Variational autoencoders (VAEs) are powerful deep generative models widely used to
represent high-dimensional complex data through a low-dimensional latent space learned …

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 …

In this work, we build upon our previous publication and use diffusion-based generative
models for speech enhancement. We present a detailed overview of the diffusion process …

Diffusion models have shown a great ability at bridging the performance gap between
predictive and generative approaches for speech enhancement. We have shown that they …

Score-based generative models (SGMs) have recently shown impressive results for difficult
generative tasks such as the unconditional and conditional generation of natural images …

Language models (LMs) have recently shown superior performances in various speech
generation tasks, demonstrating their powerful ability for semantic context modeling. Given …

Deep neural networks (DNN) techniques have become pervasive in domains such as
natural language processing and computer vision. They have achieved great success in …

Diffusion models have recently shown promising results for difficult enhancement tasks such
as the conditional and unconditional restoration of natural images and audio signals. In this …

Most of the deep learning-based speech enhancement models are learned in a supervised
manner, which implies that pairs of noisy and clean speech are required during training …

To obtain improved speech enhancement models, researchers often focus on increasing
performance according to specific instrumental metrics. However, when the same metric is …