Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features
A. Correya, R. Hennequin, and M. Arcos. (2018)cite arxiv:1808.10351Comment: Music Information Retrieval, Cover Song Identification, Million Song Dataset, Natural Language Processing.
Abstract
Cover song detection is a very relevant task in Music Information Retrieval
(MIR) studies and has been mainly addressed using audio-based systems. Despite
its potential impact in industrial contexts, low performances and lack of
scalability have prevented such systems from being adopted in practice for
large applications. In this work, we investigate whether textual music
information (such as metadata and lyrics) can be used along with audio for
large-scale cover identification problem in a wide digital music library. We
benchmark this problem using standard text and state of the art audio
similarity measures. Our studies shows that these methods can significantly
increase the accuracy and scalability of cover detection systems on Million
Song Dataset (MSD) and Second Hand Song (SHS) datasets. By only leveraging
standard tf-idf based text similarity measures on song titles and lyrics, we
achieved 35.5% of absolute increase in mean average precision compared to the
current scalable audio content-based state of the art methods on MSD. These
experimental results suggests that new methodologies can be encouraged among
researchers to leverage and identify more sophisticated NLP-based techniques to
improve current cover song identification systems in digital music libraries
with metadata.
Description
Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features
%0 Generic
%1 correya2018largescale
%A Correya, Albin Andrew
%A Hennequin, Romain
%A Arcos, Mickaël
%D 2018
%K audio cover identification lyrics mir music similarity uncovr version
%T Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features
%U http://arxiv.org/abs/1808.10351
%X Cover song detection is a very relevant task in Music Information Retrieval
(MIR) studies and has been mainly addressed using audio-based systems. Despite
its potential impact in industrial contexts, low performances and lack of
scalability have prevented such systems from being adopted in practice for
large applications. In this work, we investigate whether textual music
information (such as metadata and lyrics) can be used along with audio for
large-scale cover identification problem in a wide digital music library. We
benchmark this problem using standard text and state of the art audio
similarity measures. Our studies shows that these methods can significantly
increase the accuracy and scalability of cover detection systems on Million
Song Dataset (MSD) and Second Hand Song (SHS) datasets. By only leveraging
standard tf-idf based text similarity measures on song titles and lyrics, we
achieved 35.5% of absolute increase in mean average precision compared to the
current scalable audio content-based state of the art methods on MSD. These
experimental results suggests that new methodologies can be encouraged among
researchers to leverage and identify more sophisticated NLP-based techniques to
improve current cover song identification systems in digital music libraries
with metadata.
@misc{correya2018largescale,
abstract = {Cover song detection is a very relevant task in Music Information Retrieval
(MIR) studies and has been mainly addressed using audio-based systems. Despite
its potential impact in industrial contexts, low performances and lack of
scalability have prevented such systems from being adopted in practice for
large applications. In this work, we investigate whether textual music
information (such as metadata and lyrics) can be used along with audio for
large-scale cover identification problem in a wide digital music library. We
benchmark this problem using standard text and state of the art audio
similarity measures. Our studies shows that these methods can significantly
increase the accuracy and scalability of cover detection systems on Million
Song Dataset (MSD) and Second Hand Song (SHS) datasets. By only leveraging
standard tf-idf based text similarity measures on song titles and lyrics, we
achieved 35.5% of absolute increase in mean average precision compared to the
current scalable audio content-based state of the art methods on MSD. These
experimental results suggests that new methodologies can be encouraged among
researchers to leverage and identify more sophisticated NLP-based techniques to
improve current cover song identification systems in digital music libraries
with metadata.},
added-at = {2022-03-03T15:46:51.000+0100},
author = {Correya, Albin Andrew and Hennequin, Romain and Arcos, Mickaël},
biburl = {https://www.bibsonomy.org/bibtex/224d1bbf83fe803f3178764d53504fd75/simonha94},
description = {Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features},
interhash = {2fd25d7d7cb8997ec4bfc02edc80347f},
intrahash = {24d1bbf83fe803f3178764d53504fd75},
keywords = {audio cover identification lyrics mir music similarity uncovr version},
note = {cite arxiv:1808.10351Comment: Music Information Retrieval, Cover Song Identification, Million Song Dataset, Natural Language Processing},
timestamp = {2022-03-03T15:46:51.000+0100},
title = {Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features},
url = {http://arxiv.org/abs/1808.10351},
year = 2018
}