We aim to assess the perceived quality of estimated source signals in the context of audio
source separation. These signals may involve one or more kinds of distortions, including …

Conventional speaker recognition systems perform poorly under noisy conditions. Inspired
by auditory perception, computational auditory scene analysis (CASA) typically segregates …

We present the outcomes of three recent evaluation campaigns in the field of audio and
biomedical source separation. These campaigns have witnessed a boom in the range of …

Robustness of speaker recognition systems is crucial for real-world applications, which
typically contain both additive noise and room reverberation. However, the combined effects …

We present a multi-channel database of overlapping speech for training, evaluation, and
detailed analysis of source separation and extraction algorithms: SMS-WSJ--Spatialized …

To clarify the role of spatial cues in sound segregation, this study explored whether
interaural time differences (ITDs) are sufficient to allow listeners to identify a novel sound …

A monaural binary time-frequency (TF) masking technique is proposed for suppressing
reverberation. The mask is estimated for each TF unit by extracting a variance-based feature …

Some of the earliest work examining human selective attention considered auditory
communication signals, focusing on the issue of how we choose what to listen to in a mixture …

Reverberation continues to present a major problem for sound source separation
algorithms, due to its corruption of many of the acoustical cues on which these algorithms …

Purpose In this article, a new signal-processing algorithm is proposed and evaluated for the
suppression of the combined effects of reverberation and noise. Method The proposed …