The BUCEA Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2022

TL;DR

This paper presents the BUCEA speaker diarization system for VoxCeleb Challenge 2022, combining multiple modules like VAD, embedding extraction, clustering, and overlap detection, achieving low error rates.

Contribution

The paper introduces a comprehensive speaker diarization system with novel fusion and overlap handling methods for improved accuracy.

Findings

DER of 5.48% on VoxSRC 2022 test set

JER of 32.1% on VoxSRC 2022 test set

Effective system fusion using Dover-LAP

Abstract

This paper describes the BUCEA speaker diarization system for the 2022 VoxCeleb Speaker Recognition Challenge. Voxsrc-22 provides the development set and test set of VoxConverse, and we mainly use the test set of VoxConverse for parameter adjustment. Our system consists of several modules, including speech activity detection (VAD), speaker embedding extractor, clustering methods, overlapping speech detection (OSD), and result fusion. Without considering overlap, the Dover-LAP (short for Diarization Output Voting Error Reduction) method was applied to system fusion, and overlapping speech detection and processing were finally carried out. Our best system achieves a diarization error rate (DER) of 5.48% and a Jaccard error rate (JER) of 32.1% on the VoxSRC 2022 evaluation set respectively.