TCG CREST System Description for the DISPLACE-M Challenge

TL;DR

This paper describes the TCG CREST system for speaker diarization in noisy medical conversations, comparing different VAD and clustering methods, and achieving significant error rate improvements in the DISPLACE-M challenge.

Contribution

It introduces a hybrid neural diarization system and novel spectral clustering variants, demonstrating improved performance over baseline methods in challenging real-world scenarios.

Findings

Diarizen system improved DER by approximately 39% over baseline.

Best system achieved DER of 10.37% on development set.

Team ranked fifth out of eleven in the challenge.

Abstract

This report presents the TCG CREST system description for Track 1 (Speaker Diarization) of the DISPLACE-M challenge, focusing on naturalistic medical conversations in noisy rural-healthcare scenarios. Our study evaluates the impact of various voice activity detection (VAD) methods and advanced clustering algorithms on overall speaker diarization (SD) performance. We compare and analyze two SD frameworks: a modular pipeline utilizing SpeechBrain with ECAPA-TDNN embeddings, and a state-of-the-art (SOTA) hybrid end-to-end neural diarization system, Diarizen, built on top of a pre-trained WavLM. With these frameworks, we explore diverse clustering techniques, including agglomerative hierarchical clustering (AHC), and multiple novel variants of spectral clustering, such as SC-adapt, SC-PNA, and SC-MK. Experimental results demonstrate that the Diarizen system provides an approximate $39\%$ relative improvement in the diarization error rate (DER) on the post-evaluation analysis of Phase~I compared to the SpeechBrain baseline. Our best-performing submitted system employing the Diarizen baseline with AHC employing a median filtering with a larger context window of $29$ achieved a DER of 10.37\% on the development and 9.21\% on the evaluation sets, respectively. Our team ranked fifth out of the 11 participating teams after the Phase~I evaluation.