For More Information:
Booz Allen Hamilton Distinguished Colloquium in Electrical and Computer Engineering
"Automatic Speech Recognition and Code Breaking"
Dr. Fred Jelinek
Julian Sinclair Smith Professor, Department of Electrical and Computer Engineering and Director, Center for Language and Speech Processing, Johns Hopkins University
Friday, November 20, 2009
Jeong H. Kim Engineering Bldg., Rm. 1110
Practical automatic speech recognition is of necessity a (near) real time activity performed by a system whose structure is fixed and whose parameters once trained may be adapted on the basis of the speech that the system observed during recognition.
However, in specially important situations (e.g., recovery of out-of-vocabulary words) the recognition task could be viewed as an activity akin to code--breaking to whose accomplishment can be devoted an essentially infinite amount of effort. In such a case everything would be fair, including, for instance, the retraining of a language and/or acoustic model on the basis of newly acquired data (from the internet!) or even a complete change of the recognizer paradigm.
An obvious way to proceed is to use the basic recognizer to produce a lattice or confusion network and then do the utmost to eliminate ambiguity. Another possibility is to create a list of frequent confusions (for instance the pair IN and AND) and prepare an appropriate individual decision algorithm to resolve each when it occurs in test data. One or two cases of code-breaking will be presented.
Dr. Fred Jelinek received his S.B., S.M., and Ph.D. in Electrical Engineering from Massachusetts Institute of Technology.
Dr. Jelinek served as an Instructor at MIT (1959-1962), a Visiting Lecturer at Harvard University (1962), and a Professor of Electrical Engineering at Cornell University (1962-1974). Prof. Jelinek's past work includes fundamental contributions to information theory and coding. From 1972 to 1993 he headed the large Continuous Speech Recognition group of the IBM T.J. Watson Research Center. There he pioneered with his colleagues the statistical methods that are the basis of current state-of-the art speech recognizers. His primary research interests are in Speech Recognition, statistical methods of natural language processing, and information theory. Prof. Jelinek's special interest is language modeling, that is, the prediction of future words given preceding text or speech. He is also interested in novel methods of automatic parsing, of text understanding, and of machine translation.
He has been the recipient of numerous honors and awards. He received the IEEE Signal Processing Society's "Society Award" for leadership and technical contributions to the field in 1998. In November 2001, Dr. Jelinek was awarded an Honorary Doctorate of Mathematical Physical Disciplines awarded by the Academic Senate of Charles University of Prague. Dr. Jelinek was elected to the National Academy of Engineering (NAE) in 2006. He was recognized for his contributions to statistical language processing with applications to automatic speech recognition. In 2008, Dr. Jelinek was honored by the International Speech Communication Association (ISCA) that named him to be one of the association's twelve inaugural Fellows.
This Event is For: Campus • Clark School • All Students • Faculty • Staff • Corporate • Donors