ISCA Archive Interspeech 2022
ISCA Archive Interspeech 2022

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

Md Iftekhar Tanveer, Diego Casabuena, Jussi Karlgren, Rosie Jones

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.