Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation
Jian Luo, Jianzong Wang, Ning Cheng, Edward Xiao, Xulong Zhang, Jing Zhong Xiao · Interspeech 2022 · 2022
Time-domain Transformer neural networks have proven their superiority in speech separation tasks.However, these models usually have a large number of network parameters, thus often encountering the problem of GPU memory explosion.In this paper, we proposed Tiny-Sepformer, a tiny version of Transformer network for speech separation.We present two techniques to reduce the model parameters and memory consumption: (1) Convolution-Attention (CA) block, spliting the vanilla Transformer to two paths, multi-head attention and 1D depthwise separable convolution, (2) parameter sharing, sharing the layer parameters within the CA block.In our experiments, Tiny-Sepformer could greatly reduce the model size, and achieves comparable separation performance with vanilla Sepformer on WSJ0-2/3Mix datasets.