Communication strategies for a computerized caregiver for individuals with Alzheimer's disease

Authors:
Frank Rudzicz;Rozanne Wilson;Alex Mihailidis;Elizabeth Rochon;Carol Leonard
Affiliations:
University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada;University of Ottawa, Ottawa, Canada
Venue:
SLPAT '12 Proceedings of the Third Workshop on Speech and Language Processing for Assistive Technologies
Year:
2012

Citing 4
Cited 0

WordNet: a lexical database for English

Communications of the ACM
A data-driven approach to optimizing spectral speech enhancement methods for various error criteria

Speech Communication
Benefits of social intelligence in home dialogue systems

INTERACT'05 Proceedings of the 2005 IFIP TC13 international conference on Human-Computer Interaction
Cepstrum-Domain Model Combination Based on Decomposition of Speech and Noise Using MMSE-LSA for ASR in Noisy Environments

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Currently, health care costs associated with aging at home can be prohibitive if individuals require continual or periodic supervision or assistance because of Alzheimer's disease. These costs, normally associated with human caregivers, can be mitigated to some extent given automated systems that mimic some of their functions. In this paper, we present inaugural work towards producing a generic automated system that assists individuals with Alzheimer's to complete daily tasks using verbal communication. Here, we show how to improve rates of correct speech recognition by preprocessing acoustic noise and by modifying the vocabulary according to the task. We conclude by outlining current directions of research including specialized grammars and automatic detection of confusion.