C. Kirst, F. Weninger, C. Joder, P. Grosche, J. Geiger, and B. Schuller, “On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise,” in Proc. AES Conference: 53rd International Conference: Semantic Audio, Jan. 2014, pp. 4-2:1-7. [Online]. Available: https://aes.org/publications/elibrary-page/?id=17090
Kirst C, Weninger F, Joder C, Grosche P, Geiger J, Schuller B. On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise. In: AES Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society; 2014.pp. 4-2:1-7. Available from: https://aes.org/publications/elibrary-page/?id=17090
@inproceedings{Kirst2014_17090,
author = {Kirst, Christian and Weninger, Felix and Joder, Cyril and Grosche, Peter and Geiger, Jürgen and Schuller, Björn},
title = {{On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise}},
booktitle = {AES Conference: 53rd International Conference: Semantic Audio},
pages = {4-2:1-7},
url = {https://aes.org/publications/elibrary-page/?id=17090},
year = {2014},
month = jan,
publisher = {Audio Engineering Society}
}
TY - CPAPER
TI - On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise
AU - Kirst, Christian
AU - Weninger, Felix
AU - Joder, Cyril
AU - Grosche, Peter
AU - Geiger, Jürgen
AU - Schuller, Björn
T2 - AES Conference: 53rd International Conference: Semantic Audio
SP - 1
EP - 7
M1 - Paper 4-2
PY - 2014
DA - 2014/01/06
UR - https://aes.org/publications/elibrary-page/?id=17090
PB - Audio Engineering Society
LA - en
AB - Speech de-noising algorithms often suffer from introduction of artifacts, either by removal of parts of the speech signal, or imperfect noise reduction causing the remaining noise to sound unnatural and disturbing. This contribution proposes to spatially distribute monaural noisy speech signals based on single-channel source separation, in order to improve the perceived speech quality. Stereo up-mixing is utilized on the estimated speech and noise sources instead of simply suppressing the noise. This paper investigates the case of non-negative matrix factorization (NMF) speech enhancement applied to high levels of non-stationary noise. NMF-based and spectral subtraction speech enhancement algorithms are evaluated in a listening test in terms of speech intelligibility, presence of interfering noises and overall quality with respect to the unprocessed signal. In the result, the listening test provides evidence for superior noise reduction by NMF, yet also a drop in perceived speech quality that is not covered by the employed set of common objective metrics. However, stereo up-mixing of NMF-separated speech and noise delivers high subjective noise reduction while preserving the perceived speech quality.
ER -