Despite the recent success of deep learning for many speech processing tasks, single-
microphone, speaker-independent speech separation remains challenging for two main …

Data-driven models for audio source separation such as U-Net or Wave-U-Net are usually
models dedicated to and specifically trained for a single task, eg a particular instrument …

Signal extraction from a single-channel mixture with additional undesired signals is most
commonly performed using time-frequency (TF) masks. Typically, the mask is estimated with …

We propose PSMGAN, an efficient phase sensitive masking-based single-channel speech
enhancement technique using a conditional generative adversarial network (cGAN). The …

Phase retrieval (PR) aims to recover a signal from the magnitudes of a set of inner products.
This problem arises in many audio signal processing applications which operate on a short …

In recent years, deep learning based supervised speech enhancement methods have
gained a considerable amount of research attention over the statistical signal processing …

In this paper, we propose a model to perform speech dereverberation by estimating its
spectral magnitude from the reverberant counterpart. Our models are capable of extracting …

Independent low-rank matrix analysis (ILRMA) is the state-of-the-art algorithm for blind
source separation (BSS) in the determined situation (the number of microphones is greater …

Dereverberation is useful in hands-free communication and voice controlled devices for
distant speech acquisition. Singlechannel dereverberation can be achieved by applying a …

Denoising a single-channel speech (recorded using one microphone) remains an open
problem in many speech-related applications. Recently, supervised deep learning methods …