CITATION — REFERENCE ENTRY

Supervised Speech Separation Based on Deep Learning: An Overview — IEEE/ACM Transactions on Audio, Speech, and Language Processing

Revision c5ff8972-d479-445e-b63b-620450ed23de · 11/21/2026, 5:18:23 AM UTC
Key
wang2018-deep-separation
Authors
Wang, DeLiang; Chen, Jitong
Issued
2018-10
Type
article-journal
Container
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Volume
26
Issue
10
Pages
1702-1726
Raw CSL JSON
{
  "DOI": "10.1109/TASLP.2018.2842159",
  "URL": "https://arxiv.org/abs/1708.07524",
  "note": "Claims verified from the arXiv version (1708.07524); page locators refer to the arXiv PDF.",
  "page": "1702-1726",
  "type": "article-journal",
  "issue": "10",
  "title": "Supervised Speech Separation Based on Deep Learning: An Overview",
  "author": [
    {
      "given": "DeLiang",
      "family": "Wang"
    },
    {
      "given": "Jitong",
      "family": "Chen"
    }
  ],
  "issued": {
    "date-parts": [
      [
        2018,
        10
      ]
    ]
  },
  "volume": "26",
  "container-title": "IEEE/ACM Transactions on Audio, Speech, and Language Processing"
}

Claims

  1. Bregman introduced the term auditory scene analysis for the perceptual process that segregates an acoustic mixture and groups the signal from the same source.
    "he introduced the term auditory scene analysis (ASA) to refer to the perceptual process that segregates an acoustic mixture and groups the signal originating from the same sound source."
    Locator: page: 1 (arXiv; §I Introduction) · Quote language: en
  2. With the ideal binary mask as the computational goal, speech separation becomes binary classification, an elementary form of supervised learning.
    "With the IBM as the computational goal, speech separation becomes binary classification, an elementary form of supervised learning."
    Locator: page: 2 (arXiv; §I) · Quote language: en
  3. The ideal binary mask was the first training target in supervised speech separation but not the only one.
    "Although it served as the first training target in supervised speech separation, the IBM is by no means the only training target"
    Locator: page: 2 (arXiv; §I) · Quote language: en
Available in