Basic filters for convolutional neural networks applied to music: Training or design? View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-09-24

AUTHORS

Monika Dörfler, Thomas Grill, Roswitha Bammer, Arthur Flexer

ABSTRACT

When convolutional neural networks are used to tackle learning problems based on music or other time series, raw one-dimensional data are commonly preprocessed to obtain spectrogram or mel-spectrogram coefficients, which are then used as input to the actual neural network. In this contribution, we investigate, both theoretically and experimentally, the influence of this pre-processing step on the network’s performance and pose the question whether replacing it by applying adaptive or learned filters directly to the raw data can improve learning success. The theoretical results show that approximately reproducing mel-spectrogram coefficients by applying adaptive filters and subsequent time-averaging on the squared amplitudes is in principle possible. We also conducted extensive experimental work on the task of singing voice detection in music. The results of these experiments show that for classification based on convolutional neural networks the features obtained from adaptive filter banks followed by time-averaging the squared modulus of the filters’ output perform better than the canonical Fourier transform-based mel-spectrogram coefficients. Alternative adaptive approaches with center frequencies or time-averaging lengths learned from training data perform equally well. More... »

PAGES

1-14

References to SciGraph publications

  • 1998. Quantization of TF lattice-invariant operators on elementary LCA groups in GABOR ANALYSIS AND ALGORITHMS
  • 2010-04. Representation of Operators in the Time-Frequency Domain and Generalized Gabor Multipliers in JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS
  • 2003. A First Survey of Gabor Multipliers in ADVANCES IN GABOR ANALYSIS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00521-018-3704-x

    DOI

    http://dx.doi.org/10.1007/s00521-018-3704-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1107206564


    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": "University of Vienna", 
              "id": "https://www.grid.ac/institutes/grid.10420.37", 
              "name": [
                "Faculty of Mathematics, University of Vienna, 1090, Vienna, Austria"
              ], 
              "type": "Organization"
            }, 
            "familyName": "D\u00f6rfler", 
            "givenName": "Monika", 
            "id": "sg:person.014645226405.64", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014645226405.64"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Austrian Research Institute for Artificial Intelligence", 
              "id": "https://www.grid.ac/institutes/grid.432019.d", 
              "name": [
                "Austrian Research Institute for Artificial Intelligence (OFAI), Freyung 6/6, 1010, Vienna, Austria"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Grill", 
            "givenName": "Thomas", 
            "id": "sg:person.014465251537.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014465251537.06"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Vienna", 
              "id": "https://www.grid.ac/institutes/grid.10420.37", 
              "name": [
                "Faculty of Mathematics, University of Vienna, 1090, Vienna, Austria"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bammer", 
            "givenName": "Roswitha", 
            "id": "sg:person.07575117516.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07575117516.53"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Austrian Research Institute for Artificial Intelligence", 
              "id": "https://www.grid.ac/institutes/grid.432019.d", 
              "name": [
                "Austrian Research Institute for Artificial Intelligence (OFAI), Freyung 6/6, 1010, Vienna, Austria"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Flexer", 
            "givenName": "Arthur", 
            "id": "sg:person.0757053000.20", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757053000.20"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1002/cpa.21413", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007916775"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00041-009-9085-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015451988", 
              "https://doi.org/10.1007/s00041-009-9085-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00041-009-9085-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015451988", 
              "https://doi.org/10.1007/s00041-009-9085-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00041-009-9085-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015451988", 
              "https://doi.org/10.1007/s00041-009-9085-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1098/rsta.2015.0203", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025731078"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4612-0133-5_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026884934", 
              "https://doi.org/10.1007/978-1-4612-0133-5_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4612-0133-5_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026884934", 
              "https://doi.org/10.1007/978-1-4612-0133-5_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1076/jnmr.30.1.3.7124", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031126004"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.cam.2011.09.011", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039070048"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4612-2016-9_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1051968194", 
              "https://doi.org/10.1007/978-1-4612-2016-9_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/5.726791", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061179979"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/msp.2013.2266075", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061423995"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tasl.2012.2234114", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061517060"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsp.2014.2326991", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061804378"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tit.2017.2718963", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1087310362"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tit.2017.2756880", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092024944"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icmla.2012.220", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093383576"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/sampta.2017.8024473", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093496568"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icassp.2014.6854950", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093627962"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icassp.2015.7177944", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093812481"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mlsp.2016.7738895", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094033515"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icassp.2014.6854953", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094064816"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/sampta.2017.8024444", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094073520"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/isit.2016.7541482", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094640937"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/sampta.2017.8024472", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095309806"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tetci.2017.2771298", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101728912"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taslp.2018.2825108", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103270982"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-09-24", 
        "datePublishedReg": "2018-09-24", 
        "description": "When convolutional neural networks are used to tackle learning problems based on music or other time series, raw one-dimensional data are commonly preprocessed to obtain spectrogram or mel-spectrogram coefficients, which are then used as input to the actual neural network. In this contribution, we investigate, both theoretically and experimentally, the influence of this pre-processing step on the network\u2019s performance and pose the question whether replacing it by applying adaptive or learned filters directly to the raw data can improve learning success. The theoretical results show that approximately reproducing mel-spectrogram coefficients by applying adaptive filters and subsequent time-averaging on the squared amplitudes is in principle possible. We also conducted extensive experimental work on the task of singing voice detection in music. The results of these experiments show that for classification based on convolutional neural networks the features obtained from adaptive filter banks followed by time-averaging the squared modulus of the filters\u2019 output perform better than the canonical Fourier transform-based mel-spectrogram coefficients. Alternative adaptive approaches with center frequencies or time-averaging lengths learned from training data perform equally well.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s00521-018-3704-x", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1104357", 
            "issn": [
              "0941-0643", 
              "1433-3058"
            ], 
            "name": "Neural Computing and Applications", 
            "type": "Periodical"
          }
        ], 
        "name": "Basic filters for convolutional neural networks applied to music: Training or design?", 
        "pagination": "1-14", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "1af000d31c2ba834ce440f7614d873be55fcc0d34be938e5ea805afc2ef00177"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00521-018-3704-x"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1107206564"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00521-018-3704-x", 
          "https://app.dimensions.ai/details/publication/pub.1107206564"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T15:06", 
        "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_8663_00000539.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007%2Fs00521-018-3704-x"
      }
    ]
     

    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/s00521-018-3704-x'

    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/s00521-018-3704-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00521-018-3704-x'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00521-018-3704-x'


     

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

    154 TRIPLES      21 PREDICATES      48 URIs      16 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00521-018-3704-x schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Na06f519f2f71438db633f487dcb4ae36
    4 schema:citation sg:pub.10.1007/978-1-4612-0133-5_5
    5 sg:pub.10.1007/978-1-4612-2016-9_8
    6 sg:pub.10.1007/s00041-009-9085-x
    7 https://doi.org/10.1002/cpa.21413
    8 https://doi.org/10.1016/j.cam.2011.09.011
    9 https://doi.org/10.1076/jnmr.30.1.3.7124
    10 https://doi.org/10.1098/rsta.2015.0203
    11 https://doi.org/10.1109/5.726791
    12 https://doi.org/10.1109/icassp.2014.6854950
    13 https://doi.org/10.1109/icassp.2014.6854953
    14 https://doi.org/10.1109/icassp.2015.7177944
    15 https://doi.org/10.1109/icmla.2012.220
    16 https://doi.org/10.1109/isit.2016.7541482
    17 https://doi.org/10.1109/mlsp.2016.7738895
    18 https://doi.org/10.1109/msp.2013.2266075
    19 https://doi.org/10.1109/sampta.2017.8024444
    20 https://doi.org/10.1109/sampta.2017.8024472
    21 https://doi.org/10.1109/sampta.2017.8024473
    22 https://doi.org/10.1109/tasl.2012.2234114
    23 https://doi.org/10.1109/taslp.2018.2825108
    24 https://doi.org/10.1109/tetci.2017.2771298
    25 https://doi.org/10.1109/tit.2017.2718963
    26 https://doi.org/10.1109/tit.2017.2756880
    27 https://doi.org/10.1109/tsp.2014.2326991
    28 schema:datePublished 2018-09-24
    29 schema:datePublishedReg 2018-09-24
    30 schema:description When convolutional neural networks are used to tackle learning problems based on music or other time series, raw one-dimensional data are commonly preprocessed to obtain spectrogram or mel-spectrogram coefficients, which are then used as input to the actual neural network. In this contribution, we investigate, both theoretically and experimentally, the influence of this pre-processing step on the network’s performance and pose the question whether replacing it by applying adaptive or learned filters directly to the raw data can improve learning success. The theoretical results show that approximately reproducing mel-spectrogram coefficients by applying adaptive filters and subsequent time-averaging on the squared amplitudes is in principle possible. We also conducted extensive experimental work on the task of singing voice detection in music. The results of these experiments show that for classification based on convolutional neural networks the features obtained from adaptive filter banks followed by time-averaging the squared modulus of the filters’ output perform better than the canonical Fourier transform-based mel-spectrogram coefficients. Alternative adaptive approaches with center frequencies or time-averaging lengths learned from training data perform equally well.
    31 schema:genre research_article
    32 schema:inLanguage en
    33 schema:isAccessibleForFree true
    34 schema:isPartOf sg:journal.1104357
    35 schema:name Basic filters for convolutional neural networks applied to music: Training or design?
    36 schema:pagination 1-14
    37 schema:productId N75851399400a4f51832fbe8a63afb0a2
    38 N84b016af3fad48cdbfdbaa5d0fbacac4
    39 N88094759566846e3a40e4586bc62e371
    40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107206564
    41 https://doi.org/10.1007/s00521-018-3704-x
    42 schema:sdDatePublished 2019-04-10T15:06
    43 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    44 schema:sdPublisher N700fe5071b264138960145973a5e51fe
    45 schema:url http://link.springer.com/10.1007%2Fs00521-018-3704-x
    46 sgo:license sg:explorer/license/
    47 sgo:sdDataset articles
    48 rdf:type schema:ScholarlyArticle
    49 N48e9622352ae431194f7e2cf6a6e429c rdf:first sg:person.07575117516.53
    50 rdf:rest N6c144ad8cc8c4fa2883f31d24faa7637
    51 N6c144ad8cc8c4fa2883f31d24faa7637 rdf:first sg:person.0757053000.20
    52 rdf:rest rdf:nil
    53 N700fe5071b264138960145973a5e51fe schema:name Springer Nature - SN SciGraph project
    54 rdf:type schema:Organization
    55 N75851399400a4f51832fbe8a63afb0a2 schema:name doi
    56 schema:value 10.1007/s00521-018-3704-x
    57 rdf:type schema:PropertyValue
    58 N84b016af3fad48cdbfdbaa5d0fbacac4 schema:name dimensions_id
    59 schema:value pub.1107206564
    60 rdf:type schema:PropertyValue
    61 N88094759566846e3a40e4586bc62e371 schema:name readcube_id
    62 schema:value 1af000d31c2ba834ce440f7614d873be55fcc0d34be938e5ea805afc2ef00177
    63 rdf:type schema:PropertyValue
    64 N8b9b14a17c3c4ecb851840b476519f7c rdf:first sg:person.014465251537.06
    65 rdf:rest N48e9622352ae431194f7e2cf6a6e429c
    66 Na06f519f2f71438db633f487dcb4ae36 rdf:first sg:person.014645226405.64
    67 rdf:rest N8b9b14a17c3c4ecb851840b476519f7c
    68 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    69 schema:name Information and Computing Sciences
    70 rdf:type schema:DefinedTerm
    71 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    72 schema:name Artificial Intelligence and Image Processing
    73 rdf:type schema:DefinedTerm
    74 sg:journal.1104357 schema:issn 0941-0643
    75 1433-3058
    76 schema:name Neural Computing and Applications
    77 rdf:type schema:Periodical
    78 sg:person.014465251537.06 schema:affiliation https://www.grid.ac/institutes/grid.432019.d
    79 schema:familyName Grill
    80 schema:givenName Thomas
    81 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014465251537.06
    82 rdf:type schema:Person
    83 sg:person.014645226405.64 schema:affiliation https://www.grid.ac/institutes/grid.10420.37
    84 schema:familyName Dörfler
    85 schema:givenName Monika
    86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014645226405.64
    87 rdf:type schema:Person
    88 sg:person.0757053000.20 schema:affiliation https://www.grid.ac/institutes/grid.432019.d
    89 schema:familyName Flexer
    90 schema:givenName Arthur
    91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0757053000.20
    92 rdf:type schema:Person
    93 sg:person.07575117516.53 schema:affiliation https://www.grid.ac/institutes/grid.10420.37
    94 schema:familyName Bammer
    95 schema:givenName Roswitha
    96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07575117516.53
    97 rdf:type schema:Person
    98 sg:pub.10.1007/978-1-4612-0133-5_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026884934
    99 https://doi.org/10.1007/978-1-4612-0133-5_5
    100 rdf:type schema:CreativeWork
    101 sg:pub.10.1007/978-1-4612-2016-9_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051968194
    102 https://doi.org/10.1007/978-1-4612-2016-9_8
    103 rdf:type schema:CreativeWork
    104 sg:pub.10.1007/s00041-009-9085-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1015451988
    105 https://doi.org/10.1007/s00041-009-9085-x
    106 rdf:type schema:CreativeWork
    107 https://doi.org/10.1002/cpa.21413 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007916775
    108 rdf:type schema:CreativeWork
    109 https://doi.org/10.1016/j.cam.2011.09.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039070048
    110 rdf:type schema:CreativeWork
    111 https://doi.org/10.1076/jnmr.30.1.3.7124 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031126004
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.1098/rsta.2015.0203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025731078
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1109/icassp.2014.6854950 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093627962
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1109/icassp.2014.6854953 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094064816
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1109/icassp.2015.7177944 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093812481
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1109/icmla.2012.220 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093383576
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1109/isit.2016.7541482 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094640937
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/mlsp.2016.7738895 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094033515
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/msp.2013.2266075 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061423995
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/sampta.2017.8024444 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094073520
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/sampta.2017.8024472 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095309806
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/sampta.2017.8024473 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093496568
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1109/tasl.2012.2234114 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517060
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1109/taslp.2018.2825108 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103270982
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1109/tetci.2017.2771298 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101728912
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1109/tit.2017.2718963 schema:sameAs https://app.dimensions.ai/details/publication/pub.1087310362
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1109/tit.2017.2756880 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092024944
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1109/tsp.2014.2326991 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061804378
    148 rdf:type schema:CreativeWork
    149 https://www.grid.ac/institutes/grid.10420.37 schema:alternateName University of Vienna
    150 schema:name Faculty of Mathematics, University of Vienna, 1090, Vienna, Austria
    151 rdf:type schema:Organization
    152 https://www.grid.ac/institutes/grid.432019.d schema:alternateName Austrian Research Institute for Artificial Intelligence
    153 schema:name Austrian Research Institute for Artificial Intelligence (OFAI), Freyung 6/6, 1010, Vienna, Austria
    154 rdf:type schema:Organization
     




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


    ...