Sciweavers

ICCHP
2010
Springer

CanSpeak: A Customizable Speech Interface for People with Dysarthric Speech

13 years 9 months ago
CanSpeak: A Customizable Speech Interface for People with Dysarthric Speech
Current Automatic Speech Recognition (ASR) systems designed to recognize dysarthric speech require an investment in training that involves considerable effort and must be repeated if speech patterns change. We present CanSpeak, a customizable speech recognition interface that does not require automatic training and uses a list of keywords customized for each user. We conducted a preliminary user study with four subjects with dysarthric speech. Customizing the keyword lists doubled the accuracy rate of the system for two of the subjects whose parents and caregivers participated in the customizing task. For the other two subjects only small improvements were observed.
Foad Hamidi, Melanie Baljko, Nigel Livingston, Leo
Added 26 Jan 2011
Updated 26 Jan 2011
Type Journal
Year 2010
Where ICCHP
Authors Foad Hamidi, Melanie Baljko, Nigel Livingston, Leo Spalteholz
Comments (0)