Learning Noise-Invariant Representations for Robust Speech Recognition.

Davis Liang Zhiheng Huang Zachary C. Lipton

Published in: SLT (2018)

Keyphrases

speech recognition
noisy environments
invariant representations
hidden markov models
pattern recognition
speech synthesis
speech recognizer
image sequences
language model
noise reduction
image processing
low level
video sequences
speech signal
speech recognition systems