Improved phone posterior estimation through k-NN and MLP-based similarity

B Picart - 2009 - infoscience.epfl.ch
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - core.ac.uk
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - Citeseer
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - publications.idiap.ch
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - infoscience.epfl.ch
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - publidiap.idiap.ch
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …

[PDF][PDF] TROPE

ET K-NN - publications.idiap.ch
In this work, we investigate the possible use of k-nearest neighbour (kNN) classifiers to
perform frame-based acoustic phonetic classification, hence replacing Gaussian Mixture …