Aligning music audio with symbolic scores using a hybrid graphical model
Identifieur interne : 000604 ( Istex/Corpus ); précédent : 000603; suivant : 000605Aligning music audio with symbolic scores using a hybrid graphical model
Auteurs : Christopher RaphaelSource :
- Machine Learning [ 0885-6125 ] ; 2006-12-01.
English descriptors
- KwdEn :
Abstract
Abstract: We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.
Url:
DOI: 10.1007/s10994-006-8415-3
Links to Exploration step
ISTEX:698850BDEB0B2344798C55B050A2C90ACF55CFEALe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Aligning music audio with symbolic scores using a hybrid graphical model</title><author><name sortKey="Raphael, Christopher" sort="Raphael, Christopher" uniqKey="Raphael C" first="Christopher" last="Raphael">Christopher Raphael</name><affiliation><mods:affiliation>School of Informatics, Indiana University, Bloomington</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: craphael@indiana.edu</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:698850BDEB0B2344798C55B050A2C90ACF55CFEA</idno><date when="2006" year="2006">2006</date><idno type="doi">10.1007/s10994-006-8415-3</idno><idno type="url">https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000604</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000604</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Aligning music audio with symbolic scores using a hybrid graphical model</title><author><name sortKey="Raphael, Christopher" sort="Raphael, Christopher" uniqKey="Raphael C" first="Christopher" last="Raphael">Christopher Raphael</name><affiliation><mods:affiliation>School of Informatics, Indiana University, Bloomington</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: craphael@indiana.edu</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Machine Learning</title><title level="j" type="abbrev">Mach Learn</title><idno type="ISSN">0885-6125</idno><idno type="eISSN">1573-0565</idno><imprint><publisher>Kluwer Academic Publishers</publisher><pubPlace>Boston</pubPlace><date type="published" when="2006-12-01">2006-12-01</date><biblScope unit="volume">65</biblScope><biblScope unit="issue">2-3</biblScope><biblScope unit="page" from="389">389</biblScope><biblScope unit="page" to="409">409</biblScope></imprint><idno type="ISSN">0885-6125</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0885-6125</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Graphical models</term><term>Music</term><term>Score following</term><term>Score matching</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.</div></front></TEI><istex><corpusName>springer-journals</corpusName><author><json:item><name>Christopher Raphael</name><affiliations><json:string>School of Informatics, Indiana University, Bloomington</json:string><json:string>E-mail: craphael@indiana.edu</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Graphical models</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Score matching</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Music</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Score following</value></json:item></subject><articleId><json:string>8415</json:string><json:string>NO00008415</json:string></articleId><arkIstex>ark:/67375/VQC-XW605M38-D</arkIstex><language><json:string>eng</json:string></language><originalGenre><json:string>OriginalPaper</json:string></originalGenre><abstract>Abstract: We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.</abstract><qualityIndicators><refBibsNative>false</refBibsNative><abstractWordCount>110</abstractWordCount><abstractCharCount>752</abstractCharCount><keywordCount>4</keywordCount><score>8.32</score><pdfWordCount>7986</pdfWordCount><pdfCharCount>41796</pdfCharCount><pdfVersion>1.3</pdfVersion><pdfPageCount>21</pdfPageCount><pdfPageSize>439.204 x 666.007 pts</pdfPageSize></qualityIndicators><title>Aligning music audio with symbolic scores using a hybrid graphical model</title><genre><json:string>research-article</json:string></genre><host><title>Machine Learning</title><language><json:string>unknown</json:string></language><publicationDate>2006</publicationDate><copyrightDate>2006</copyrightDate><issn><json:string>0885-6125</json:string></issn><eissn><json:string>1573-0565</json:string></eissn><journalId><json:string>10994</json:string></journalId><volume>65</volume><issue>2-3</issue><pages><first>389</first><last>409</last></pages><genre><json:string>journal</json:string></genre><editor><json:item><name>Gerhard Widmer</name></json:item></editor><subject><json:item><value>Computing Methodologies</value></json:item><json:item><value>Artificial Intelligence (incl. Robotics)</value></json:item><json:item><value>Simulation and Modeling</value></json:item><json:item><value>Language Translation and Linguistics</value></json:item><json:item><value>Automation and Robotics</value></json:item></subject></host><ark><json:string>ark:/67375/VQC-XW605M38-D</json:string></ark><publicationDate>2006</publicationDate><copyrightDate>2006</copyrightDate><doi><json:string>10.1007/s10994-006-8415-3</json:string></doi><id>698850BDEB0B2344798C55B050A2C90ACF55CFEA</id><score>1</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/fulltext/pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/fulltext/zip</uri></json:item><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/fulltext/txt</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Aligning music audio with symbolic scores using a hybrid graphical model</title><respStmt><resp>Références bibliographiques récupérées via GROBID</resp><name resp="ISTEX-API">ISTEX-API (INIST-CNRS)</name></respStmt></titleStmt><publicationStmt><authority>ISTEX</authority><publisher scheme="https://publisher-list.data.istex.fr">Kluwer Academic Publishers</publisher><pubPlace>Boston</pubPlace><availability><licence><p>Springer Science + Business Media, LLC, 2006</p></licence><p scheme="https://loaded-corpus.data.istex.fr/ark:/67375/XBH-3XSW68JL-F">springer</p></availability><date>2005-09-20</date></publicationStmt><notesStmt><note type="research-article" scheme="https://content-type.data.istex.fr/ark:/67375/XTP-1JC4F85T-7">research-article</note><note type="journal" scheme="https://publication-type.data.istex.fr/ark:/67375/JMC-0GLKJH51-B">journal</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Aligning music audio with symbolic scores using a hybrid graphical model</title><author xml:id="author-0000" corresp="yes"><persName><forename type="first">Christopher</forename><surname>Raphael</surname></persName><email>craphael@indiana.edu</email><affiliation>School of Informatics, Indiana University, Bloomington</affiliation></author><idno type="istex">698850BDEB0B2344798C55B050A2C90ACF55CFEA</idno><idno type="ark">ark:/67375/VQC-XW605M38-D</idno><idno type="DOI">10.1007/s10994-006-8415-3</idno><idno type="article-id">8415</idno><idno type="article-id">NO00008415</idno></analytic><monogr><title level="j">Machine Learning</title><title level="j" type="abbrev">Mach Learn</title><idno type="pISSN">0885-6125</idno><idno type="eISSN">1573-0565</idno><idno type="journal-ID">true</idno><idno type="journal-SPIN">MACH</idno><idno type="issue-article-count">10</idno><idno type="volume-issue-count">3</idno><editor xml:id="book-author-0000"><persName><forename type="first">Gerhard</forename><surname>Widmer</surname></persName></editor><imprint><publisher>Kluwer Academic Publishers</publisher><pubPlace>Boston</pubPlace><date type="published" when="2006-12-01"></date><biblScope unit="volume">65</biblScope><biblScope unit="issue">2-3</biblScope><biblScope unit="page" from="389">389</biblScope><biblScope unit="page" to="409">409</biblScope></imprint></monogr></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2005-09-20</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>Abstract: We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.</p></abstract><textClass xml:lang="en"><keywords scheme="keyword"><list><head>Keywords</head><item><term>Graphical models</term></item><item><term>Score matching</term></item><item><term>Music</term></item><item><term>Score following</term></item></list></keywords></textClass><textClass><keywords scheme="Journal Subject"><list><head>Computer Science</head><item><term>Computing Methodologies</term></item><item><term>Artificial Intelligence (incl. Robotics)</term></item><item><term>Simulation and Modeling</term></item><item><term>Language Translation and Linguistics</term></item><item><term>Automation and Robotics</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2005-09-20">Created</change><change when="2006-12-01">Published</change><change xml:id="refBibs-istex" who="#ISTEX-API" when="2017-12-1">References added</change></revisionDesc></teiHeader></istex:fulltextTEI></fulltext><metadata><istex:metadataXml wicri:clean="corpus springer-journals not found" wicri:toSee="no header"><istex:xmlDeclaration>version="1.0" encoding="UTF-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//Springer-Verlag//DTD A++ V2.4//EN" URI="http://devel.springer.de/A++/V2.4/DTD/A++V2.4.dtd" name="istex:docType"></istex:docType><istex:document><Publisher><PublisherInfo><PublisherName>Kluwer Academic Publishers</PublisherName><PublisherLocation>Boston</PublisherLocation></PublisherInfo><Journal><JournalInfo JournalProductType="ArchiveJournal" NumberingStyle="Unnumbered"><JournalID>10994</JournalID><JournalPrintISSN>0885-6125</JournalPrintISSN><JournalElectronicISSN>1573-0565</JournalElectronicISSN><JournalSPIN>MACH</JournalSPIN><JournalTitle>Machine Learning</JournalTitle><JournalAbbreviatedTitle>Mach Learn</JournalAbbreviatedTitle><JournalSubjectGroup><JournalSubject Type="Primary">Computer Science</JournalSubject><JournalSubject Type="Secondary">Computing Methodologies</JournalSubject><JournalSubject Type="Secondary">Artificial Intelligence (incl. Robotics)</JournalSubject><JournalSubject Type="Secondary">Simulation and Modeling</JournalSubject><JournalSubject Type="Secondary">Language Translation and Linguistics</JournalSubject><JournalSubject Type="Secondary">Automation and Robotics</JournalSubject></JournalSubjectGroup></JournalInfo><Volume><VolumeInfo VolumeType="Regular" TocLevels="0"><VolumeIDStart>65</VolumeIDStart><VolumeIDEnd>65</VolumeIDEnd><VolumeIssueCount>3</VolumeIssueCount></VolumeInfo><Issue IssueType="Combined"><IssueInfo TocLevels="0"><IssueIDStart>2</IssueIDStart><IssueIDEnd>3</IssueIDEnd><IssueTitle Language="En">Special Issue on Machine Learning in and for Music</IssueTitle><IssueArticleCount>10</IssueArticleCount><IssueHistory><CoverDate><Year>2006</Year><Month>12</Month></CoverDate></IssueHistory><IssueCopyright><CopyrightHolderName>Springer Science + Business Media, LLC</CopyrightHolderName><CopyrightYear>2006</CopyrightYear></IssueCopyright></IssueInfo><IssueHeader><EditorGroup><Editor><EditorName DisplayOrder="Western"><GivenName>Gerhard</GivenName><FamilyName>Widmer</FamilyName></EditorName></Editor></EditorGroup></IssueHeader><Article ID="NO00008415"><ArticleInfo ArticleType="OriginalPaper" Language="En" TocLevels="0" NumberingStyle="Unnumbered" ContainsESM="No"><ArticleID>8415</ArticleID><ArticleDOI>10.1007/s10994-006-8415-3</ArticleDOI><ArticleSequenceNumber>5</ArticleSequenceNumber><ArticleTitle Language="En">Aligning music audio with symbolic scores using a hybrid graphical model</ArticleTitle><ArticleFirstPage>389</ArticleFirstPage><ArticleLastPage>409</ArticleLastPage><ArticleHistory><RegistrationDate><Year>2006</Year><Month>1</Month><Day>1</Day></RegistrationDate><Received><Year>2005</Year><Month>9</Month><Day>20</Day></Received><Revised><Year>2006</Year><Month>2</Month><Day>17</Day></Revised><Accepted><Year>2006</Year><Month>3</Month><Day>9</Day></Accepted><OnlineDate><Year>2006</Year><Month>5</Month><Day>8</Day></OnlineDate></ArticleHistory><ArticleCopyright><CopyrightHolderName>Springer Science + Business Media, LLC</CopyrightHolderName><CopyrightYear>2006</CopyrightYear></ArticleCopyright><ArticleGrants Type="Regular"><MetadataGrant Grant="OpenAccess"></MetadataGrant><AbstractGrant Grant="OpenAccess"></AbstractGrant><BodyPDFGrant Grant="OpenAccess"></BodyPDFGrant><BodyHTMLGrant Grant="OpenAccess"></BodyHTMLGrant><BibliographyGrant Grant="OpenAccess"></BibliographyGrant><ESMGrant Grant="OpenAccess"></ESMGrant></ArticleGrants></ArticleInfo><ArticleHeader><AuthorGroup><Author AffiliationIDS="Aff1" CorrespondingAffiliationID="Aff1"><AuthorName DisplayOrder="Western"><GivenName>Christopher</GivenName><FamilyName>Raphael</FamilyName></AuthorName><Contact><Email>craphael@indiana.edu</Email></Contact></Author><Affiliation ID="Aff1"><OrgDivision>School of Informatics</OrgDivision><OrgName>Indiana University</OrgName><OrgAddress><City>Bloomington</City></OrgAddress></Affiliation></AuthorGroup><Abstract Language="En" ID="Abs1"><Heading>Abstract</Heading><Para>We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.</Para></Abstract><KeywordGroup Language="En"><Heading>Keywords</Heading><Keyword>Graphical models</Keyword><Keyword>Score matching</Keyword><Keyword>Music</Keyword><Keyword>Score following</Keyword></KeywordGroup><ArticleNote Type="Misc"><SimplePara>This work supported by NSF grants IIS-0113496 and IIS-0534694.</SimplePara></ArticleNote><ArticleNote Type="Misc"><SimplePara><Emphasis Type="Bold">Editor:</Emphasis> Gerhard Widmer</SimplePara></ArticleNote></ArticleHeader><NoBody></NoBody></Article></Issue></Volume></Journal></Publisher></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Aligning music audio with symbolic scores using a hybrid graphical model</title></titleInfo><titleInfo type="alternative" contentType="CDATA" lang="en"><title>Aligning music audio with symbolic scores using a hybrid graphical model</title></titleInfo><name type="personal" displayLabel="corresp"><namePart type="given">Christopher</namePart><namePart type="family">Raphael</namePart><affiliation>School of Informatics, Indiana University, Bloomington</affiliation><affiliation>E-mail: craphael@indiana.edu</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="OriginalPaper" authority="ISTEX" authorityURI="https://content-type.data.istex.fr" valueURI="https://content-type.data.istex.fr/ark:/67375/XTP-1JC4F85T-7">research-article</genre><originInfo><publisher>Kluwer Academic Publishers</publisher><place><placeTerm type="text">Boston</placeTerm></place><dateCreated encoding="w3cdtf">2005-09-20</dateCreated><dateIssued encoding="w3cdtf">2006-12-01</dateIssued><dateIssued encoding="w3cdtf">2006</dateIssued><copyrightDate encoding="w3cdtf">2006</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><abstract lang="en">Abstract: We present a new method for establishing an alignment between a polyphonic musical score and a corresponding sampled audio performance. The method uses a graphical model containing both latent discrete variables, corresponding to score position, as well as a latent continuous tempo process. We use a simple data model based only on the pitch content of the audio signal. The data interpretation is defined to be the most likely configuration of the hidden variables, given the data, and we develop computational methodology to identify or approximate this configuration using a variant of dynamic programming involving parametrically represented continuous variables. Experiments are presented on a 55-minute hand-marked orchestral test set.</abstract><subject lang="en"><genre>Keywords</genre><topic>Graphical models</topic><topic>Score matching</topic><topic>Music</topic><topic>Score following</topic></subject><relatedItem type="host"><titleInfo><title>Machine Learning</title></titleInfo><titleInfo type="abbreviated"><title>Mach Learn</title></titleInfo><name type="personal"><namePart type="given">Gerhard</namePart><namePart type="family">Widmer</namePart><role><roleTerm type="text">editor</roleTerm></role></name><genre type="journal" displayLabel="Archive Journal" authority="ISTEX" valueURI="https://publication-type.data.istex.fr/ark:/67375/JMC-0GLKJH51-B">journal</genre><originInfo><publisher>Springer</publisher><dateIssued encoding="w3cdtf">2006-12-01</dateIssued><copyrightDate encoding="w3cdtf">2006</copyrightDate></originInfo><subject><genre>Computer Science</genre><topic>Computing Methodologies</topic><topic>Artificial Intelligence (incl. Robotics)</topic><topic>Simulation and Modeling</topic><topic>Language Translation and Linguistics</topic><topic>Automation and Robotics</topic></subject><identifier type="ISSN">0885-6125</identifier><identifier type="eISSN">1573-0565</identifier><identifier type="JournalID">10994</identifier><identifier type="JournalSPIN">MACH</identifier><identifier type="IssueArticleCount">10</identifier><identifier type="VolumeIssueCount">3</identifier><part><date>2006</date><detail type="issue"><title>Special Issue on Machine Learning in and for Music</title></detail><detail type="volume"><number>65</number><caption>vol.</caption></detail><detail type="issue"><number>2-3</number><caption>no.</caption></detail><extent unit="pages"><start>389</start><end>409</end></extent></part><recordInfo><recordOrigin>Springer Science + Business Media, LLC, 2006</recordOrigin></recordInfo></relatedItem><identifier type="istex">698850BDEB0B2344798C55B050A2C90ACF55CFEA</identifier><identifier type="ark">ark:/67375/VQC-XW605M38-D</identifier><identifier type="DOI">10.1007/s10994-006-8415-3</identifier><identifier type="ArticleID">8415</identifier><identifier type="ArticleID">NO00008415</identifier><accessCondition type="use and reproduction" contentType="copyright">Springer Science + Business Media, LLC, 2006</accessCondition><recordInfo><recordContentSource authority="ISTEX" authorityURI="https://loaded-corpus.data.istex.fr" valueURI="https://loaded-corpus.data.istex.fr/ark:/67375/XBH-3XSW68JL-F">springer</recordContentSource><recordOrigin>Springer Science + Business Media, LLC, 2006</recordOrigin></recordInfo></mods><json:item><extension>json</extension><original>false</original><mimetype>application/json</mimetype><uri>https://api.istex.fr/document/698850BDEB0B2344798C55B050A2C90ACF55CFEA/metadata/json</uri></json:item></metadata><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/DebussyV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000604 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000604 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= DebussyV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:698850BDEB0B2344798C55B050A2C90ACF55CFEA
|texte= Aligning music audio with symbolic scores using a hybrid graphical model
}}
| This area was generated with Dilib version V0.6.33. |  |