Pandaemonium Architecture 6.0

In this course

Frederick Jelinek was a foundational figure in statistical speech recognition, pioneering the maximum likelihood decoding framework that transformed speech processing from rule-based to probabilistic methods. His work with colleagues at IBM established the mathematical foundations for treating speech recognition as a channel coding problem, enabling the shift toward data-driven machine learning approaches that underpin modern AI speech systems. In this course's context, Jelinek's contributions exemplify how information theory and statistical modeling become the conceptual bedrock for systems that learn patterns from data rather than following explicit linguistic rules.

Mentioned in 1 reading

Robert Mercer et al.

A Maximum Likelihood Approach to Continuous Speech Recognition

4

A Maximum Likelihood Approach to Continuous Speech Recognition LALIT R. BAHL, MEMBER, IEEE, FREDERICK JELINEK, FELLOW, IEEE, AND ROBERT L. MERCER Abstract—Speech recognition is formulated as a problem of maximum likelihood decoding. This …[3] L. R. Bahl, R. Bakis, P. S. Cohen, A. G. Cole, F. Jelinek, B. L. Lewis, and R. L. Mercer, "Recognition results with several acoustic processors," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Washington, DC, Apr. 1979, pp…[14] L. R. Bahl and F. Jelinek, "Decoding for channels with insertions, deletions, and substitutions with applications to speech recognition," IEEE Trans. Inform. Theory, vol. IT-21, pp. 404-411, July 1975. [15] F. Jelinek and R. L. Mercer…

+1 more

Appears alongside

People mentioned in the same passages — sorted by co-occurrence weight.