Shift-tolerant K-subspaces for phoneme recognition.

Duanpei Wu John N. Gowdy

Published in: ICASSP (1996)

Keyphrases

phoneme recognition
hidden markov models
speaker dependent
high dimensional data
speech recognition
automatic speech recognition
audio signal
high dimensional
low dimensional
feature space
neural network
data points
principal component analysis
multi modal
speaker identification
video analysis
video sequences