A Study of the Cosine Distance-Based Mean Shift for Telephone Speech Diarization

  • Authors:
  • Mohammed Senoussaoui;Patrick Kenny;Themos Stafylakis;Pierre Dumouchel

  • Affiliations:
  • Centre de Rech. Inf. de Montreal (CRIM), Montréal, QC, Canada;Centre de Rech. Inf. de Montreal (CRIM), Montréal, QC, Canada;Centre de Rech. Inf. de Montreal (CRIM), Montréal, QC, Canada;Ecole de Technol. Super. (ETS), Montréal, QC, Canada

  • Venue:
  • IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

Speaker clustering is a crucial step for speaker diarization. The short duration of speech segments in telephone speech dialogue and the absence of prior information on the number of clusters dramatically increase the difficulty of this problem in diarizing spontaneous telephone speech conversations. We propose a simple iterative Mean Shift algorithm based on the cosine distance to perform speaker clustering under these conditions. Two variants of the cosine distance Mean Shift are compared in an exhaustive practical study. We report state of the art results as measured by the Diarization Error Rate and the Number of Detected Speakers on the LDC CallHome telephone corpus.