Similar to humans' cognitive ability to generalize knowledge and skills, self-supervised
learning (SSL) targets discovering general representations from large-scale data. This …

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

Speech enhancement and separation are two fundamental tasks for robust speech
processing. Speech enhancement suppresses background noise while speech separation …

Abstract We introduce the Bioacoustic Cocktail Party Problem Network (BioCPPNet), a
lightweight, modular, and robust U-Net-based machine learning architecture optimized for …

We introduce a new paradigm for single-channel target source separation where the
sources of interest can be distinguished using non-mutually exclusive concepts (eg …

The SepFormer architecture shows very good results in speech separation. Like other
learned-encoder models, it uses short frames, as they have been shown to obtain better …

Self-supervised Speech Models (S3Ms) have been proven successful in many speech
downstream tasks, like ASR. However, how pretraining data affects S3Ms' downstream …

AV-HuBERT, a multi-modal self-supervised learning model, has been shown to be effective
for categorical problems such as automatic speech recognition and lip-reading. This …

We present a novel approach that improves the performance of reverberant speech
separation. Our approach is based on an accurate geometric acoustic simulator (GAS) …

Speaker-independent speech separation has achieved remarkable performance in recent
years with the development of deep neural network (DNN). Various network architectures …