EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Speaker Diarization: A Review of Objectives and Methods

Douglas O’Shaughnessy

Applied Sciences · 2025-02-14 · 15 (4) · 2002

DOI: 10.3390/app15042002 ↗

At a glance

Journal article in Applied Sciences, published online on 2025-02-14. Written by Douglas O’Shaughnessy. Cited 12 times so far (Crossref); 101 references. The full text is freely available (open access, CC BY 4.0). Funded by: NSERC of Canada.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Recorded audio often contains speech from multiple people in conversation. It is useful to label such signals with speaker turns, noting when each speaker is talking and identifying each speaker. This paper discusses how to process speech signals to do such speaker diarization (SD). We examine the nature of speech signals, to identify the possible acoustical features that could assist this clustering task. Traditional speech analysis techniques are reviewed, as well as measures of spectral similarity and clustering. Speech activity detection requires separating speech from background noise in general audio signals. SD may use stochastic models (hidden Markov and Gaussian mixture) and embeddings such as x-vectors. Modern neural machine learning methods are examined in detail. Suggestions are made for future improvements.

Funding

  • NSERC of Canada

Cite

APA

O’Shaughnessy, D. (2025). Speaker Diarization: A Review of Objectives and Methods. Applied Sciences, 15(4), 2002. https://doi.org/10.3390/app15042002

Vancouver

O’Shaughnessy D. Speaker Diarization: A Review of Objectives and Methods. Applied Sciences. 2025;15(4):2002. doi:10.3390/app15042002

BibTeX
@article{OShaughnessy2025,
  author = {O’Shaughnessy, Douglas},
  title = {Speaker Diarization: A Review of Objectives and Methods},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {4},
  pages = {2002},
  doi = {10.3390/app15042002}
}
Start for free →