Non-negative matrix factorization based noise reduction for noise robust automatic speech recognition

Authors:
Seon Man Kim;Ji Hun Park;Hong Kook Kim;Sung Joo Lee;Yun Keun Lee
Affiliations:
School of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, Korea;School of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, Korea;School of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, Korea;Speech/Language Information Research Center, Electronics and Telecommunications Research Institute, Daejeon, Korea;Speech/Language Information Research Center, Electronics and Telecommunications Research Institute, Daejeon, Korea
Venue:
LVA/ICA'12 Proceedings of the 10th international conference on Latent Variable Analysis and Signal Separation
Year:
2012

Citing 2
Cited 0

Tracking speech-presence uncertainty to improve speech enhancement in non-stationary noise environments

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a noise reduction method based on non-negative matrix factorization (NMF) for noise-robust automatic speech recognition (ASR). Most noise reduction methods applied to ASR front-ends have been developed for suppressing background noise that is assumed to be stationary rather than non-stationary. Instead, the proposed method attenuates non-target noise by a hybrid approach that combines a Wiener filtering and an NMF technique. This is motivated by the fact that Wiener filtering and NMF are suitable for reduction of stationary and non-stationary noise, respectively. It is shown from ASR experiments that an ASR system employing the proposed approach improves the average word error rate by 11.9%, 22.4%, and 5.2%, compared to systems employing the two-stage mel-warped Wiener filter, the minimum mean square error log-spectral amplitude estimator, and NMF with a Wiener post-filter, respectively.