Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free

TL;DR

This paper introduces an unsupervised speaker diarization method that is language-agnostic, overlap-aware, and tuning-free, significantly improving accuracy on podcast data without needing prior speaker count information.

Contribution

The proposed approach is novel in being unsupervised, language-agnostic, and overlap-aware, eliminating the need for tuning or speaker number estimation.

Findings

79% improvement on purity scores

34% improvement on F-score

Effective on podcast data

Abstract

Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data.