Real Time Speech Enhancement
Real-time speech enhancement aims to improve the clarity and intelligibility of speech signals in noisy environments, focusing on computationally efficient methods suitable for resource-constrained devices. Current research emphasizes lightweight neural network architectures, such as two-stage networks and those employing sub-band processing or dynamic attention mechanisms, to achieve real-time performance while maintaining high speech quality. These advancements are crucial for applications like voice assistants and hearing aids, improving user experience and accessibility in various communication technologies.
Papers
Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features
Emiru Tsunoo, Yuki Saito, Wataru Nakata, Hiroshi Saruwatari
BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement
Cunhang Fan, Enrui Liu, Andong Li, Jianhua Tao, Jian Zhou, Jiahao Li, Chengshi Zheng, Zhao Lv