CSL
2010
Springer
13 years 9 months ago
2010
Springer
A conventional automatic speech recognizer does not perform well in the presence of multiple sound sources, while human listeners are able to segregate and recognize a signal of i...
AAAI
1994
13 years 10 months ago
1994
We propose a novel approach to auditory stream segregation which extracts individual sounds (auditory stream) from a mixture of sounds in auditory scene analysis. The HBSS (Harmon...
NIPS
2004
13 years 10 months ago
2004
An auditory "scene", composed of overlapping acoustic sources, can be viewed as a complex object whose constituent parts are the individual sources. Pitch is known to be...
NIPS
2007
13 years 10 months ago
2007
Natural sounds are structured on many time-scales. A typical segment of speech, for example, contains features that span four orders of magnitude: Sentences (∼1 s); phonemes (âˆ...