Psycholinguistic approaches to speech recognition in adverse conditions
8-10 March 2010; University of Bristol, UK.http://language.psy.bris.ac.uk/workshop/index.html
Speech recognition in ‘adverse conditions’ has been a familiar area of research in computer science, engineering, and hearing sciences for several decades. In contrast, most psycholinguistic theories of speech recognition are built upon evidence gathered from tasks performed by healthy listeners on carefully recorded speech, in a quiet environment, and under conditions of undivided attention. The aim of this workshop is to gather academics from various fields in order to discuss the benefits, prospects, and limitations of considering adverse conditions in models of speech recognition. The adverse conditions we will consider include extrinsic signal distortions (e.g., speech in noise, vocoded speech), intrinsic distortions (e.g., accented speech, conversational speech, dysarthric speech, Lombard speech), listener-specific limitations (e.g., non-native listeners, older individuals), and cognitive load (e.g., speech recognition under an attentional or memory load, multi-tasking).
