EfficientTDNN: Efficient Architecture Search for Speaker Recognition [article]

Rui Wang, Zhihua Wei, Haoran Duan, Shouling Ji, Yang Long, Zhen Hong
2021 arXiv   pre-print
Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory. Discovering the specialized CNN that meets a specific constraint requires a substantial effort of human experts. Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual
more » ... tecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition. In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm. The proposed supernet introduces temporal convolution of different ranges of the receptive field and feature aggregation of various resolutions from different layers to TDNN. On top of it, the TDNN-NAS algorithm quickly searches for the desired TDNN architecture via weight-sharing subnets, which surprisingly reduces computation while handling the vast number of devices with various resources requirements. Experimental results on the VoxCeleb dataset show the proposed EfficientTDNN enables approximate 10^13 architectures concerning depth, kernel, and width. Considering different computation constraints, it achieves a 2.20 multiply-accumulate operations (MACs), 1.41 0.94 trained supernet generalizes subnets not sampled during training and obtains a favorable trade-off between accuracy and efficiency.
arXiv:2103.13581v4 fatcat:rwmzhvfdubfapjl5mldbg2ulkm