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

In real-world scenarios, dynamic ambient noise often degrades speech quality, highlighting
the need for advanced speech enhancement techniques. Traditional methods, which rely on …

Performance degradation caused by noise has been a long-standing challenge for speaker
verification. Previous methods usually involve applying a denoising transformation to …

This paper presents the crossing scheme (X-scheme) for improving the performance of deep
neural network (DNN)-based music source separation (MSS) with almost no increasing …

The goal of speech enhancement (SE) is to eliminate the background interference from the
noisy speech signal. Generative models such as diffusion models (DM) have been applied …

Speech data gathered from real-world environments typically contain noise, a significant
element that undermines the performance of deep neural network-based speaker …

Most existing speech enhancement (SE) approaches heavily depend on simulated data for
training, leading to performance degradation on realistic data and subsequent speech …

For deep learning-based speech enhancement (SE) systems, the training-test acoustic
mismatch can cause notable performance degradation. To address the mismatch issue …

This paper describes a supervised speech enhancement (SE) method utilising a noise-
aware four-layer deep neural network and training target switching. For optimal speech …

Recent research on speech enhancement (SE) has seen the emergence of deep-learning-
based methods. It is still a challenging task to determine the effective ways to increase the …