Cepstrum-domain model combination based on decomposition of speech and noise for noisy speech recognition.

Hong Kook Kim Richard C. Rose

Published in: ICASSP (2002)

Keyphrases

speech recognition
noisy environments
noisy speech
hidden markov models
automatic speech recognition
probabilistic model
language model
speech processing
speaker identification
recognition engine
pattern recognition
feature vectors
speech synthesis
speech recognizer