Towards personalized speech synthesis for augmentative and alternative communication

TitleTowards personalized speech synthesis for augmentative and alternative communication
Publication TypeJournal Article
Year of Publication2014
AuthorsMills, T., Bunnell H. T., & Patel R.
JournalAugmentative and alternative communication (Baltimore, Md. : 1985)
Volume30
Issue3
Pagination226-36
Date Published2014 Sep
ISSN1477-3848
KeywordsAssistive communication; Assistive technology; Communication Aids for Disabled; Dysarthria; Humans; Speaker identity; Speech synthesis; Voice; Voice conversion
Abstract

Text-to-speech options on augmentative and alternative communication (AAC) devices are limited. Often, several individuals in a group setting use the same synthetic voice. This lack of customization may limit technology adoption and social integration. This paper describes our efforts to generate personalized synthesis for users with profoundly limited speech motor control. Existing voice banking and voice conversion techniques rely on recordings of clearly articulated speech from the target talker, which cannot be obtained from this population. Our VocaliD approach extracts prosodic properties from the target talker's source function and applies these features to a surrogate talker's database, generating a synthetic voice with the vocal identity of the target talker and the clarity of the surrogate talker. Promising intelligibility results suggest areas of further development for improved personalization.

DOI10.3109/07434618.2014.924026
Alternate JournalAugment Altern Commun
Refereed DesignationRefereed