Speaker Recognition Based on Cuckoo Search Algorithm
Monica Sood1, Gurline Kaur2
1Monica Sood, Assistant Professor, Department of CSE, IT, Lovely Professional University, Phagwara (Punjab), India.
2Gurline Kaur, M.Tech Student, Department of CSE, IT, Lovely Professional University, Phagwara (Punjab), India.
Manuscript received on 15 April 2013 | Revised Manuscript received on 22 April 2013 | Manuscript Published on 30 April 2013 | PP: 311-313 | Volume-2 Issue-5, April 2013 | Retrieval Number: E0756042413/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Today’s world sees a lot of changes being done. These are a result of some modification or some innovation. This research is being done in the field of Swarm Intelligence or SI. It deals with studying the behaviour of organisms or swarms. Swarms are individual entities which are working on their own, yet their combined or aggregate behaviour yields some great results. This begins by studying the behaviour of any organism as fish, ants, bees, cuckoo bird or something like water drops. When the behaviour is understood it is then converted in the form of an algorithm. It is this algorithm that is of utmost importance; it not only studies the behaviour of these organisms but also provides some principles which can help in providing solutions to real world applications. This research is based on an algorithm of Swarm Intelligence called Cuckoo Search. This is an algorithm which is aimed at understanding the breeding behaviour of the cuckoo bird. In this research, it is applied in the field of Biometrics. Biometrics is used to identify an individual as per their some special characteristics as finger print, voice, iris, handwriting, typing speed. In this Cuckoo Search has been applied on Speaker Recognition systems and voice. Thus by applying this algorithm, the process of Speaker Recognition is optimized by a fitness function by matching of voices being done on only the extracted optimized features produced by the Cuckoo Search algorithm.
Keywords: Correlation, Mean, Fitness Function, Swarm Intelligence.
Scope of the Article: Pattern Recognition