Subject: Tech report on speech segregation From: DeLiang Wang <dwang(at)CIS.OHIO-STATE.EDU> Date: Fri, 25 Jun 1999 09:59:52 -0400The following technical report is available via FTP/WWW: ******************************************************************** "A Comparison of Auditory and Blind Separation Techniques for Speech Segregation" Technical Report #15, June 1999 Department of Computer and Information Science The Ohio State University ******************************************************************** Andre J. W. van der Kouwe, The Ohio State University DeLiang L. Wang, The Ohio State University Guy J. Brown, The University of Sheffield 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 recently 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. (10 pages, 92 KB compressed) for anonymous ftp: FTP-HOST: ftp.cis.ohio-state.edu Directory: /pub/tech-report/1999/ Filename: TR15.ps.gz for WWW: http://www.cis.ohio-state.edu/~dwang/reports.html -- ------------------------------------------------------------ My contact information through September, 1999 is: Dr. DeLiang Wang Visual Sciences Lab. William James Hall Harvard University 33 Kirkland Street Cambridge, MA 02138 Email: dwang(at)wjh.harvard.edu (my OSU email address is good too) Phone: 617-496-3367 (OFFICE); 617-495-3884 (LAB) Fax: 617-495-3764 URL: http://www.cis.ohio-state.edu/~dwang