By the same authors

An Improved Speaker Diarization System

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Author(s)

Department/unit(s)

Publication details

Title of host publicationINTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4
DatePublished - 2007
Pages1253-1256
Number of pages4
PublisherISCA-INST SPEECH COMMUNICATION ASSOC
Place of PublicationBAIXAS
Original languageEnglish
ISBN (Print)978-1-60560-316-2

Abstract

This paper describes an automatic speaker diarization system for natural, multi-speaker meeting conversations. Only one central microphone is used to record the meeting. The new system is robust to different acoustic environments - it requires neither pre-training models nor development sets to initialize the parameters. The new system determines the model complexity automatically. It adapts the segment model from a universal background model, and uses the cross-likelihood ratio instead of the Bayesian Information Criterion (BIC) for merging. Finally it uses an intra-cluster/inter-cluster ratio as the stopping criterion. Together this reduces the speaker diarization error rate from 21.76% to 17.21% compared with the baseline system [1].

    Research areas

  • speaker diarization, model complexity selection, MIXTURE-MODELS

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations