Audio visual speech recognition

Kenneth H. Davis; R. E. Folsom; F. Ivy Carroll; Phillip C. Cooley; Lyle M. Retzlaff; Michael F. Weeks; H. Koo; Herbert H. Seltzman; E. Pellizzari; Deborah W. McFadden; Roger D. Austin; Martin B. Lee; Judith T. Lynch; Debra M. Fleischmann; Carol Place; Stephen D. Cooper; Rick L. Williams; Lillie B. Barber; Doris J. Rouse; Ivey A. McDaniel; Charlotte O. Scheper; Paul Kizakevich; Donna M. Jewell; Marion E. Deerhake; Cora B. Parker; Eugene P. Brantly; Phyllis D. Elkins; Patricia A. Cunningham; Robert S. Truesdale; Sara C. Wheeless; Robert M. Bray; Cynthia A. Salmons; Gary B. Howe; Coleen M. Northeim; Susan K. Myers; Gordon M. Cressman; Josephine A. Mauskopf; Tim J. Gabel; Luis Arturo Crouch; Celia D. Keller; Lisa E. Packer; Pamela B. Lamb; Keith White Little; Nathaniel F. Rodman; M. Owen; James P. Hayes; Daniel L. Winfield; Deborah A. Gibbs; Janice E. Kelly-Reid; Wayne G. Winstead; Cindy O. McClintock; Terrence K. Pierson; Johnny R. Albritton; Sherry L. Black; Jeffrey B. Coburn; Joe B. Simpson; Ed E. Rickman; James T. Hanley; R. Suresh; Barbara L. Kroner; K. Heller; James C. Blake; Barri B. Burrus; Anthony C. Clayton; Donna S. Womack; S. Mascarella; Scott A. Guthrie; Sheryl C. Cates; Albert D. Bethke; Suson F. VonLehmden; Kathryn L. Dowd; Daniel J. Pratt; Lisa J. McQuay; Matthew A. Koch; Jonathan T. Ennis; Robert A. Zerbonia; Nick L. Kinsey; Susan H. Kinsey; Christopher P. Carson; J. Newsome; S. Keesling; James A. O'Rourke; Kathryn R. Batts; Craig R. Hollingsworth; Priya Suresh; Joseph Wendell Wilson; Vorapranee Wickelgren; E. Andrew Jessup; Diana S. Goss; Sheri E. Fehnel; Gayle S. Bieler; Donna P. Coleman; R. Crawford; Jeanne Ann Snodgrass; Nellie I. Hansen; Michelle Lang; Deirdre M. Mladsi; Gary A. Zarkin; Rachel A. Caspar; Carol L. Woodell; R Beadles

Audio visual speech recognition

Beadles, R. (1988). Audio visual speech recognition. (U.S. Patent No. 4757541). http://patft.uspto.gov/netacgi/nph-Parser?patentnumber=4757541

Copy citation

Abstract

A method and apparatus for indicating at least some of a sequence of spoken phonemes in which detected sounds are analyzed to determine a group of phonemes to which a phoneme belongs, the lipshape is optically detected and the respective signals correlated by a computer to indicate the detected phoneme.