DMCA
Score guided audio restoration via generalised coupled tensor factorization (2012)
| Citations: | 5 - 1 self |
BibTeX
@MISC{Yılmaz12scoreguided,
author = {Y. Kenan Yılmaz and A. Taylan Cemgil and et al.},
title = {Score guided audio restoration via generalised coupled tensor factorization},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Generalised coupled tensor factorisation is a recently proposed algorithmic framework for simultaneously estimating tensor factorisation models where several observed tensors can share a set of latent factors. This paper proposes a model in this framework for coupled factorisation of piano spectrograms and piano roll representations to solve audio interpolation and restoration problem. The model incorporates temporal and harmonic information from an approximate musical score (not necessarily belonging to the played piece), and spectral information from isolated piano sounds. The performance of the proposed approach is evaluated on the restoration of classical music pieces where we get about 5dB SNR improvement when50 % of data frames are missing.
Keyphrases
spectral information approximate musical score harmonic information restoration problem audio interpolation coupled factorisation tensor factorisation model index term audio restoration classical music piece piano roll representation isolated piano sound several observed tensor piano spectrogram latent factor algorithmic framework snr improvement when50 data frame tensor factorisation coupled tensor factorisation
