AES E-Library

B. Cauchi, T. Gerkmann, S. Doclo, PA. A.. Naylor, and S. Goetze, "Spectrally and Spatially Informed Noise Suppression Using Beamforming and Convolutive NMF," Paper 4-1, (2016 January.). doi: B. Cauchi, T. Gerkmann, S. Doclo, PA. A.. Naylor, and S. Goetze, "Spectrally and Spatially Informed Noise Suppression Using Beamforming and Convolutive NMF," Paper 4-1, (2016 January.). doi:
Abstract: Speech enhancement in low SNR conditions or in presence of large amount of reverberation is a challenging task. However, in some applications, prior information about the interfering noise source is available and can be exploited to tackle this issue. We propose to combine a beamformer with convolutive NMF in order to estimate the PSDs of the target speech signal and of the noise to be suppressed by exploiting knowledge of the noise source location and about its spectral content. We apply the proposed system to ego-noise suppression for a robotic platform. Simulations show that the spectral information exploited using convolutive NMF is beneficial to the noise reduction performance when compared to methods based on blind estimation but that estimating the noise PSD from the output of the beamformer is beneficial mostly when no prior knowledge of the noise spectral content is available.

@article{cauchi2016spectrally,
author={cauchi, benjamin and gerkmann, timo and doclo, simon and naylor, patrick a. and goetze, stefan},
journal={journal of the audio engineering society},
title={spectrally and spatially informed noise suppression using beamforming and convolutive nmf},
year={2016},
volume={},
number={},
pages={},
doi={},
month={january},} @article{cauchi2016spectrally,
author={cauchi, benjamin and gerkmann, timo and doclo, simon and naylor, patrick a. and goetze, stefan},
journal={journal of the audio engineering society},
title={spectrally and spatially informed noise suppression using beamforming and convolutive nmf},
year={2016},
volume={},
number={},
pages={},
doi={},
month={january},
abstract={speech enhancement in low snr conditions or in presence of large amount of reverberation is a challenging task. however, in some applications, prior information about the interfering noise source is available and can be exploited to tackle this issue. we propose to combine a beamformer with convolutive nmf in order to estimate the psds of the target speech signal and of the noise to be suppressed by exploiting knowledge of the noise source location and about its spectral content. we apply the proposed system to ego-noise suppression for a robotic platform. simulations show that the spectral information exploited using convolutive nmf is beneficial to the noise reduction performance when compared to methods based on blind estimation but that estimating the noise psd from the output of the beamformer is beneficial mostly when no prior knowledge of the noise spectral content is available.},}

TY - paper
TI - Spectrally and Spatially Informed Noise Suppression Using Beamforming and Convolutive NMF
SP - EP -
AU - Cauchi, Benjamin
AU - Gerkmann, Timo
AU - Doclo, Simon
AU - Naylor, Patrick A.
AU - Goetze, Stefan
PY - 2016
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - January 2016 TY - paper
TI - Spectrally and Spatially Informed Noise Suppression Using Beamforming and Convolutive NMF
SP - EP -
AU - Cauchi, Benjamin
AU - Gerkmann, Timo
AU - Doclo, Simon
AU - Naylor, Patrick A.
AU - Goetze, Stefan
PY - 2016
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - January 2016
AB - Speech enhancement in low SNR conditions or in presence of large amount of reverberation is a challenging task. However, in some applications, prior information about the interfering noise source is available and can be exploited to tackle this issue. We propose to combine a beamformer with convolutive NMF in order to estimate the PSDs of the target speech signal and of the noise to be suppressed by exploiting knowledge of the noise source location and about its spectral content. We apply the proposed system to ego-noise suppression for a robotic platform. Simulations show that the spectral information exploited using convolutive NMF is beneficial to the noise reduction performance when compared to methods based on blind estimation but that estimating the noise PSD from the output of the beamformer is beneficial mostly when no prior knowledge of the noise spectral content is available.