19 Nov 1999
Sphinx Speech Group, CMU-SCS (rkm@cs.cmu.edu)
Single Word Recognition
·Search all words in parallel
·Initialize start state of every word with path-score 1.0
·For each frame of input speech:
·Update path scores within each HMM
·Propagate exit state score from one HMM to initial state of its successor (using Viterbi criterion)
·Select word with best exit state path-score
UW
ONE
TWO
THREE
T
AH
W
N
R
TH
IY