193 search results - page 28 / 39 » To Separate Speech |
INTERSPEECH
2010
13 years 2 months ago
2010
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...
ACL
2012
11 years 10 months ago
2012
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...
IROS
2006
IEEE
14 years 1 months ago
2006
IEEE
— 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...
NN
2004
Springer
14 years 27 days ago
2004
Springer
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...
LREC
2008
13 years 9 months ago
2008
The present contribution aims at increasing our understanding of automatic speech recognition (ASR) errors involving frequent homophone or almost homophone words by confronting th...