Presentation Open Access

ISMIR 2019 tutorial: waveform-based music processing with deep learning

Jongpil Lee; Jordi Pons; Sander Dieleman


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/5e92b682-8ae7-4020-8992-67d91f8252ef/ISMIR%202019%20tutorial_%20waveform-based%20music%20processing%20with%20deep%20learning.pdf"
      }, 
      "checksum": "md5:cbba74f5bc737ce56e641f635729cdd1", 
      "bucket": "5e92b682-8ae7-4020-8992-67d91f8252ef", 
      "key": "ISMIR 2019 tutorial_ waveform-based music processing with deep learning.pdf", 
      "type": "pdf", 
      "size": 13731274
    }
  ], 
  "owners": [
    26581
  ], 
  "doi": "10.5281/zenodo.3529714", 
  "stats": {
    "version_unique_downloads": 311.0, 
    "unique_views": 471.0, 
    "views": 538.0, 
    "version_views": 544.0, 
    "unique_downloads": 310.0, 
    "version_unique_views": 477.0, 
    "volume": 5231615394.0, 
    "version_downloads": 382.0, 
    "downloads": 381.0, 
    "version_volume": 5245346668.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3529714", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3529713", 
    "bucket": "https://zenodo.org/api/files/5e92b682-8ae7-4020-8992-67d91f8252ef", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3529713.svg", 
    "html": "https://zenodo.org/record/3529714", 
    "latest_html": "https://zenodo.org/record/3529714", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3529714.svg", 
    "latest": "https://zenodo.org/api/records/3529714"
  }, 
  "conceptdoi": "10.5281/zenodo.3529713", 
  "created": "2019-11-05T17:59:52.622818+00:00", 
  "updated": "2020-01-20T17:33:08.858385+00:00", 
  "conceptrecid": "3529713", 
  "revision": 7, 
  "id": 3529714, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3529714", 
    "description": "<p>A common practice when processing music signals with deep learning is to transform the raw waveform input into a time-frequency representation. This pre-processing step allows having less variable and more interpretable input signals. However, along that process, one can limit the model&#39;s learning capabilities since potentially useful information (like the phase or high frequencies) is discarded. In order to overcome the potential limitations associated with such pre-processing, researchers have been exploring waveform-level music processing techniques, and many advances have been made with the recent advent of deep learning.</p>\n\n<p>In this tutorial, we introduce three main research areas where waveform-based music processing can have a substantial impact:</p>\n\n<p>1) Classification: waveform-based music classifiers have the potential to simplify production and research pipelines.</p>\n\n<p>2) Source separation: making possible waveform-based music source separation would allow overcoming some historical challenges associated with discarding the phase.</p>\n\n<p>3) Generation: waveform-level music generation would enable, e.g., to directly synthesize expressive music.</p>\n\n<p><a href=\"https://docs.google.com/presentation/d/1_ezZXDkyhp9USAYMc5oKJCkUrUhBfo-Di8H8IfypGBM/edit?usp=sharing\">Link to the original Google Slides</a></p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "ISMIR 2019 tutorial: waveform-based music processing with deep learning", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3529713"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3529714"
          }
        }
      ]
    }, 
    "publication_date": "2019-11-04", 
    "creators": [
      {
        "affiliation": "KAIST", 
        "name": "Jongpil Lee"
      }, 
      {
        "affiliation": "Dolby Laboratories", 
        "name": "Jordi Pons"
      }, 
      {
        "affiliation": "DeepMind", 
        "name": "Sander Dieleman"
      }
    ], 
    "meeting": {
      "acronym": "ISMIR", 
      "url": "https://ismir2019.ewi.tudelft.nl/?q=node/1", 
      "session": "Tutorial", 
      "place": "Delft", 
      "title": "20th annual conference of the International Society for Music Information Retrieval"
    }, 
    "access_right": "open", 
    "resource_type": {
      "type": "presentation", 
      "title": "Presentation"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3529713", 
        "relation": "isVersionOf"
      }
    ]
  }
}
544
382
views
downloads
All versions This version
Views 544538
Downloads 382381
Data volume 5.2 GB5.2 GB
Unique views 477471
Unique downloads 311310

Share

Cite as