Saved in:
Bibliographic Details
Main Authors: Du, Yu, Liu, Xu, Chua, Yansong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.03641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910416328720384
author Du, Yu
Liu, Xu
Chua, Yansong
author_facet Du, Yu
Liu, Xu
Chua, Yansong
contents Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce the Spiking Structured State Space Model (Spiking-S4). This approach merges the energy efficiency of Spiking Neural Networks (SNN) with the long-range sequence modeling capabilities of Structured State Space Models (S4), offering a compelling solution. Evaluation on the DNS Challenge and VoiceBank+Demand Datasets confirms that Spiking-S4 rivals existing Artificial Neural Network (ANN) methods but with fewer computational resources, as evidenced by reduced parameters and Floating Point Operations (FLOPs).
format Preprint
id arxiv_https___arxiv_org_abs_2309_03641
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spiking Structured State Space Model for Monaural Speech Enhancement
Du, Yu
Liu, Xu
Chua, Yansong
Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce the Spiking Structured State Space Model (Spiking-S4). This approach merges the energy efficiency of Spiking Neural Networks (SNN) with the long-range sequence modeling capabilities of Structured State Space Models (S4), offering a compelling solution. Evaluation on the DNS Challenge and VoiceBank+Demand Datasets confirms that Spiking-S4 rivals existing Artificial Neural Network (ANN) methods but with fewer computational resources, as evidenced by reduced parameters and Floating Point Operations (FLOPs).
title Spiking Structured State Space Model for Monaural Speech Enhancement
topic Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
url https://arxiv.org/abs/2309.03641