Towards Reliable Partial Music Alignments Using Multiple Synchronization Strategies
Identifieur interne : 000314 ( Main/Exploration ); précédent : 000313; suivant : 000315Towards Reliable Partial Music Alignments Using Multiple Synchronization Strategies
Auteurs : Sebastian Ewert [Allemagne] ; Meinard Müller [Allemagne] ; Roger B. Dannenberg [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
English descriptors
- Teeft :
- Algorithm, Alignment, Alignment methods, Alignment result, Alignment results, Alignment strategies, Alignment strategy, Anthology release, Audio, Audio recording, Audio recordings, Automatic synchronization, Beatles, Beatles songs, Binary matrices, Boundary condition, Chroma, Chroma features, Computer accompaniment, Consistency alignment, Corresponding area, Cost matrix, Critical passages, Dannenberg, Dynamic programming, Ewert, Exible alignment, Feature vectors, Future work, Global path, Horizontal axis, Ieee icassp, Interesting deviations, Intersection matrix, Ismir, Local cost measure, Local deviations, Markov models, Matrix, Midi, Midi segment, Midi version, Misguided alignments, Monotonic, Multiple information sources, Music alignments, Music data, Music database, Music representations, Music synchronization, Musical work, Negative entries, Negative score, Novel method, Optimal path, Other hand, Overall synchronization result, Polyphonic, Proc, Recursive, Recursive variant, Reliable passages, Saarland university, Same piece, Score alignment, Score matrix, Sect, Several techniques, Several types, Solo segments, Subsequent discussion, Subsequent improvements, Synchronization, Synchronization results, Synchronization strategies, Synchronization task, Various alignments, Vertical axis.
Abstract
Abstract: The general goal of music synchronization is to align multiple information sources related to a given piece of music. This becomes a hard problem when the various representations to be aligned reveal significant differences not only in tempo, instrumentation, or dynamics but also in structure or polyphony. Because of the complexity and diversity of music data, one can not expect to find a universal synchronization algorithm that yields reasonable solutions in all situations. In this paper, we present a novel method that allows for automatically identifying the reliable parts of alignment results. Instead of relying on one single strategy, our idea is to combine several types of conceptually different synchronization strategies within an extensible framework, thus accounting for various musical aspects. Looking for consistencies and inconsistencies across the synchronization results, our method automatically classifies the alignments locally as reliable or critical. Considering only the reliable parts yields a high-precision partial alignment. Moreover, the identification of critical parts is also useful, as they often reveal musically interesting deviations between the versions to be aligned.
Url:
DOI: 10.1007/978-3-642-18449-9_4
Affiliations:
- Allemagne, États-Unis
- District de Cologne, Pennsylvanie, Rhénanie-du-Nord-Westphalie, Sarre (Land)
- Bonn, Pittsburgh, Sarrebruck
- Université Carnegie-Mellon
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001245
- to stream Istex, to step Curation: 001156
- to stream Istex, to step Checkpoint: 000175
- to stream Main, to step Merge: 000314
- to stream Main, to step Curation: 000314
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Towards Reliable Partial Music Alignments Using Multiple Synchronization Strategies</title><author><name sortKey="Ewert, Sebastian" sort="Ewert, Sebastian" uniqKey="Ewert S" first="Sebastian" last="Ewert">Sebastian Ewert</name></author><author><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name></author><author><name sortKey="Dannenberg, Roger B" sort="Dannenberg, Roger B" uniqKey="Dannenberg R" first="Roger B." last="Dannenberg">Roger B. Dannenberg</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:B170F009ADEA3E056315CE14389E9BF0AB934B8A</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/978-3-642-18449-9_4</idno><idno type="url">https://api.istex.fr/document/B170F009ADEA3E056315CE14389E9BF0AB934B8A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001245</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">001245</idno><idno type="wicri:Area/Istex/Curation">001156</idno><idno type="wicri:Area/Istex/Checkpoint">000175</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000175</idno><idno type="wicri:doubleKey">0302-9743:2011:Ewert S:towards:reliable:partial</idno><idno type="wicri:Area/Main/Merge">000314</idno><idno type="wicri:Area/Main/Curation">000314</idno><idno type="wicri:Area/Main/Exploration">000314</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Towards Reliable Partial Music Alignments Using Multiple Synchronization Strategies</title><author><name sortKey="Ewert, Sebastian" sort="Ewert, Sebastian" uniqKey="Ewert S" first="Sebastian" last="Ewert">Sebastian Ewert</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Multimedia Signal Processing Group, Bonn University, Bonn</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Cologne</region><settlement type="city">Bonn</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country></affiliation></author><author><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Saarland University, Saarbrücken</wicri:regionArea><placeName><region type="land" nuts="2">Sarre (Land)</region><settlement type="city">Sarrebruck</settlement></placeName></affiliation><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>MPI Informatik, Saarbrücken</wicri:regionArea><placeName><region type="land" nuts="2">Sarre (Land)</region><settlement type="city">Sarrebruck</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country></affiliation></author><author><name sortKey="Dannenberg, Roger B" sort="Dannenberg, Roger B" uniqKey="Dannenberg R" first="Roger B." last="Dannenberg">Roger B. Dannenberg</name><affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country><wicri:regionArea>School of Computer Science, Carnegie Mellon University, Pittsburgh</wicri:regionArea><placeName><settlement type="city">Pittsburgh</settlement><region type="state">Pennsylvanie</region></placeName><orgName type="university">Université Carnegie-Mellon</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2011</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Algorithm</term><term>Alignment</term><term>Alignment methods</term><term>Alignment result</term><term>Alignment results</term><term>Alignment strategies</term><term>Alignment strategy</term><term>Anthology release</term><term>Audio</term><term>Audio recording</term><term>Audio recordings</term><term>Automatic synchronization</term><term>Beatles</term><term>Beatles songs</term><term>Binary matrices</term><term>Boundary condition</term><term>Chroma</term><term>Chroma features</term><term>Computer accompaniment</term><term>Consistency alignment</term><term>Corresponding area</term><term>Cost matrix</term><term>Critical passages</term><term>Dannenberg</term><term>Dynamic programming</term><term>Ewert</term><term>Exible alignment</term><term>Feature vectors</term><term>Future work</term><term>Global path</term><term>Horizontal axis</term><term>Ieee icassp</term><term>Interesting deviations</term><term>Intersection matrix</term><term>Ismir</term><term>Local cost measure</term><term>Local deviations</term><term>Markov models</term><term>Matrix</term><term>Midi</term><term>Midi segment</term><term>Midi version</term><term>Misguided alignments</term><term>Monotonic</term><term>Multiple information sources</term><term>Music alignments</term><term>Music data</term><term>Music database</term><term>Music representations</term><term>Music synchronization</term><term>Musical work</term><term>Negative entries</term><term>Negative score</term><term>Novel method</term><term>Optimal path</term><term>Other hand</term><term>Overall synchronization result</term><term>Polyphonic</term><term>Proc</term><term>Recursive</term><term>Recursive variant</term><term>Reliable passages</term><term>Saarland university</term><term>Same piece</term><term>Score alignment</term><term>Score matrix</term><term>Sect</term><term>Several techniques</term><term>Several types</term><term>Solo segments</term><term>Subsequent discussion</term><term>Subsequent improvements</term><term>Synchronization</term><term>Synchronization results</term><term>Synchronization strategies</term><term>Synchronization task</term><term>Various alignments</term><term>Vertical axis</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: The general goal of music synchronization is to align multiple information sources related to a given piece of music. This becomes a hard problem when the various representations to be aligned reveal significant differences not only in tempo, instrumentation, or dynamics but also in structure or polyphony. Because of the complexity and diversity of music data, one can not expect to find a universal synchronization algorithm that yields reasonable solutions in all situations. In this paper, we present a novel method that allows for automatically identifying the reliable parts of alignment results. Instead of relying on one single strategy, our idea is to combine several types of conceptually different synchronization strategies within an extensible framework, thus accounting for various musical aspects. Looking for consistencies and inconsistencies across the synchronization results, our method automatically classifies the alignments locally as reliable or critical. Considering only the reliable parts yields a high-precision partial alignment. Moreover, the identification of critical parts is also useful, as they often reveal musically interesting deviations between the versions to be aligned.</div></front></TEI><affiliations><list><country><li>Allemagne</li><li>États-Unis</li></country><region><li>District de Cologne</li><li>Pennsylvanie</li><li>Rhénanie-du-Nord-Westphalie</li><li>Sarre (Land)</li></region><settlement><li>Bonn</li><li>Pittsburgh</li><li>Sarrebruck</li></settlement><orgName><li>Université Carnegie-Mellon</li></orgName></list><tree><country name="Allemagne"><region name="Rhénanie-du-Nord-Westphalie"><name sortKey="Ewert, Sebastian" sort="Ewert, Sebastian" uniqKey="Ewert S" first="Sebastian" last="Ewert">Sebastian Ewert</name></region><name sortKey="Ewert, Sebastian" sort="Ewert, Sebastian" uniqKey="Ewert S" first="Sebastian" last="Ewert">Sebastian Ewert</name><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name></country><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Dannenberg, Roger B" sort="Dannenberg, Roger B" uniqKey="Dannenberg R" first="Roger B." last="Dannenberg">Roger B. Dannenberg</name></region><name sortKey="Dannenberg, Roger B" sort="Dannenberg, Roger B" uniqKey="Dannenberg R" first="Roger B." last="Dannenberg">Roger B. Dannenberg</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sarre/explor/MusicSarreV3/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000314 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000314 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sarre
|area= MusicSarreV3
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:B170F009ADEA3E056315CE14389E9BF0AB934B8A
|texte= Towards Reliable Partial Music Alignments Using Multiple Synchronization Strategies
}}
| This area was generated with Dilib version V0.6.33. |  |