2007 · 99 citations · 16 references
ComputingOtolaryngologyFeature EngineeringUltrasonographyUltrasoundSpeech AcousticsSpeech RecognitionVoice ProcessingAcoustic Feature ExtractionContour ModelingLaryngeal FeaturesNeural Network ModelingSpectral Analysis Of SpeechSpeech Corpus AnnotationVocal Tract Modeling
The article compares two approaches to the description of ultrasound vocal tract images for application in a "silent speech interface," one based on tongue contour modeling, and a second, global coding approach in which images are projected onto a feature space of Eigentongues. A curvature-based lip profile feature extraction method is also presented. Extracted visual features are input to a neural network which learns the relation between the vocal tract configuration and line spectrum frequencies (LSF) contained in a one-hour speech corpus. An examination of the quality of LSFs derived from the two approaches demonstrates that the Eigemongues approach has a more efficient implementation and provides superior results based on a normalized mean squared error criterion.
16
Robust Regression and Outlier Detection
Gregory F. Piepel, Peter J. Rousseeuw, Annick M. Leroy · Technometrics · 1989 · 6.2K citations
Mathematical Methods of Statistics.
R. C. Geary, H. Leslie Cramer · The Economic Journal · 1947 · 6K citations
Face recognition using eigenfaces
Matthew Turk, Alex Pentland · 2002 · 5.2K citations
Some informational aspects of visual perception.
Fred Attneave · Psychological Review · 1954 · 2.9K citations