Wednesday, 14 November 2012
Building personalised synthetic voices for individuals with severe speech impairment
Sarah Creer and Stuart Cunningham from the RAT group (and colleagues Phil Green and Junichi Yamagishi) have recently had a paper published in Computer Speech and Language: special issue on Speech and Language Processing for Assistive Technologies.
Entitled "Building personalised synthetic voices for individuals with severe speech impairment" the article examines the use of voice output communication aids (or VOCA) to support spoken communication needs. The type and number of synthetic voices that can be accessed with a VOCA is often limited and this has been implicated as a factor for rejection of the devices. This paper reports on recent advances in speech synthesis to produce personalised synthetic voices for 3 speakers with mild to severe dysarthria, one of the most common speech disorders. The evaluation showed that for one of the 3 speakers a voice could be created which conveyed many of his personal characteristics, such as regional identity, sex and age.