IEEE Home | Shop IEEE | Join IEEE | myIEEE | Contact IEEE | IEEEXplore

IEEE Signal Processing Society (SP)
Baltimore Chapter

SP Home   |   IEEE Home   |   IEEE Baltimore   |   Join SP   |   Contact SP
SP Main Menu

Meeting Number:   9

May 22, 2007


Recognize Speech v/s Wreck a Nice Beach: The Mathematics of Automatic Speech Recognition


Dr. Sanjeev Khudanpur
Johns Hopkins University


Tuesday, May 22, 2007


5:45 PM:   Snacks
6:00 PM:   Talk begins


Historical Electronics Museum (HEM)
1745 W. Nursery Road, Linthicum, MD 21090

Please Respond To

Please respond to if you are planning to attend this meeting. Also, let me know if you will be joining us afterwards at Ruby Tuesdays for dinner so I can make reservations. Again, only the speaker’s dinner is paid for. The rest of us need to pay our own way.


From Star Trek to Star Wars and through much of science fiction, seamlessness is a recurrent theme in human computer interfaces -- communicating with machines the way we communicate with other human beings. Thanks to advances in the last twenty five years, this vision is closer to reality than one may suspect. Yet, we are not around the corner from a day when an automated agent participates at a conference table by taking notes and digging out facts from a database in response to spoken cues. This talk focuses on the speech recognition aspect of human computer interaction.

This introductory presentation will begin with an overview of the evolution and the state of the art in automatic speech recognition. It will then illustrate the application of statistical modeling, optimization techniques and abstract algebra in transforming what was perceived as a pipe dream in the early seventies into a dictation system available today on a personal computer for $99 plus taxes. Classification and regression trees, hidden Markov models, multivariate Gaussian distributions, nonparametric estimation and finite state automata theory are but a few of the keystones in this ongoing march to success.

While it is only a matter of time before products employing speech recognition will be ubiquitous as the telephone, several challenging problems remain in this field. This presentation will also serve to familiarize the audience with current problems in automatic speech recognition.

Click on the following link for the presentation.

      The Mathematics of Automatic Speech Recognition


Sanjeev Khudanpur received a B.Tech. degree in Electrical Engineering from the Indian Institute of Technology, Bombay, in 1988, and a Ph.D. from the Department of Electrical and Computer Engineering, University of Maryland, College Park, in 1997. He then joined the faculty of the Johns Hopkins University, serving until June 2001 as Associate Research Scientist in the Center for Language and Speech Processing and, since then, as Assistant Professor in the Department of Electrical and Computer Engineering and the Department of Computer Science. His research interests are in the application of information theoretic methods to human language technologies such as automatic speech recognition, machine translation and natural language processing. All these technologies make heavy use of statistical models of human language.

SP Home   |    IEEE Home   |    IEEE Baltimore   |    Privacy & Security   |    Terms & Conditions