Humans can listen to a target speaker even in challenging acoustic conditions that have
noise, reverberation, and interfering speakers. This phenomenon is known as the cocktail …

Speech enhancement and speech separation are two related tasks, whose purpose is to
extract either one or more target speech signals, respectively, from a mixture of sounds …

The key advantage of using multiple microphones for speech enhancement is that spatial
filtering can be used to complement the tempo-spectral processing. In a traditional setting …

Target speech separation refers to extracting a target speaker's voice from an overlapped
audio of simultaneous talkers. Previously the use of visual modality for target speech …

Standing upon the intersection of traditional beamformers and deep neural networks, we
propose a causal neural beamformer paradigm called Embedding and Beamforming, and …

Recently, frequency domain all-neural beamforming methods have achieved remarkable
progress for multichannel speech separation. In parallel, the integration of time domain …

We introduce the active audio-visual source separation problem, where an agent must move
intelligently in order to better isolate the sounds coming from an object of interest in its …

In a multi-channel separation task with multiple speakers, we aim to recover all individual
speech signals from the mixture. In contrast to single-channel approaches, which rely on the …

We introduce region-customizable sound extraction (ReZero), a general and flexible
framework for the multi-channel region-wise sound extraction (R-SE) task. R-SE task aims at …

To date, mainstream target speech separation (TSS) approaches are formulated to estimate
the complex ratio mask (cRM) of target speech in time-frequency domain under supervised …