An utterance comparison model for speaker clustering using factor analysis

We propose a novel utterance comparison model based on probability theory and factor analysis that computes the likelihood of two speech utterances originating from the same speaker. The model depends only on a set of statistics extracted from each utterance and can ef ciently compare utterances using these statistics without requiring the inde nite storage of speech features. We apply the model as a distance metric for speaker clustering in the CALLHOME telephone conversation corpus to achieve competitive results compared to three other known similarity measures: the Generalized Likelihood Ratio, Cross-Likelihood Ratio, and eigenvoice distance.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Woojay Jeon, Changxue Ma, Dusan Macho
• Keywords: Generalized Likelihood Ratio, ICASSP 2011, Signal Processing, Utterance Comparison Model, Utterances