On the Robustness of Deep Learning-Based Speech Enhancement.

Amit S. Chhetri Philip Hilmes Mrudula Athi Nikhil Shankar

Published in: ICMLA (2022)

Keyphrases

deep learning
speech enhancement
noisy environments
noise reduction
unsupervised learning
signal to noise ratio
machine learning
linear prediction
speech signal
weakly supervised
single channel
mental models
higher order
vocal tract
wiener filter
maximum likelihood
background noise
high dimensional