Audio Quality Assessment of Vinyl Music Collections Using Self-Supervised Learning
Alessandro Ragano, Emmanouil Benetos, Andrew Hines
Abstract
Metadata such as mean opinion score (MOS) quality ratings are critical to improve the usability and accessibility of music archive collections. Developing a non-intrusive objective quality metric that predicts MOS of archive music collections is challenging, since it requires labeling large datasets made of real-world recordings, which currently do not exist for this task. In this paper, we show that the self-supervised learning (SSL) model wav2vec 2.0 can be successfully used to predict the perceived audio quality of archive music collections. Using vinyl recordings, we evaluated wav2vec 2.0 on a new dataset of 620 tracks labeled with crowdsourcing. The proposed model shows superior performance to perceptual measures adapted from speech quality prediction. Finally, we propose a new evaluation metric called pairwise ranking accuracy (PRA) that takes into account subjective rater uncertainty by measuring the ability of an objective metric to rank pairs with high-confidence labels.
BibTeX
@inproceedings{icassp2023_audioqualityasse,
title = {Audio Quality Assessment of Vinyl Music Collections Using Self-Supervised Learning},
author = {Alessandro Ragano and Emmanouil Benetos and Andrew Hines},
booktitle = {ICASSP 2023},
year = {2023}
}