Robust Acoustic Domain Identification with its Application to Speaker Diarization

TL;DR

This paper introduces a simple, efficient acoustic domain identification method using speaker embeddings to improve speaker diarization performance across diverse recording environments, achieving significant DER reductions.

Contribution

The paper presents a novel acoustic domain identification approach integrated with speaker diarization, enhancing performance by domain-specific threshold optimization.

Findings

Over 5% relative DER improvement in core conditions

Over 8% relative DER improvement in full conditions

Effective use of speaker embeddings for domain classification

Abstract

With the rise in multimedia content over the years, more variety is observed in the recording environments of audio. An audio processing system might benefit when it has a module to identify the acoustic domain at its front-end. In this paper, we demonstrate the idea of \emph{acoustic domain identification} (ADI) for \emph{speaker diarization}. For this, we first present a detailed study of the various domains of the third DIHARD challenge highlighting the factors that differentiated them from each other. Our main contribution is to develop a simple and efficient solution for ADI. In the present work, we explore speaker embeddings for this task. Next, we integrate the ADI module with the speaker diarization framework of the DIHARD III challenge. The performance substantially improved over that of the baseline when the thresholds for agglomerative hierarchical clustering were optimized according to the respective domains. We achieved a relative improvement of more than $5\%$ and $8\%$ in DER for core and full conditions, respectively, on Track 1 of the DIHARD III evaluation set.