A new approach to the separation of speech from speech-in-noise mixtures is the use of time-
frequency (TF) masking. Originated in the field of computational auditory scene analysis, TF …

Speech enhancement and separation are core problems in audio signal processing, with
commercial applications in devices as diverse as mobile phones, conference call systems …

This paper describes the acquisition of a new database of dysarthric speech in terms of
aligned acoustics and articulatory data. This database currently includes data from seven …

A method is proposed that provides an approximation of the acoustic energy decay (energy–
time curve) in room impulse responses generated using the image-source technique. A …

During the past three decades, the issue of processing spectral phase has been largely
neglected in speech applications. There is no doubt that the interest of speech processing …

The performance of most of the classical sound source localization algorithms degrades
seriously in the presence of background noise or reverberation. Recently, deep neural …

The image-source method has become a ubiquitous tool in many fields of acoustics and
signal processing. A technique was recently proposed to predict the energy decay (energy …

Separation of speech mixtures, often referred to as the cocktail party problem, has been
studied for decades. In many source separation tasks, the separation method is limited by …

A central question in derandomization is whether randomized logspace (RL) equals
deterministic logspace (L). To show that RL= L, it suffices to construct explicit pseudorandom …

The feature extraction stage of speech recognition is important historically and is the subject
of much current research, particularly to promote robustness to acoustic disturbances such …