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 …

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

This study proposes a cross-domain multi-objective speech assessment model, called
MOSA-Net, which can simultaneously estimate the speech quality, intelligibility, and …

Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a
target acoustic environment. Existing methods assume access to paired training data, where …

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 …

This paper introduces the Unbeatable Team's submission to the ICASSP 2023 Deep Noise
Suppression (DNS) Challenge. We expand our previous work, TEA-PSE, to its upgraded …

Speech quality estimation has recently undergone a paradigm shift from human-hearing
expert designs to machine-learning models. However, current models rely mainly on …

Supervised masking approaches in the time-frequency domain aim to employ deep neural
networks to estimate a multiplicative mask to extract clean speech. This leads to a single …

In reverberant conditions with a single speaker, each far-field microphone records a
reverberant version of the same speaker signal at a different location. In over-determined …

This paper introduces an end-to-end neural speech restoration model, HD-DEMUCS,
demonstrating efficacy across multiple distortion environments. Unlike conventional …