-
17EARSHOT: A Minimal Neural Network Model of Incremental Human Speech RecognitionCognitive Science 44 (4). 2020.Despite the lack of invariance problem (the many‐to‐many mapping between acoustics and percepts), human listeners experience phonetic constancy and typically perceive what a speaker intends. Most models of human speech recognition (HSR) have side‐stepped this problem, working with abstract, idealized inputs and deferring the challenge of working with real speech. In contrast, carefully engineered deep learning networks allow robust, real‐world automatic speech recognition (ASR). However, the com…Read more
-
Watching spoken language perception: Using eye-movements to track lexical access. In G. W. Cottrell (Ed.)In Garrison W. Cottrell (ed.), Proceedings of the Eighteenth Annual Conference of the Cognitive Science Society, Lawrence Erlbaum. 1996.
-
Brown UniversityResearcher
Providence, Rhode Island, United States of America