Real-time speech enhancement (SE) is essential to online speech communication. Causal
SE models use only the previous context while predicting future information, such as …

Automatically predicting the mean opinion score (MOS) of a synthesized speech without the
reference signal with deep learning systems has been studied extensively recently and …

Deep neural network (DNN) based speech enhancement techniques have shown superior
performance compared to the traditional speech enhancement approaches in handling …

In this paper, we propose DCDP-Net for real-time speech enhancement in the time-
frequency domain, which denoises both the magnitude and phase spectra. DCDP-Net uses …

Speech background noise is a common issue, which has become especially important with
the increasing popularity of online meetings and live internet broadcasting. Recently, Deep …

Since noise significantly impacts speech quality and intelligibility, it is important to eliminate
it in speech enhancement. Conformer networks have gained popularity in this area due to …