Speech Feature Smoothing for Robust ASR.

Chia-Ping Chen Jeff A. Bilmes Daniel P. W. Ellis

Published in: ICASSP (1) (2005)

Keyphrases

automatic speech recognition
speech recognition
noisy environments
speech signal
feature vectors
speech synthesis
spontaneous speech
image features
language model
preprocessing step
word error rate
speech retrieval
data sets
conversational speech
robust statistical
hidden markov models
neural network