Constraints on theories of human vs. machine recognition of speech
Moore, R. K., & Cutler, A.
Constraints on theories of human vs. machine recognition of speech. In R. Smits, J. Kingston, T. Neary, & R. Zondervan (Eds.
), Proceedings of the workshop on Speech Recognition as Pattern Classification (SPRAAC)
(pp. 145-150). Nijmegen: Max Planck Institute for Psycholinguistics.
The central issues in the study of speech recognition by human listeners (HSR) and of automatic speech recognition (ASR) are clearly comparable; nevertheless the research communities that concern themselves with ASR and HSR are largely distinct. This paper compares the research objectives of the two fields, and attempts to draw informative lessons from one to the other.