SPGM: Prioritizing Local Features for enhanced speech separation performance
Abstract
Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships. However, it has been found that inter-blocks, which comprise half a dual-path model's parameters, contribute minimally to performance. Thus, we propose the Single-Path Global Modulation (SPGM) block to replace inter-blocks. SPGM is named after its structure consisting of a parameter-free global pooling module followed by a modulation module comprising only 2% of the model's total parameters. The SPGM block allows all transformer layers in the model to be dedicated to local feature modelling, making the overall model single-path. SPGM achieves 22.1 dB SI-SDRi on WSJ0-2Mix and 20.4 dB SI-SDRi on Libri2Mix, exceeding the performance of Sepformer by 0.5 dB and 0.3 dB respectively and matches the performance of recent SOTA models with up to 8 times fewer parameters. Model and weights are available at huggingface.co/yipjiaqi/spgm
Cite
@article{arxiv.2309.12608,
title = {SPGM: Prioritizing Local Features for enhanced speech separation performance},
author = {Jia Qi Yip and Shengkui Zhao and Yukun Ma and Chongjia Ni and Chong Zhang and Hao Wang and Trung Hieu Nguyen and Kun Zhou and Dianwen Ng and Eng Siong Chng and Bin Ma},
journal= {arXiv preprint arXiv:2309.12608},
year = {2024}
}
Comments
This paper was accepted by ICASSP 2024