About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
Odyssey 2012
Conference paper
Online two speaker diarization
Abstract
Short conversations pose some challenges for online diarization due to data sparseness and unbalanced representation of the two speakers. This paper presents our recent advances in online diarization of two-wire telephone conversations, introducing several methods for improving processing efficiency and accuracy on short conversations. Our framework is based on the offline diarization of a conversation prefix followed by an efficient online processing of the rest of the conversation. We use an adaptive prefix size, resulting from the tradeoff between desired efficiency and accuracy as measured by a confidence measure on the diarization output. We further show the enhancement of our online speaker recognition system based on implicit speaker diarization using the proposed techniques.