Pronunciation variation in ASR: which variation to model?

Mirjam Wester Judith M. Kessens Helmer Strik

Published in: INTERSPEECH (2000)

Keyphrases

computational model
video sequences
theoretical analysis
mathematical model
experimental data
sensitivity analysis
language learning
formal model
information systems
high level
face recognition
pattern recognition
probabilistic model
statistical model
bayesian framework
noisy environments