Title :
A comparison of auditory and blind separation techniques for speech segregation
Author :
Van der Kouwe, Andre J W ; Wang, DeLiang ; Brown, Guy J.
Author_Institution :
Nucl. Magnetic Resonance Center, Massachusetts Gen. Hosp., Charlestown, MA, USA
fDate :
3/1/2001 12:00:00 AM
Abstract :
A fundamental problem in auditory and speech processing is the segregation of speech from concurrent sounds. This problem has been a focus of study in computational auditory scene analysis (CASA), and it has also been investigated from the perspective of blind source separation. Using a standard corpus of voiced speech mixed with interfering sounds, we report a comparison between CASA and blind source separation techniques, which have been developed independently. Our comparison reveals that they perform well under very different conditions. A number of conclusions are drawn with respect to their relative strengths and weaknesses in speech segregation applications as well as in modeling auditory function
Keywords :
acoustic signal processing; hearing; speech processing; speech recognition; auditory function modelling; auditory processing; auditory separation; blind separation; blind source separation; computational auditory scene analysis; concurrent sounds; interfering sounds; speech processing; speech segregation; speech segregation applications; voiced speech; Biomedical computing; Biomedical engineering; Blind source separation; Cognitive science; Image analysis; Loudspeakers; Nuclear magnetic resonance; Speech analysis; Speech processing; Standards development;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
