Speech Processing
525.747

Course Description
The course emphasizes processing of the human speech waveform, primarily using digital techniques. Theory of speech production as related to signal models in time and frequency domains is covered, as well as the measurement of model parameters, short-time Fourier spectrum, and linear predictor coefficients. Speech coding, recognition and synthesis, and speaker recognition are also included. Some consideration is given to speech processing hardware. Software projects are required.

Prerequisites
525.427 Digital Signal Processing and 525.414   Probability and Stochastic Processes for Engineers. Background in linear algebra and Matlab is helpful.

Instructor
Joe Campbell received a B.S.E.E. from Rensselaer Polytechnic Institute in 1979, an M.S.E.E. from The Johns Hopkins University in 1986, and a Ph.D. in EE from Oklahoma State University in 1992. Dr. Campbell has been employed by the Department of Defense since 1979. From 1979 to 1990, he worked in the Narrowband Secure Voice Technology research group. His team developed LPC-10e, which enhanced the Federal Standard 1015 voice coder. He led the U.S. Government's speech coding team in the development of the CELP voice coder that became Federal Standard 1016. Since 1991, he has been with the Biometric Authentication Technology research group where he's pursuing voice verification.

He currently chairs the Biometric Consortium and is a frequent session chairman at the IEEE International Conferences on Acoustics, Speech, and Signal Processing; is a charter associate editor for the IEEE Transactions on Speech and Audio Processing; teaches speech processing at the Johns Hopkins University; chairs the Ilchester PTA Technology Committee; and is a member of Sigma Xi.

E-mail the instructor.

Computer Lab Requirements
The required software projects may be done in the computer lab (e.g., at Dorsey Center), however, most students prefer using the Student Edition of Matlab on their home computer or at their employer's facilities.

Textbook
Discrete-Time Processing of Speech Signals by Deller, Proakis, and Hansen

Return to Electrical Engineering Courses | Electrical Engineering | Part-Time Engineering

updated September 1997