Engineering Colloquium Home
Schedule for this lecture.

Goddard Space Flight Center Engineering Colloquium

Date: Monday, December 1, 1997

Speech Recognition Research in the U.S.

Speaker: Frederick Jelinek


Speech and language processing is an increasingly important component of advanced modes of computer interaction. There are many commercial interests in application-domain specific systems with automated speech input -- for example, telephone number dialing, airline schedules and reservations, speech transcribers, and audio PC interfaces. Government requirements (automated keyword recognizers, natural modes of computer interfaces, natural language processes, etc.) further drive basic and applied research in speech recognition. However, it is difficult to determine the current status of speech recognition technology because of differences in commercial vs. research systems, different goals and requirements of applications, and the lack of standard measures of performance for comparisons. The talk will survey the current government programs supporting speech recognition research. The various goals of DARPA, NSA, and CIA will be outlined, results given, and recorded examples of the speech being transcribed will be played to demonstrate state-of-the-art technology.


Dr. Frederick Jelinek is a professor in the Department of Electrical and Computer Engineering of the Johns Hopkins University, where he is also the Director of the Center for Language and Speech Processing. A graduate in electrical engineering from the Massachusetts Institute of Technology in 1962, he has taught at MIT, Harvard, and Cornell Universities, and was a visiting scientist at MIT Lincoln Laboratories. From 1968 to 1993 he worked at the IBM Watson Research Center at Yorktown Heights, NY, and headed the large Continuous Speech Recognition group for more than 20 years. His special interest is language modeling (prediction of future words given preceding text or speech) but he is also involved in methods of automatic parsing, text understanding, machine translation, statistical methods of natural language processing, and information theory and coding. Dr. Jelinek is a fellow of the IEEE and has authored numerous articles and book chapters. He was named one of the top 100 innovators in speech recognition by Technology Magazine in 1981.

Engineering Colloquium home page: