Dover-lap: A method for combining overlap-aware diarization outputs

Desh Raj, Leibny Paola Garcia-Perera, Zili Huang, Shinji Watanabe, Daniel Povey, Andreas Stolcke, Sanjeev Khudanpur

Research output: Contribution to journalArticlepeer-review

Abstract

Several advances have been made recently towards handling overlapping speech for speaker diarization. Since speech and natural language tasks often benefit from ensemble techniques, we propose an algorithm for combining outputs from such diarization systems through majority voting. Our method, DOVER-Lap, is inspired from the recently proposed DOVER algorithm, but is designed to handle overlapping segments in diarization outputs. We also modify the pair-wise incremental label mapping strategy used in DOVER, and propose an approximation algorithm based on weighted k-partite graph matching, which performs this mapping using a global cost tensor. We demonstrate the strength of our method by combining outputs from diverse systems — clustering-based, region proposal networks, and target-speaker voice activity detection — on AMI and LibriCSS datasets, where it consistently outperforms the single best system. Additionally, we show that DOVER-Lap can be used for late fusion in multichannel diarization, and compares favorably with early fusion methods like beamforming.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - 2020 Nov 3

Keywords

  • Multichannel diarization
  • Overlapped speaker diarization
  • Voting-based methods

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Dover-lap: A method for combining overlap-aware diarization outputs'. Together they form a unique fingerprint.

Cite this