Autoencoders are a self-supervised learning system where, during training, the output is an
approximation of the input. Typically, autoencoders have three parts: Encoder (which …

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 …

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

Dynamical variational autoencoders (DVAEs) are a class of deep generative models with
latent variables, dedicated to model time series of high-dimensional data. DVAEs can be …

Along with AIGC shines in CV and NLP, its potential in the wireless domain has also
emerged in recent years. Yet, existing RF-oriented generative solutions are ill-suited for …

Music is a universal language that can communicate emotions and feelings. It forms an
essential part of the whole spectrum of creative media ranging from movies to social media …

Traditional stereophonic acoustic echo cancellation algorithms need to estimate acoustic
echo paths from stereo loudspeakers to a microphone, which often suffers from the …

We propose a multi-dimensional structured state space (S4) approach to speech
enhancement. To better capture the spectral dependencies across the frequency axis, we …

Recently, the standard variational autoencoder has been successfully used to learn a
probabilistic prior over speech signals, which is then used to perform speech enhancement …

The goal of this study is to implement diffusion models for speech enhancement (SE). The
first step is to emphasize the theoretical foundation of variance-preserving (VP)-based …