CITATION — REFERENCE ENTRY

Separation of speech by computational auditory scene analysis — Speech Enhancement

Revision e342e630-acf5-4af5-96c1-9e863d6b985b · 11/21/2026, 6:45:48 AM UTC
Key
brown2005-casa
Authors
Brown, Guy J.; Wang, DeLiang
Issued
2005
Type
chapter
Container
Speech Enhancement
Publisher
Springer
Pages
371-402
Raw CSL JSON
{
  "DOI": "10.1007/3-540-27489-8_16",
  "URL": "https://pnlwang.github.io/papers/Brown-Wang05.pdf",
  "page": "371-402",
  "type": "chapter",
  "title": "Separation of speech by computational auditory scene analysis",
  "author": [
    {
      "given": "Guy J.",
      "family": "Brown"
    },
    {
      "given": "DeLiang",
      "family": "Wang"
    }
  ],
  "editor": [
    {
      "given": "J.",
      "family": "Benesty"
    },
    {
      "given": "S.",
      "family": "Makino"
    },
    {
      "given": "J.",
      "family": "Chen"
    }
  ],
  "issued": {
    "date-parts": [
      [
        2005
      ]
    ]
  },
  "publisher": "Springer",
  "container-title": "Speech Enhancement"
}

Claims

  1. Some CASA systems are closely modeled on the known stages of auditory processing, while others adopt a more functional approach.
    "Some CASA systems are closely modelled on the known stages of auditory processing, whereas others adopt a more functional approach."
    Locator: page: 371 (Abstract) · Quote language: en
  2. Weintraub gave the first computational implementation of Licklider's theory of pitch, calling it an auto-coincidence representation; Slaney and Lyon later introduced the term correlogram.
    "The first computational implementation of Licklider’s theory was described by Weintraub [67], who referred to it as an ‘auto-coincidence’ representation; subsequently, Slaney and Lyon [57] introduced the term correlogram."
    Locator: page: 376 (sec. 16.3.2) · Quote language: en
  3. Computational auditory scene analysis is the field of study that attempts to replicate auditory scene analysis, the human ability to form perceptual representations of the sources in an acoustic mixture, in machines.
    "The term auditory scene analysis (ASA) refers to the ability of human listeners to form perceptual representations of the constituent sources in an acoustic mixture, as in the well-known ‘cocktail party’ effect. Accordingly, computational auditory scene analysis (CASA) is the field of study which attempts to replicate ASA in machines."
    Locator: page: 371 (Abstract) · Quote language: en
  4. The gammatone filter, an approximation to the physiologically recorded impulse responses of auditory nerve fibers, is often used in CASA's peripheral processing.
    "The ‘gammatone’ filter is often used, which is an approximation to the physiologically-recorded impulse responses of auditory nerve fibres"
    Locator: page: 375 (sec. 16.3.1) · Quote language: en
  5. Weintraub was the first to use a time-frequency mask in a CASA system; mask values may be binary or real-valued.
    "The mask values may be binary or real-valued. Weintraub [67] was the first to use this approach in a CASA system"
    Locator: page: 374 (sec. 16.3) · Quote language: en
Available in