Abstract
A system has been constructed for articulatory recognition in question–answer utterances such as ‘‘Is it five five nine pine street? No its five NINE nine pine street’’ [J. Westbury and O. Fujimura, J. Acoust. Soc. Am. Suppl. 1 85, S98 (1989)]. This system takes as input microbeam pellet movement data currently from five speakers. It uses an abductive problem solving strategy [J. Josephson, AAAI Spring Symposium Series: Automated Abduction, 140–144 (1990)], first hypothesizing gestures (e.g., labial and apical closure for consonantal identification, dorsal motion for syllable nuclei, mandible movement for emphasis) in examining the pellet data, and then explaining these gestures in terms of possible word and emphasis hypotheses. Uncertainties in gesture identification are handled by including noise hypotheses. Pellet position thresholds used for identifying gestures vary depending upon the syllable’s position within an utterance. Initial results indicate a very high accuracy in inferring the correct words and emphasis without using acoustic signals.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
