Login / Signup
Temporal contrast normalization and edge-preserved smoothing on temporal modulation structure for robust speech recognition.
Xugang Lu
Shigeki Matsuda
Masashi Unoki
Tohru Shimizu
Satoshi Nakamura
Published in:
ICASSP (2009)
Keyphrases
</>
speech recognition
hidden markov models
language model
noisy environments
speech understanding
pattern recognition
speech processing
computer vision
edge detection
automatic speech recognition
speech recognizer
speech recognition systems
neural network
image processing
speech signal
speech synthesis