Text-informed speech enhancement with deep neural networks.

Keisuke Kinoshita Marc Delcroix Atsunori Ogawa Tomohiro Nakatani

Published in: INTERSPEECH (2015)

Keyphrases

neural network
speech enhancement
noisy environments
noise reduction
information retrieval
single channel
signal to noise ratio
pattern recognition
speech signal
image segmentation
linear prediction
background noise
vocal tract
low contrast
image processing
smoothing algorithm
computer vision