Generally, the performance of deep neural networks (DNNs) heavily depends on the quality
of data representation learning. Our preliminary work has emphasized the significance of …

Most speech enhancement algorithms need an estimate of the noise power spectral density
(PSD) to work. In this paper, we introduce a model-based framework for doing noise PSD …

This article focuses on leveraging deep representation learning (DRL) for speech
enhancement (SE). In general, the performance of the deep neural network (DNN) is heavily …

In real-time speech communication systems, speech signals are often degraded by multiple
distortions. Recently, a two-stage Repair-and-Denoising network (RaD-Net) was proposed …

This paper advances the field of environmental sound recognition, presenting a refined
approach to beamforming and noise identification through digital simulations of realistic …

This study presents an innovative beamforming method tailored for audio surveillance
applications, developed through virtual simulations conducted at Liverpool John Moores …

In this paper, we propose a supervised single-channel speech enhancement method that
combines Kullback-Leibler (KL) divergence-based non-negative matrix factorization (NMF) …

This paper presents a delay and sum beamforming audio zoom method for addressing
broken microphones in video surveillance systems. The proposed approach utilises a …

This paper is a presentation of two important types of information regarding natural signals
and groups of relative things. The measure of the first information type is the order of the …

In natural listening environments, speech signals are easily distorted by various acoustic
interference, which reduces the speech quality and intelligibility of human listening; …