Abstract
Genetic Algorithms have become increasingly appreciated as an easy-to-use general method for a wide range of optimization problems. Their principle consists of maintaining and manipulating a population of solutions and implementing a ‘survival of the fittest’ strategy in their search for better solutions. In this chapter, GAs are combined with a signal subspace decomposition technique to enhance speech that is severely degraded by noise. To evaluate the effectiveness of this hybrid approach, a set of continuous speech recognition experiments is carried out by using the NTIMIT telephone speech database.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Selouani, SA. (2011). Evolutionary Techniques for Speech Enhancement. In: Speech Processing and Soft Computing. SpringerBriefs in Electrical and Computer Engineering(). Springer, New York, NY. https://doi.org/10.1007/978-1-4419-9685-5_5
Download citation
DOI: https://doi.org/10.1007/978-1-4419-9685-5_5
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-9684-8
Online ISBN: 978-1-4419-9685-5
eBook Packages: EngineeringEngineering (R0)