Skip to main navigation Skip to search Skip to main content

Top-down Approach to Solving Speaker Diarization Errors in diaLogic System

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Speaker diarization, which separates continuous speech signals into utterances associated to different speakers, is critical to any environment that supports team collaboration using models based on data extracted from speech. However, the occurring diarization errors are hard to reduce only through better processing. This paper proposes top-down error correction based on Bayesian prediction about the most likely author of an utterance. Experiments studied the effectiveness of the method.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE International Symposium on Smart Electronic Systems, iSES 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages213-218
Number of pages6
ISBN (Electronic)9798350399226
DOIs
StatePublished - 2022
Event8th IEEE International Symposium on Smart Electronic Systems, iSES 2022 - Warangal, India
Duration: Dec 19 2022Dec 21 2022

Publication series

NameProceedings - 2022 IEEE International Symposium on Smart Electronic Systems, iSES 2022

Conference

Conference8th IEEE International Symposium on Smart Electronic Systems, iSES 2022
Country/TerritoryIndia
CityWarangal
Period12/19/2212/21/22

Keywords

  • Speaker diarization
  • errors
  • top-down correction

Fingerprint

Dive into the research topics of 'Top-down Approach to Solving Speaker Diarization Errors in diaLogic System'. Together they form a unique fingerprint.

Cite this