Skip to main navigation Skip to search Skip to main content

Compensation for inter-frame correlations in speaker diarization and recognition

  • Computer Research Institute of Montreal
  • École de technologie supérieure

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

6 Citations (Scopus)

Abstract

In this paper, we introduce the concept of the effective sample size to speaker diarization and recognition. We show why the use of the nominal sample size is inadequate to feature streams that exhibit inter-frame correlations and how it adversely affects inference. We then discuss the effective sample size, that is the sample size of a set of independent observations that carry the equivalent amount of statistical information about the model parameters and how the scaling factor can be estimated. Our experiments on speaker diarization show that once the effective sample size is adopted, state-of-the-art results can be attained even with single Gaussians and Hierarchical Clustering, and even when the scaling factor is set to be common for all utterances. On speaker recognition, encouraging results are reported on NIST-2010 using iVectors and PLDA.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages7731-7735
Number of pages5
DOIs
Publication statusPublished - 18 Oct 2013
Externally publishedYes
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 26 May 2013 → 31 May 2013

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Country/TerritoryCanada
CityVancouver, BC
Period26/05/13 → 31/05/13

Keywords

  • Bayesian methods
  • Clustering methods
  • Speaker recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Compensation for inter-frame correlations in speaker diarization and recognition'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this