Spiking Structured State Space Model for Monaural Speech Enhancement

arXiv:2309.03641v2 Announce Type: replace-cross
Abstract: 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 …

abstract arxiv challenges computational costs cs.cv cs.sd deep learning eess.as efficiency energy energy efficiency extract face information space speech state state space model structured state space type