The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

In the age of artificial intelligence, the best approach to handling huge amounts of data is a
tremendously motivating and hard problem. Among machine learning models, stochastic …

Recent advancements in generative speech models based on audio-text prompts have
enabled remarkable innovations like high-quality zero-shot text-to-speech. However …

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

This paper proposes a full-band and sub-band fusion model, named as FullSubNet, for
single-channel real-time speech enhancement. Full-band and sub-band refer to the models …

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 …

Previously proposed FullSubNet has achieved outstanding performance in Deep Noise
Suppression (DNS) Challenge and attracted much attention. However, it still encounters …

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 …

Curriculum learning begins to thrive in the speech enhancement area, which decouples the
original spectrum estimation task into multiple easier sub-tasks to achieve better …