Speech Recognition

The objective of this project is to recognize speech signals and to understand simple sentences through learning. The first phase of the project uses our SHOSLIF framwork. The second phase uses SAIL.


J. Weng, Y. B. Lee and C. H. Evans, ``The developmental approach to multimedia speech learning,'' in Proc. IEEE Int'l Conf. on Acoustics, Speech, and Signal Processing, Phoenix, Arizona, vol. 6, pp. 3093 - 3096, March 15 - 19, 1999. Download PDF file.
J. Weng, ``SHOSLIF: A framework for sensor-based learning for high-dimensional complex systems,'' invited paper in Proc. IEEE Workshop on Architectures for Semiotic Modeling and situation analysis in Large Complex Systems, Monterey, CA, Aug. 27-29, 1995.
J. Brotherton and J. Weng, HEARME: Speaker Independent Word Recognition Using SHOSLIF, MSU-CPS-96-33, Department of Computer Science, Michigan State University, East Lansing, Michigan, October, 1996.
 Back To Weng's Home Page: http://web.cps.msu.edu/~weng/