Two-Stage Speaker Adaptation of Hybrid Tied-Posterior Acoustic Models.

Jan Stadermann Gerhard Rigoll

Published in: ICASSP (1) (2005)

Keyphrases

speech recognition
speaker adaptation
acoustic models
speaker independent
speech recognizer
automatic speech recognition
hidden markov models
speaker identification
language model
pattern recognition
speech signal
digit recognition
probability distribution
posterior probability
broadcast news
hand written