Conference paper Open Access

Using weakly aligned score–audio pairs to train deep chroma models for cross-modal music retrieval

Frank Zalkow; Meinard Müller

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="">
  <controlfield tag="005">20201106002702.0</controlfield>
  <controlfield tag="001">4245400</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">October 11-16, 2020</subfield>
    <subfield code="g">ISMIR 2020</subfield>
    <subfield code="a">International Society for Music Information Retrieval Conference</subfield>
    <subfield code="c">Montreal, Canada</subfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Meinard Müller</subfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">831590</subfield>
    <subfield code="z">md5:2cbe5c2a931796e4c4ec43019e66e339</subfield>
    <subfield code="u"></subfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u"></subfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-10-11</subfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-ismir</subfield>
    <subfield code="o"></subfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Frank Zalkow</subfield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Using weakly aligned score–audio pairs to train deep chroma models for cross-modal music retrieval</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ismir</subfield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u"></subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2"></subfield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Many music information retrieval tasks involve the comparison of a symbolic score representation with an audio recording. A typical strategy is to compare score–audio pairs based on a common mid-level representation, such as chroma features. Several recent studies demonstrated the effectiveness of deep learning models that learn task-specific mid-level representations from temporally aligned training pairs. However, in practice, there is often a lack of strongly aligned training data, in particular for real-world scenarios. In our study, we use weakly aligned score–audio pairs for training, where only the beginning and end of a score excerpt is annotated in an audio recording, without aligned correspondences in between. To exploit such weakly aligned data, we employ the Connectionist Temporal Classification (CTC) loss to train a deep learning model for computing an enhanced chroma representation. We then apply this model to a cross-modal retrieval task, where we aim at finding relevant audio recordings of Western classical music, given a short monophonic musical theme in symbolic notation as a query. We present systematic experiments that show the effectiveness of the CTC-based model for this theme-based retrieval task.</subfield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.4245399</subfield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="g">184-191</subfield>
    <subfield code="b">ISMIR</subfield>
    <subfield code="a">Montreal, Canada</subfield>
    <subfield code="t">Proceedings of the 21st International Society for Music Information Retrieval Conference</subfield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4245400</subfield>
    <subfield code="2">doi</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
All versions This version
Views 128128
Downloads 5151
Data volume 42.4 MB42.4 MB
Unique views 115115
Unique downloads 4545


Cite as