G - Physics – 06 – N
Patent
G - Physics
06
N
G06N 3/04 (2006.01) G10L 15/16 (2006.01)
Patent
CA 2066952
A speech recognition method according to the present invention uses distances calculated through a variance weighting process using covariance matrixes as the local distances (prediction residuals) between the feature vectors of input syllables/sound elements and predicted vectors formed by different statuses of reference neural prediction models (NPM's) using finite status transition networks. The category to minimize the accumulated value of these local distances along the status transitions of all the prediction models is figured out by dynamic programming, and used as the recognition output. Learning of the reference predic- tion models used in this recognition method is accomplished by repeating said distance calculating process and the pro- cess to correct the parameters of the different statuses and the covariance matrixes of said prediction models in the direction of reducing the distance between the learning patterns whose category is known and the prediction models of the same category as this known category, and what have satisfied prescribed conditions of convergence through these calculating and correcting processes are determined as re- ference pattern models.
Corporation Nec
Smart & Biggar
LandOfFree
Speech recognition by neural network adapted to reference... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speech recognition by neural network adapted to reference..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition by neural network adapted to reference... will most certainly appreciate the feedback.
Profile ID: LFCA-PAI-O-1436665