Label Driven Time-Frequency Masking for Robust Continuous Speech Recognition.

Meet H. Soni Ashish Panda

Published in: INTERSPEECH (2019)

Keyphrases

continuous speech recognition
wavelet transform
data driven
frequency domain
robust estimation
artificial intelligence
real time
computer vision
feature selection
image segmentation
bayesian networks
pairwise
multiresolution
supervised learning
signal processing
computationally efficient