A data-driven residual gain approach for two-stage speech enhancement.

Yu Gwang Jin Chul Min Lee Kiho Cho Nam Soo Kim

Published in: ICASSP (2011)

Keyphrases

data driven
speech enhancement
noise reduction
noisy environments
signal to noise ratio
single channel
linear prediction
speech signal
smoothing algorithm
speech recognition
wiener filter
multi channel
background noise
vocal tract
edge preserving
automatic speech recognition
image sequences