Frequency-domain monaural speech enhancement has been extensively studied for over
60 years, and a great number of methods have been proposed and applied to many …

Speech enhancement has substantial interest in the utilization of speaker identification,
video-conference, speech transmission through communication channels, speech-based …

For challenging acoustic scenarios as low signal-to-noise ratios, current speech
enhancement systems usually suffer from performance bottleneck in extracting the target …

The capability of the human to pay attention to both coarse and fine-grained regions has
been applied to computer vision tasks. Motivated by that, we propose a collaborative …

Sub-band models have achieved promising results due to their ability to model local
patterns in the spectrogram. Some studies further improve the performance by fusing sub …

With the advance in automatic speech recognition, voice user interface has gained
popularity recently. Since the COVID-19 pandemic, VUI is increasingly preferred in online …

Many deep learning-based speech enhancement algorithms are designed to minimize the
mean-square error (MSE) in some transform domain between a predicted and a target …

Deep neural network (DNN) based end-to-end optimization in the complex time-frequency
(TF) domain or time domain has shown considerable potential in monaural speech …

We address talker-independent monaural speaker separation from the perspectives of deep
learning and computational auditory scene analysis (CASA). Specifically, we decompose …

We propose a novel application of an attention mechanism in neural speech enhancement,
by presenting a U-Net architecture with attention mechanism, which processes the raw …