Publication: Offline speaker segmentation using genetic algorithms and mutual information
Loading...
Identifiers
Publication date
2006-04
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Export
Abstract
We present an evolutionary approach to speaker segmentation, an activity that is especially important prior to speaker recognition and audio content analysis tasks. Our approach consists of a genetic algorithm (GA), which encodes possible segmentations of an audio record, and a measure of mutual information between the audio data and possible segmentations, which is used as fitness function for the GA. We introduce a compact encoding of the problem into the GA which reduces the length of the GA individuals and improves the GA convergence properties. Our algorithm has been tested on the segmentation of real audio data, and its performance has been compared with several existing algorithms for speaker segmentation, obtaining very good results in all test problems.
Description
Keywords
Genetic Algorithms (GAs), Mutual information, Speaker segmentation, Unsupervised learning
Bibliographic citation
Salcedo-Sanz, S., Gallardo-Antolin, A., Leiva-Murillo, J. & Bousono-Calzon, C. (2006). Offline speaker segmentation using genetic algorithms and mutual information. IEEE Transactions on Evolutionary Computation, 10(2), pp. 175–186.