Offline speaker segmentation using genetic algorithms and mutual information

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 inf...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on evolutionary computation 2006-04, Vol.10 (2), p.175-186
Main Authors: Salcedo-Sanz, S., Gallardo-Antolin, A., Leiva-Murillo, J.M., Bousono-Calzon, C.
Format: Article
Language:English
Subjects:
Acoustics
Algorithms
Applied sciences
Artificial intelligence
Audio data
Audio databases
Audition
Biological and medical sciences
Computer science
control theory
systems
Convergence
Exact sciences and technology
Fitness
Fundamental and applied biological sciences. Psychology
Fundamental areas of phenomenology (including applications)
Genetic algorithms
Genetic algorithms (GAs)
Hidden Markov models
Image segmentation
Indexing
Information retrieval
Learning and adaptive systems
Mathematical analysis
Mutual information
Perception
Physics
Psychology. Psychoanalysis. Psychiatry
Psychology. Psychophysiology
Segmentation
speaker segmentation
Tasks
Testing
Transduction
acoustical devices for the generation and reproduction of sound
Unsupervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1089-778X
1941-0026
DOI:10.1109/TEVC.2005.857079