As part of an internally funded R&D program in automatic speech recognition, I have written a suite of programs for training ``Hidden Markov Models'' using the ``Segmental K-Means Algorithm.'' This suite includes shell scripts and programs written in C and Haskell. I am writing a report describing the Haskell part of the system. A PostScript version of the current draft of this report is now available by ftp from nebula.cs.yale.edu in the directory pub/haskell/papers in the file hmms.ps.gz. This draft will be handed out at the upcoming Dagstuhl Seminar on Functional Programming in the Real World. In addition, a copy of the viewgraphs that accompany the Dagstuhl talk are also available at the same site in the same directory, the file being hmms-viewgraphs.ps.gz. Although the copyright notice at the beginning of the report gives permission to freely distribute the software, I haven't yet packaged the programs up for distribution. I hope to do that soon; at the moment the files are still scattered about. Even then, some of the programs will not be runnable without a large database of speech files. David M. Goblirsch ([EMAIL PROTECTED]) Lead Engineer, Signal Processing Center The MITRE Corporation, 7525 Colshire Dr, McLean VA 22102-3481, Mail Stop W622 voice: (703) 883-5450 or (703) 883-5769 FAX: (703) 883-6708
