IEEE

HyIMC: Analog-Digital Hybrid In-Memory Computing SoC for High-Quality Low-Latency Speech Enhancement

Abstract: In-memory computing (IMC) holds significant promise for accelerating deep learning-based speech enhancement (DL-SE). However, existing IMC architectures face challenges in simultaneously ...
IEEE

Neural Memory Self-Supervised State Space Models With Learnable Gates

Abstract: Discrete Ordinary Differential Equations (ODEs) have been employed to develop lightweight deep neural networks in recent years. In this letter, we introduce a novel lightweight UNet variant ...