Multi-Stage Speaker Diarization for Noisy Classrooms

TL;DR

This paper evaluates multi-stage speaker diarization in noisy classrooms, demonstrating that denoising and hybrid VAD models significantly improve accuracy, with the integration of ASR timestamps further reducing errors in challenging acoustic conditions.

Contribution

It introduces a hybrid VAD approach combining ASR timestamps with frame-wise VAD and assesses its effectiveness in noisy classroom environments, advancing diarization techniques.

Findings

Denoising reduces missed speech and improves DER.

Training on combined denoised and noisy data enhances robustness.

Hybrid VAD achieves DER as low as 17% in teacher-student separation.

Abstract

Speaker diarization, the process of identifying "who spoke when" in audio recordings, is essential for understanding classroom dynamics. However, classroom settings present distinct challenges, including poor recording quality, high levels of background noise, overlapping speech, and the difficulty of accurately capturing children's voices. This study investigates the effectiveness of multi-stage diarization models using Nvidia's NeMo diarization pipeline. We assess the impact of denoising on diarization accuracy and compare various voice activity detection (VAD) models, including self-supervised transformer-based frame-wise VAD models. We also explore a hybrid VAD approach that integrates Automatic Speech Recognition (ASR) word-level timestamps with frame-level VAD predictions. We conduct experiments using two datasets from English speaking classrooms to separate teacher vs. student speech and to separate all speakers. Our results show that denoising significantly improves the Diarization Error Rate (DER) by reducing the rate of missed speech. Additionally, training on both denoised and noisy datasets leads to substantial performance gains in noisy conditions. The hybrid VAD model leads to further improvements in speech detection, achieving a DER as low as 17% in teacher-student experiments and 45% in all-speaker experiments. However, we also identified trade-offs between voice activity detection and speaker confusion. Overall, our study highlights the effectiveness of multi-stage diarization models and integrating ASR-based information for enhancing speaker diarization in noisy classroom environments.