Analysis of the BUT Diarization System for VoxConverse Challenge
This is an incremental improvement for speaker diarization in audio processing, specifically for challenge participants and researchers.
The paper tackles speaker diarization on the VoxConverse dataset by developing a system with multiple steps including clustering and Bayesian modeling, achieving second place in diarization error rate and first in Jaccard error rate in the VoxCeleb challenge.
This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. The system consists of signal pre-processing, voice activity detection, speaker embedding extraction, an initial agglomerative hierarchical clustering followed by diarization using a Bayesian hidden Markov model, a reclustering step based on per-speaker global embeddings and overlapped speech detection and handling. We provide comparisons for each of the steps and share the implementation of the most relevant modules of our system. Our system scored second in the challenge in terms of the primary metric (diarization error rate) and first according to the secondary metric (Jaccard error rate).