In this article, we aim to provide a review of the key ideas and approaches
proposed in 20 years of scientific literature around musical version
identification (VI) research and connect them to current practice. For more
than a decade, VI systems suffered from the accuracy-scalability trade-off,
with attempts to increase accuracy that typically resulted in cumbersome,
non-scalable systems. Recent years, however, have witnessed the rise of deep
learning-based approaches that take a step toward bridging the
accuracy-scalability gap, yielding systems that can realistically be deployed
in industrial applications. Although this trend positively influences the
number of researchers and institutions working on VI, it may also result in
obscuring the literature before the deep learning era. To appreciate two
decades of novel ideas in VI research and to facilitate building better
systems, we now review some of the successful concepts and applications
proposed in the literature and study their evolution throughout the years.
Описание
[2109.02472] Audio-based Musical Version Identification: Elements and Challenges
%0 Generic
%1 yesiler2021audiobased
%A Yesiler, Furkan
%A Doras, Guillaume
%A Bittner, Rachel M.
%A Tralie, Christopher J.
%A Serrà, Joan
%D 2021
%K audio duplicate identification mir ml similarity uncovr variant version
%T Audio-based Musical Version Identification: Elements and Challenges
%U http://arxiv.org/abs/2109.02472
%X In this article, we aim to provide a review of the key ideas and approaches
proposed in 20 years of scientific literature around musical version
identification (VI) research and connect them to current practice. For more
than a decade, VI systems suffered from the accuracy-scalability trade-off,
with attempts to increase accuracy that typically resulted in cumbersome,
non-scalable systems. Recent years, however, have witnessed the rise of deep
learning-based approaches that take a step toward bridging the
accuracy-scalability gap, yielding systems that can realistically be deployed
in industrial applications. Although this trend positively influences the
number of researchers and institutions working on VI, it may also result in
obscuring the literature before the deep learning era. To appreciate two
decades of novel ideas in VI research and to facilitate building better
systems, we now review some of the successful concepts and applications
proposed in the literature and study their evolution throughout the years.
@misc{yesiler2021audiobased,
abstract = {In this article, we aim to provide a review of the key ideas and approaches
proposed in 20 years of scientific literature around musical version
identification (VI) research and connect them to current practice. For more
than a decade, VI systems suffered from the accuracy-scalability trade-off,
with attempts to increase accuracy that typically resulted in cumbersome,
non-scalable systems. Recent years, however, have witnessed the rise of deep
learning-based approaches that take a step toward bridging the
accuracy-scalability gap, yielding systems that can realistically be deployed
in industrial applications. Although this trend positively influences the
number of researchers and institutions working on VI, it may also result in
obscuring the literature before the deep learning era. To appreciate two
decades of novel ideas in VI research and to facilitate building better
systems, we now review some of the successful concepts and applications
proposed in the literature and study their evolution throughout the years.},
added-at = {2021-10-12T16:07:09.000+0200},
author = {Yesiler, Furkan and Doras, Guillaume and Bittner, Rachel M. and Tralie, Christopher J. and Serrà, Joan},
biburl = {https://www.bibsonomy.org/bibtex/2b583865228b06bcbad56c57cfd70313d/jaeschke},
description = {[2109.02472] Audio-based Musical Version Identification: Elements and Challenges},
interhash = {fa0c04a3c2666bd3adec86c7af78c085},
intrahash = {b583865228b06bcbad56c57cfd70313d},
keywords = {audio duplicate identification mir ml similarity uncovr variant version},
note = {cite arxiv:2109.02472Comment: Accepted to be published in IEEE Signal Processing Magazine},
timestamp = {2021-10-12T16:07:09.000+0200},
title = {Audio-based Musical Version Identification: Elements and Challenges},
url = {http://arxiv.org/abs/2109.02472},
year = 2021
}