Mitigating Domain Dependency for Improved Speech Enhancement Via SNR Loss Boosting.

Lili Yin Di Wu Zhibin Qiu Hao Huang

Published in: ICASSP (2023)

Keyphrases

speech enhancement
signal to noise ratio
noise reduction
noisy environments
single channel
speech signal
linear prediction
edge preserving
wiener filter
multi channel
feature vectors
additive noise
smoothing algorithm
speech recognition
frequency domain
language model
background noise
high resolution
prior knowledge