Conference paper Open Access

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

Frank Zalkow; Meinard Müller


JSON-LD (schema.org) Export

{
  "description": "Many music information retrieval tasks involve the comparison of a symbolic score representation with an audio recording. A typical strategy is to compare score\u2013audio 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\u2013audio 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.", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "@type": "Person", 
      "name": "Frank Zalkow"
    }, 
    {
      "@type": "Person", 
      "name": "Meinard M\u00fcller"
    }
  ], 
  "headline": "Using weakly aligned score\u2013audio pairs to train deep chroma models for cross-modal music retrieval", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2020-10-11", 
  "url": "https://zenodo.org/record/4245400", 
  "@type": "ScholarlyArticle", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.4245400", 
  "@id": "https://doi.org/10.5281/zenodo.4245400", 
  "workFeatured": {
    "url": "https://www.ismir2020.net/", 
    "alternateName": "ISMIR 2020", 
    "location": "Montreal, Canada", 
    "@type": "Event", 
    "name": "International Society for Music Information Retrieval Conference"
  }, 
  "name": "Using weakly aligned score\u2013audio pairs to train deep chroma models for cross-modal music retrieval"
}
128
51
views
downloads
All versions This version
Views 128128
Downloads 5151
Data volume 42.4 MB42.4 MB
Unique views 115115
Unique downloads 4545

Share

Cite as