Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
2000-11-16
2004-04-27
Dorvil, Richemond (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S278000, C704S235000, C434S185000
Reexamination Certificate
active
06728680
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates generally to analysis of human speech and, in particular, to an improved method and apparatus for providing visual feedback relative to speech production.
2. Description of Related Art
Most people take human speech for granted. However, various speech impediments or physical deficiencies may impair an individual's abilities to produce what may be considered “normal” human speech. Speech pathologists are professionals who work with individuals who cannot speak in a normal manner. Typically, a speech pathologist will work with such an individual over a period of time to teach the individual how to more accurately produce desired sounds.
A speech pathologist encourages such an individual to concentrate on the articulators that produce acceptable speech. These articulators include the lips, teeth, the tongue, etc. Conventionally, a videotape player and a mirror are used to allow an individual to compare the individual's externally visible articulators with those of a model. However, a videotape player does not allow for easy replay of short speech production models. Furthermore, people may suffer from left-right confusions due to, for example, neurological damage, learning disabilities, and possible visual processing problems. Therefore, the comparison of a mirror image with a videotape reproduction may create confusion for such an individual.
Computers and computer software provide tools to improve the tasks of a speech professional. These software tools analyze an incoming speech sample with comparisons to a stored speech sample to determine whether a particular sound, such as a phoneme, has been made correctly. Once a model is created, an incoming sound may be compared to the model. If the incoming sound does not fit within the range of the model, the user is notified of the discrepancy.
However, the prior art speech and language analysis software tools provide feedback based only on acoustic information. Therefore, it would be advantageous to provide visual feedback of speech production and to associate a speech model with the articulators responsible for speech production.
SUMMARY OF THE INVENTION
The present invention collects video and audio samples of acceptable speech production. A camera focuses on a speaker's face and, particularly, articulation visible in the vicinity of the mouth, or other body movements associated with speech production. Video files are used to archive acceptable and unacceptable productions, as well as acceptable facial expressions that enhance communication. These files may then be used to provide feedback about acceptable and unacceptable ways to produce speech. The camera is also used to provide real-time feedback as a person is speaking for comparison with a stored model. A speaker may use video models in conjunction with acoustic models for comparison with a current attempt. Image processing may be used to create a mirror image of a video model or a current attempt or both to avoid left-right confusion.
REFERENCES:
patent: 5836770 (1998-11-01), Powers
patent: 6109923 (2000-08-01), Rothenberg
patent: 6151577 (2000-11-01), Braun
patent: 6293802 (2001-09-01), Ahlgren
patent: 6332147 (2001-12-01), Moran et al.
patent: 6336089 (2002-01-01), Everding
patent: 6397185 (2002-05-01), Komissarchik et al.
De Filippo et al., “Linking Visual and Kinesthetic Imagery in Lipreading Instruction,” Feb. 1995, Journal of Speech and Hearing Research, vol. 38, pp. 244-256.*
Jiang et al., “Visual speech analysis and synthesis with application to Mandarin speech training,” 1999, Proceedings of the ACM symposium on Virtural reality software and technology, pp. 111-115.
Aaron Joseph D.
Brunet Peter Thomas
Kjeldsen Frederik C. M.
Luther Paul S.
Mahaffey Robert Bruce
Dawkins Marilyn Smith
Dorvil Richemond
Harper V. Paul
Walder, Jr. Stephen J.
Yee Duke W.
LandOfFree
Method and apparatus for providing visual feedback of speed... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for providing visual feedback of speed..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for providing visual feedback of speed... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3254069