Most existing binaural approaches to speech segregation rely on spatial filtering. In environments with minimal reverberation and when sources are well separated in space, spatial...
John Woodruff, Rohit Prabhavalkar, Eric Fosler-Lus...
This paper presents a novel way of improving POS tagging on heterogeneous data. First, two separate models are trained (generalized and domain-specific) from the same data set by...
— This paper presents a robot audition system that recognizes simultaneous speech in the real world by using robotembedded microphones. We have previously reported Missing Featur...
A sound source separation technique based on a bio-inspired neural network, capable of functioning in more than two-source mixtures, is proposed. Separation results are compared wi...
The present contribution aims at increasing our understanding of automatic speech recognition (ASR) errors involving frequent homophone or almost homophone words by confronting th...