Relational IBL in classical music View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2006-09

AUTHORS

Asmir Tobudic, Gerhard Widmer

ABSTRACT

It is well known that many hard tasks considered in machine learning and data mining can be solved in a rather simple and robust way with an instance- and distance-based approach. In this work we present another difficult task: learning, from large numbers of complex performances by concert pianists, to play music expressively. We model the problem as a multi-level decomposition and prediction task. We show that this is a fundamentally relational learning problem and propose a new similarity measure for structured objects, which is built into a relational instance-based learning algorithm named DISTALL. Experiments with data derived from a substantial number of Mozart piano sonata recordings by a skilled concert pianist demonstrate that the approach is viable. We show that the instance-based learner operating on structured, relational data outperforms a propositional k-NN algorithm. In qualitative terms, some of the piano performances produced by DISTALL after learning from the human artist are of substantial musical quality; one even won a prize in an international ‘computer music performance’ contest. The experiments thus provide evidence of the capabilities of ILP in a highly complex domain such as music. More... »

PAGES

5-24

References to SciGraph publications

  • 1998. A framework for defining distances between first-order logic objects in INDUCTIVE LOGIC PROGRAMMING
  • 2003-06-18. Playing Mozart Phrase by Phrase in CASE-BASED REASONING RESEARCH AND DEVELOPMENT
  • 2003. Relational IBL in Music with a New Structural Similarity Measure in INDUCTIVE LOGIC PROGRAMMING
  • 2001-07. A polynomial time computable metric between point sets in ACTA INFORMATICA
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10994-006-8260-4

    DOI

    http://dx.doi.org/10.1007/s10994-006-8260-4

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1006816744


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Austrian Research Institute for Artificial Intelligence", 
              "id": "https://www.grid.ac/institutes/grid.432019.d", 
              "name": [
                "Austrian Research Institute for Artificial Intelligence, Vienna"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tobudic", 
            "givenName": "Asmir", 
            "id": "sg:person.011516435301.70", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011516435301.70"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Austrian Research Institute for Artificial Intelligence", 
              "id": "https://www.grid.ac/institutes/grid.432019.d", 
              "name": [
                "Department of Computational Perception, Johannes Kepler University Linz, and Austrian Research Institute for Artificial Intelligence, Vienna"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Widmer", 
            "givenName": "Gerhard", 
            "id": "sg:person.013641401431.40", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013641401431.40"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/0743-1066(94)90035-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002893202"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1076/jnmr.31.1.37.8103", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009581532"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1080/088395198117686", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011832436"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0027331", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014361691", 
              "https://doi.org/10.1007/bfb0027331"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1076/jnmr.32.3.259.16860", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023718011"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-39917-9_24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023779986", 
              "https://doi.org/10.1007/978-3-540-39917-9_24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/pl00013304", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031362934", 
              "https://doi.org/10.1007/pl00013304"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0004-3702(03)00016-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035588669"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45006-8_42", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046598564", 
              "https://doi.org/10.1007/3-540-45006-8_42"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45006-8_42", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046598564", 
              "https://doi.org/10.1007/3-540-45006-8_42"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1121/1.402843", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062354132"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2006-09", 
        "datePublishedReg": "2006-09-01", 
        "description": "It is well known that many hard tasks considered in machine learning and data mining can be solved in a rather simple and robust way with an instance- and distance-based approach. In this work we present another difficult task: learning, from large numbers of complex performances by concert pianists, to play music expressively. We model the problem as a multi-level decomposition and prediction task. We show that this is a fundamentally relational learning problem and propose a new similarity measure for structured objects, which is built into a relational instance-based learning algorithm named DISTALL. Experiments with data derived from a substantial number of Mozart piano sonata recordings by a skilled concert pianist demonstrate that the approach is viable. We show that the instance-based learner operating on structured, relational data outperforms a propositional k-NN algorithm. In qualitative terms, some of the piano performances produced by DISTALL after learning from the human artist are of substantial musical quality; one even won a prize in an international \u2018computer music performance\u2019 contest. The experiments thus provide evidence of the capabilities of ILP in a highly complex domain such as music.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s10994-006-8260-4", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1125588", 
            "issn": [
              "0885-6125", 
              "1573-0565"
            ], 
            "name": "Machine Learning", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1-3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "64"
          }
        ], 
        "name": "Relational IBL in classical music", 
        "pagination": "5-24", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "2078bfec6c133a2ae43ac96917a20ff1e90fb2154fc57835ef3aa2334d5ace4b"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10994-006-8260-4"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1006816744"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10994-006-8260-4", 
          "https://app.dimensions.ai/details/publication/pub.1006816744"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T23:23", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8693_00000510.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007%2Fs10994-006-8260-4"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s10994-006-8260-4'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10994-006-8260-4'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10994-006-8260-4'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10994-006-8260-4'


     

    This table displays all metadata directly associated to this object as RDF triples.

    103 TRIPLES      21 PREDICATES      37 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10994-006-8260-4 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N08f03c9a5d7d4a72b2aa94323a8ab02b
    4 schema:citation sg:pub.10.1007/3-540-45006-8_42
    5 sg:pub.10.1007/978-3-540-39917-9_24
    6 sg:pub.10.1007/bfb0027331
    7 sg:pub.10.1007/pl00013304
    8 https://doi.org/10.1016/0743-1066(94)90035-3
    9 https://doi.org/10.1016/s0004-3702(03)00016-x
    10 https://doi.org/10.1076/jnmr.31.1.37.8103
    11 https://doi.org/10.1076/jnmr.32.3.259.16860
    12 https://doi.org/10.1080/088395198117686
    13 https://doi.org/10.1121/1.402843
    14 schema:datePublished 2006-09
    15 schema:datePublishedReg 2006-09-01
    16 schema:description It is well known that many hard tasks considered in machine learning and data mining can be solved in a rather simple and robust way with an instance- and distance-based approach. In this work we present another difficult task: learning, from large numbers of complex performances by concert pianists, to play music expressively. We model the problem as a multi-level decomposition and prediction task. We show that this is a fundamentally relational learning problem and propose a new similarity measure for structured objects, which is built into a relational instance-based learning algorithm named DISTALL. Experiments with data derived from a substantial number of Mozart piano sonata recordings by a skilled concert pianist demonstrate that the approach is viable. We show that the instance-based learner operating on structured, relational data outperforms a propositional k-NN algorithm. In qualitative terms, some of the piano performances produced by DISTALL after learning from the human artist are of substantial musical quality; one even won a prize in an international ‘computer music performance’ contest. The experiments thus provide evidence of the capabilities of ILP in a highly complex domain such as music.
    17 schema:genre research_article
    18 schema:inLanguage en
    19 schema:isAccessibleForFree true
    20 schema:isPartOf N61134b5ba2004ab6ab7fddc577af7736
    21 Na244daba8fad493ca745892404498293
    22 sg:journal.1125588
    23 schema:name Relational IBL in classical music
    24 schema:pagination 5-24
    25 schema:productId N63999f5fae0447e5be3eccdeb21c2276
    26 N8686246cb0514153b6f59bbe3ac6212b
    27 Nd9c50efc301944169b337733594cc9d7
    28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006816744
    29 https://doi.org/10.1007/s10994-006-8260-4
    30 schema:sdDatePublished 2019-04-10T23:23
    31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    32 schema:sdPublisher Nbd5b585be33d4efa9c65ae1d55ce1008
    33 schema:url http://link.springer.com/10.1007%2Fs10994-006-8260-4
    34 sgo:license sg:explorer/license/
    35 sgo:sdDataset articles
    36 rdf:type schema:ScholarlyArticle
    37 N08f03c9a5d7d4a72b2aa94323a8ab02b rdf:first sg:person.011516435301.70
    38 rdf:rest Nc80ba119739a4ab095e77caa0a19d5f6
    39 N61134b5ba2004ab6ab7fddc577af7736 schema:issueNumber 1-3
    40 rdf:type schema:PublicationIssue
    41 N63999f5fae0447e5be3eccdeb21c2276 schema:name dimensions_id
    42 schema:value pub.1006816744
    43 rdf:type schema:PropertyValue
    44 N8686246cb0514153b6f59bbe3ac6212b schema:name readcube_id
    45 schema:value 2078bfec6c133a2ae43ac96917a20ff1e90fb2154fc57835ef3aa2334d5ace4b
    46 rdf:type schema:PropertyValue
    47 Na244daba8fad493ca745892404498293 schema:volumeNumber 64
    48 rdf:type schema:PublicationVolume
    49 Nbd5b585be33d4efa9c65ae1d55ce1008 schema:name Springer Nature - SN SciGraph project
    50 rdf:type schema:Organization
    51 Nc80ba119739a4ab095e77caa0a19d5f6 rdf:first sg:person.013641401431.40
    52 rdf:rest rdf:nil
    53 Nd9c50efc301944169b337733594cc9d7 schema:name doi
    54 schema:value 10.1007/s10994-006-8260-4
    55 rdf:type schema:PropertyValue
    56 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    57 schema:name Information and Computing Sciences
    58 rdf:type schema:DefinedTerm
    59 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    60 schema:name Artificial Intelligence and Image Processing
    61 rdf:type schema:DefinedTerm
    62 sg:journal.1125588 schema:issn 0885-6125
    63 1573-0565
    64 schema:name Machine Learning
    65 rdf:type schema:Periodical
    66 sg:person.011516435301.70 schema:affiliation https://www.grid.ac/institutes/grid.432019.d
    67 schema:familyName Tobudic
    68 schema:givenName Asmir
    69 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011516435301.70
    70 rdf:type schema:Person
    71 sg:person.013641401431.40 schema:affiliation https://www.grid.ac/institutes/grid.432019.d
    72 schema:familyName Widmer
    73 schema:givenName Gerhard
    74 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013641401431.40
    75 rdf:type schema:Person
    76 sg:pub.10.1007/3-540-45006-8_42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046598564
    77 https://doi.org/10.1007/3-540-45006-8_42
    78 rdf:type schema:CreativeWork
    79 sg:pub.10.1007/978-3-540-39917-9_24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023779986
    80 https://doi.org/10.1007/978-3-540-39917-9_24
    81 rdf:type schema:CreativeWork
    82 sg:pub.10.1007/bfb0027331 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014361691
    83 https://doi.org/10.1007/bfb0027331
    84 rdf:type schema:CreativeWork
    85 sg:pub.10.1007/pl00013304 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031362934
    86 https://doi.org/10.1007/pl00013304
    87 rdf:type schema:CreativeWork
    88 https://doi.org/10.1016/0743-1066(94)90035-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002893202
    89 rdf:type schema:CreativeWork
    90 https://doi.org/10.1016/s0004-3702(03)00016-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1035588669
    91 rdf:type schema:CreativeWork
    92 https://doi.org/10.1076/jnmr.31.1.37.8103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009581532
    93 rdf:type schema:CreativeWork
    94 https://doi.org/10.1076/jnmr.32.3.259.16860 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023718011
    95 rdf:type schema:CreativeWork
    96 https://doi.org/10.1080/088395198117686 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011832436
    97 rdf:type schema:CreativeWork
    98 https://doi.org/10.1121/1.402843 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062354132
    99 rdf:type schema:CreativeWork
    100 https://www.grid.ac/institutes/grid.432019.d schema:alternateName Austrian Research Institute for Artificial Intelligence
    101 schema:name Austrian Research Institute for Artificial Intelligence, Vienna
    102 Department of Computational Perception, Johannes Kepler University Linz, and Austrian Research Institute for Artificial Intelligence, Vienna
    103 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...