Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free
This addresses the problem of speaker diarization in multilingual and overlapping conversational audio for applications like podcast analysis, though it is incremental as it builds on existing unsupervised techniques.
The paper tackles unsupervised speaker diarization for podcasts by proposing a language-agnostic, overlap-aware method that does not require tuning or speaker count information, achieving a 79% improvement in purity scores and 34% in F-score compared to Google Cloud Platform.
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.