Coordinated training of noise removing networks

Seung Hwan Moon, Jenq–Neng Hwang

Abstract

When a recognition system designed with a noise-free speech signal is deployed in the real world, it experiences severe degradation due to environmental acoustic ambient noise. An enhancement technique based on a noise removing network (NRN) which has recurrent connections is proposed. This NRN is trained in coordination with a time delay neural network (TDNN) which has been trained for noise-free speech recognition tasks. The proposed enhancement technique has favorable performance for white/colored Gaussian noisy speech when compared with the NRN without coordinated training and the classical linear Wiener filtering methods.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>
BibTeX
@inproceedings{moon1993coordinated,
  author = {Seung Hwan Moon and Jenq–Neng Hwang},
  title = {{Coordinated training of noise removing networks}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1993},
}

Loading related content...

Figure