Automatic phoneme recognition with Segmental Hidden Markov Models.

Areg G. Baghdasaryan A. A. (Louis) Beex

Published in: ACSCC (2011)

Keyphrases

hidden markov models
phoneme recognition
speech recognition
markov models
sequential data
multiscale
conditional random fields
automatic speech recognition
hidden state
visual speech recognition
hidden states
information retrieval
motion estimation
speaker dependent