A robust speaker clustering algorithm

Abstract

In this paper, we present a novel speaker segmentation and clustering algorithm. The algorithm automatically performs both speaker segmentation and clustering without any prior knowledge of the identities or the number of speakers. Our algorithm uses "standard" speech processing components and techniques such as HMM, agglomerative clustering, and the Bayesian information criterion. However, we have combined and modified these so as to produce an algorithm with the following advantages: no threshold adjustment requirements; no need for training/development data; and robustness to different data conditions. This paper also reports the performance of this algorithm on different datasets released by the USA National Institute of Standards and Technology (NIST) with different initial conditions and parameter settings. The consistently low speaker-diarization error rate clearly indicates the robustness and utility of the algorithm.