SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniques
Preprint
Abstract
Speech enhancement aims to improve speech quality and intelligibility, especially in noisy environments where background noise degrades speech signals. Currently, deep learning methods achieve great success in speech enhancement, e.g. the representative convolutional recurrent neural network (CRN) and its variants. However, CRN typically employs consecutive downsampling and upsampling convolution for frequency modeling, which destroys the inherent structure of the signal over frequency. Additionally, convolutional layers lacks of temporal modelling abilities. To address these issues, we propose an innovative module combing a State space model and Inplace Convolution (SIC), and to replace the conventional convolution in CRN, called SICRN. Specifically, a dual-path multidimensional State space model captures the global frequencies dependency and long-term temporal dependencies. Meanwhile, the 2D-inplace convolution is used to capture the local structure, which abandons the downsampling and upsampling. Systematic evaluations on the public INTERSPEECH 2020 DNS challenge dataset demonstrate SICRN's efficacy. Compared to strong baselines, SICRN achieves performance close to state-of-the-art while having advantages in model parameters, computations, and algorithmic delay. The proposed SICRN shows great promise for improved speech enhancement.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models2023
- FFC-SE: Fast Fourier Convolution for Speech Enhancement2022
- Inplace Gated Convolutional Recurrent Neural Network for Dual-Channel Speech Enhancement2021
- DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement2020
- PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss2020
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement2018