Two-step noise reduction based on soft mask for robust speaker identification.

Gennadiy Tupitsin Artem Topnikov Andrey Priorov

Published in: FRUCT (2016)

Keyphrases

noise reduction
noisy environments
speaker identification
edge preserving
signal to noise ratio
edge detection
speech enhancement
median filter
noise level
speech recognition
edge enhancement
feature extraction
multiresolution
information retrieval
image processing
text mining