AES E-Library

G. Tauboeck, S. Rajbamshi, and P. Balazs, "Sparse Audio Inpainting: A Dictionary Learning Technique to Improve Its Performance," Paper 10402, (2020 October.). doi: G. Tauboeck, S. Rajbamshi, and P. Balazs, "Sparse Audio Inpainting: A Dictionary Learning Technique to Improve Its Performance," Paper 10402, (2020 October.). doi:
Abstract: The objective of audio inpainting is to fill a gap in a signal, either to be meaningful or even to reconstruct the original signal. We propose a novel approach applying sparse modeling in the time-frequency (TF) domain. In particular, we develop a dictionary learning technique which deforms a given Gabor frame such that the sparsity of the analysis coefficients of the resulting frame is maximized. A suitable modification of the SParse Audio Inpainter (SPAIN) allows to exploit the obtained sparsity gain and, hence, to benefit from the learned dictionary. Our experiments demonstrate that our methods outperforms several state-of-the-art audio inpainting techniques in terms of signal-to-noise ratio (SNR) and objective difference grade (ODG).

@article{tauboeck2020sparse,
author={tauboeck, georg and rajbamshi, shristi and balazs, peter},
journal={journal of the audio engineering society},
title={sparse audio inpainting: a dictionary learning technique to improve its performance},
year={2020},
volume={},
number={},
pages={},
doi={},
month={october},} @article{tauboeck2020sparse,
author={tauboeck, georg and rajbamshi, shristi and balazs, peter},
journal={journal of the audio engineering society},
title={sparse audio inpainting: a dictionary learning technique to improve its performance},
year={2020},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={the objective of audio inpainting is to fill a gap in a signal, either to be meaningful or even to reconstruct the original signal. we propose a novel approach applying sparse modeling in the time-frequency (tf) domain. in particular, we develop a dictionary learning technique which deforms a given gabor frame such that the sparsity of the analysis coefficients of the resulting frame is maximized. a suitable modification of the sparse audio inpainter (spain) allows to exploit the obtained sparsity gain and, hence, to benefit from the learned dictionary. our experiments demonstrate that our methods outperforms several state-of-the-art audio inpainting techniques in terms of signal-to-noise ratio (snr) and objective difference grade (odg).},}

TY - paper
TI - Sparse Audio Inpainting: A Dictionary Learning Technique to Improve Its Performance
SP - EP -
AU - Tauboeck, Georg
AU - Rajbamshi, Shristi
AU - Balazs, Peter
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2020 TY - paper
TI - Sparse Audio Inpainting: A Dictionary Learning Technique to Improve Its Performance
SP - EP -
AU - Tauboeck, Georg
AU - Rajbamshi, Shristi
AU - Balazs, Peter
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2020
AB - The objective of audio inpainting is to fill a gap in a signal, either to be meaningful or even to reconstruct the original signal. We propose a novel approach applying sparse modeling in the time-frequency (TF) domain. In particular, we develop a dictionary learning technique which deforms a given Gabor frame such that the sparsity of the analysis coefficients of the resulting frame is maximized. A suitable modification of the SParse Audio Inpainter (SPAIN) allows to exploit the obtained sparsity gain and, hence, to benefit from the learned dictionary. Our experiments demonstrate that our methods outperforms several state-of-the-art audio inpainting techniques in terms of signal-to-noise ratio (SNR) and objective difference grade (ODG).