Unsupervised Analysis and Generation of Audio Percussion Sequences
Identifieur interne : 000600 ( Main/Exploration ); précédent : 000599; suivant : 000601Unsupervised Analysis and Generation of Audio Percussion Sequences
Auteurs : Marco Marchini [Espagne, États-Unis] ; Hendrik Purwins [Espagne, États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
English descriptors
Abstract
Abstract: A system is presented that learns the structure of an audio recording of a rhythmical percussion fragment in an unsupervised manner and that synthesizes musical variations from it. The procedure consists of 1) segmentation, 2) symbolization (feature extraction, clustering, sequence structure analysis, temporal alignment), and 3) synthesis. The symbolization step yields a sequence of event classes. Simultaneously, representations are maintained that cluster the events into few or many classes. Based on the most regular clustering level, a tempo estimation procedure is used to preserve the metrical structure in the generated sequence. Employing variable length Markov chains, the final synthesis is performed, recombining the audio material derived from the sample itself. Representations with different numbers of classes are used to trade off statistical significance (short context sequence, low clustering refinement) versus specificity (long context, high clustering refinement) of the generated sequence. For a broad variety of musical styles the musical characteristics of the original are preserved. At the same time, considerable variability is introduced in the generated sequence.
Url:
DOI: 10.1007/978-3-642-23126-1_14
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001096
- to stream Istex, to step Curation: 000D99
- to stream Istex, to step Checkpoint: 000166
- to stream Main, to step Merge: 000602
- to stream Main, to step Curation: 000600
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Unsupervised Analysis and Generation of Audio Percussion Sequences</title><author><name sortKey="Marchini, Marco" sort="Marchini, Marco" uniqKey="Marchini M" first="Marco" last="Marchini">Marco Marchini</name></author><author><name sortKey="Purwins, Hendrik" sort="Purwins, Hendrik" uniqKey="Purwins H" first="Hendrik" last="Purwins">Hendrik Purwins</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:8E69B0150B067CF0ABF55E0DF3EB0AED1CEAD0C9</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/978-3-642-23126-1_14</idno><idno type="url">https://api.istex.fr/document/8E69B0150B067CF0ABF55E0DF3EB0AED1CEAD0C9/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001096</idno><idno type="wicri:Area/Istex/Curation">000D99</idno><idno type="wicri:Area/Istex/Checkpoint">000166</idno><idno type="wicri:doubleKey">0302-9743:2011:Marchini M:unsupervised:analysis:and</idno><idno type="wicri:Area/Main/Merge">000602</idno><idno type="wicri:Area/Main/Curation">000600</idno><idno type="wicri:Area/Main/Exploration">000600</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Unsupervised Analysis and Generation of Audio Percussion Sequences</title><author><name sortKey="Marchini, Marco" sort="Marchini, Marco" uniqKey="Marchini M" first="Marco" last="Marchini">Marco Marchini</name><affiliation wicri:level="4"><country xml:lang="fr">Espagne</country><wicri:regionArea>Music Technology Group, Department of Information and Communications Technologies, Universitat Pompeu Fabra, Roc Boronat, 138, 08018, Barcelona</wicri:regionArea><placeName><settlement type="city">Barcelone</settlement><region nuts="2" type="region">Catalogne</region></placeName><orgName type="university">Université Pompeu Fabra</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Purwins, Hendrik" sort="Purwins, Hendrik" uniqKey="Purwins H" first="Hendrik" last="Purwins">Hendrik Purwins</name><affiliation wicri:level="4"><country xml:lang="fr">Espagne</country><wicri:regionArea>Music Technology Group, Department of Information and Communications Technologies, Universitat Pompeu Fabra, Roc Boronat, 138, 08018, Barcelona</wicri:regionArea><placeName><settlement type="city">Barcelone</settlement><region nuts="2" type="region">Catalogne</region></placeName><orgName type="university">Université Pompeu Fabra</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></series><idno type="istex">8E69B0150B067CF0ABF55E0DF3EB0AED1CEAD0C9</idno><idno type="DOI">10.1007/978-3-642-23126-1_14</idno><idno type="ChapterID">Chap14</idno><idno type="ChapterID">14</idno></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Markov chains</term><term>machine listening</term><term>music analysis</term><term>music generation</term><term>unsupervised clustering</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: A system is presented that learns the structure of an audio recording of a rhythmical percussion fragment in an unsupervised manner and that synthesizes musical variations from it. The procedure consists of 1) segmentation, 2) symbolization (feature extraction, clustering, sequence structure analysis, temporal alignment), and 3) synthesis. The symbolization step yields a sequence of event classes. Simultaneously, representations are maintained that cluster the events into few or many classes. Based on the most regular clustering level, a tempo estimation procedure is used to preserve the metrical structure in the generated sequence. Employing variable length Markov chains, the final synthesis is performed, recombining the audio material derived from the sample itself. Representations with different numbers of classes are used to trade off statistical significance (short context sequence, low clustering refinement) versus specificity (long context, high clustering refinement) of the generated sequence. For a broad variety of musical styles the musical characteristics of the original are preserved. At the same time, considerable variability is introduced in the generated sequence.</div></front></TEI><affiliations><list><country><li>Espagne</li><li>États-Unis</li></country><region><li>Catalogne</li></region><settlement><li>Barcelone</li></settlement><orgName><li>Université Pompeu Fabra</li></orgName></list><tree><country name="Espagne"><region name="Catalogne"><name sortKey="Marchini, Marco" sort="Marchini, Marco" uniqKey="Marchini M" first="Marco" last="Marchini">Marco Marchini</name></region><name sortKey="Purwins, Hendrik" sort="Purwins, Hendrik" uniqKey="Purwins H" first="Hendrik" last="Purwins">Hendrik Purwins</name></country><country name="États-Unis"><noRegion><name sortKey="Marchini, Marco" sort="Marchini, Marco" uniqKey="Marchini M" first="Marco" last="Marchini">Marco Marchini</name></noRegion><name sortKey="Purwins, Hendrik" sort="Purwins, Hendrik" uniqKey="Purwins H" first="Hendrik" last="Purwins">Hendrik Purwins</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/MozartV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000600 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000600 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= MozartV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:8E69B0150B067CF0ABF55E0DF3EB0AED1CEAD0C9
|texte= Unsupervised Analysis and Generation of Audio Percussion Sequences
}}
| This area was generated with Dilib version V0.6.20. |  |