Frederick Jelinek
From Wikipedia, the free encyclopedia
Frederick Jelinek (born 18 November 1932 in Prague) is a researcher in information theory, automatic speech recognition, and natural language processing. Jelinek's early career produced fundamental contributions to information theory and coding. He later became a pioneer in applying statistical modeling to speech recognition and natural language processing. He and his colleagues were the first to apply hidden Markov models to these tasks. His special interest is language modeling, and much of his recent work has had to do with moving beyond n-gram models to take advantage of long distance and syntactic regularities.
Jelinek taught at the Massachusetts Institute of Technology 1959 to 1962, at Harvard University in 1962, and at Cornell University from 1962-1974. From 1972 to 1993 he headed the Continuous Speech Recognition group of IBM's Thomas J. Watson Research Center, which pioneered the statistical techniques which became the basis of modern speech recognition. In 1993 he joined the Johns Hopkins University, where he is currently Julian Sinclair Smith Professor in the university's department of electrical and computer engineering, and director of the university's Center for Language and Speech Processing.
Jelinek holds a Ph.D. from the Massachusetts Institute of Technology, as well as an honorary doctorate from the Charles University in Prague.
[edit] Books
- Probabilistic Information Theory. McGraw-Hill. 1968
- Statistical Methods for Speech Recognition. MIT Press. 1998. ISBN 0-262-10066-5.
