianchen, Zhou, Junfeng, Zhang, Jiakai, Yanjing Lei, Chen, Wenpeng
Format: Article
Language:English
Subjects:
Complexity
Computing costs
Context
Cost analysis
Inference
Masking
Modules
Neural networks
Time lag
Verification
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422