CITATION — REFERENCE ENTRY

Detection and Classification of Acoustic Scenes and Events — IEEE Transactions on Multimedia

Revision c1d9ef0d-0d49-4cea-8f54-09754e6a4653 · 11/21/2026, 6:45:58 AM UTC
Key
stowell2015-dcase
Authors
Stowell, Dan; Giannoulis, Dimitrios; Benetos, Emmanouil; Lagrange, Mathieu; Plumbley, Mark D.
Issued
2015-10
Type
article-journal
Container
IEEE Transactions on Multimedia
Volume
17
Issue
10
Pages
1733-1746
Raw CSL JSON
{
  "DOI": "10.1109/TMM.2015.2428998",
  "URL": "https://openaccess.city.ac.uk/id/eprint/13650/",
  "page": "1733-1746",
  "type": "article-journal",
  "issue": "10",
  "title": "Detection and Classification of Acoustic Scenes and Events",
  "author": [
    {
      "given": "Dan",
      "family": "Stowell"
    },
    {
      "given": "Dimitrios",
      "family": "Giannoulis"
    },
    {
      "given": "Emmanouil",
      "family": "Benetos"
    },
    {
      "given": "Mathieu",
      "family": "Lagrange"
    },
    {
      "given": "Mark D.",
      "family": "Plumbley"
    }
  ],
  "issued": {
    "date-parts": [
      [
        2015,
        10
      ]
    ]
  },
  "volume": "17",
  "container-title": "IEEE Transactions on Multimedia"
}

Claims

  1. In 2012-2013 the authors organized the first DCASE challenge, under the IEEE Audio and Acoustic Signal Processing Technical Committee, to stimulate machine listening research on general audio environments.
    "In order to stimulate research in machine listening for general audio environments, in 2012–2013 we organized a research challenge under the auspices of the IEEE Audio and Acoustic Signal Processing Technical Committee: the challenge on Detection and Classification of Acoustic Scenes and Events (DCASE)."
    Locator: page: 1733 (sec. I) · Quote language: en
  2. CASA is often taken to imply an approach that parallels the stages of human auditory processing or mimics observed phenomena of human audition.
    "CASA is often taken to imply an approach which aims either to parallel the stages of processing in human audition, and/or to mimic the observed phenomena of human audition (which may include illusions such as the “missing fundamental”) [7, Chapter 1]."
    Locator: page: 1733 (sec. I) · Quote language: en
  3. Machine listening tasks can be considered to come under the umbrella of CASA, a name that refers back to Bregman's work on human auditory scene analysis.
    "These tasks which we describe as “machine listening” tasks can also be considered to come under the umbrella of computational auditory scene analysis (CASA) [7]. This nomenclature refers back to Bregman’s influential work on human “auditory scene analysis” capabilities [8]"
    Locator: page: 1733 (sec. I) · Quote language: en
  4. One strategy for polyphonic signals is to separate the sources and analyze each separately, an approach analogous to auditory streaming in Bregman's model.
    "Such a component-wise analysis is analogous to the auditory streaming that occurs in Bregman’s model of human audition [8]. ... One strategy to handle polyphonic signals is to perform audio source separation, and then to analyze the resulting signals individually [29], [21]."
    Locator: page: 1734 (sec. II) · Quote language: en
Available in