Title
A Speech Recognition System Based on Fuzzy Neural Network Optimized by Time Variant PSO
Abstract
In order to overcome shortages of fuzzy neural network (FNN) and basic Particle Swarm Optimization (PSO) algorithm, the article proposes a novel method that the parameters of structure equivalent FNN (SEFNN) trained by Time Variant Particle Swarm Optimization (TVPSO) algorithm. TVPSO is made adaptive in nature by adaptively and dynamically changing its acceleration coefficients and its inertia weight with iterations and fitness value, which helps the algorithm to explore the search space more efficiently. The Parameters of SEFNN trained by TVPSO algorithm was used in speech recognition system which improve the ability of generalization and self-learning of FNN and is able to determine the fuzzy rule numbers according to the vocabulary to be recognized. The experimental results show that the SEFNN optimized by TVPSO for speech recognition system have faster convergence, higher recognition ratio and better robustness than SEFNN trained by PSO algorithm, FNN trained by BP algorithm.
Year
DOI
Venue
2010
10.1109/CASoN.2010.117
CASoN
Keywords
Field
DocType
pso algorithm,time variant pso,tvpso algorithm,speech recognition,time variant parames particle swarm optimization,particle swarm optimisation,basic particle swarm optimization,speech recognition system,time variant particle swarm,structure equivalence fuzzy neural network,fuzzy rule number,structure equivalent fnn,fuzzy neural nets,higher recognition ratio,bp algorithm,particle swarm optimization,fuzzy neural network,algorithm design and analysis,acceleration,search space
Convergence (routing),Computer science,Robustness (computer science),Artificial intelligence,Artificial neural network,Particle swarm optimization,Algorithm design,Pattern recognition,Speech recognition,Acceleration,Vocabulary,Machine learning,Fuzzy rule
Conference
ISBN
Citations 
PageRank 
978-1-4244-8785-1
0
0.34
References 
Authors
2
3
Name
Order
Citations
PageRank
Aiping Ning110.69
Xueying Zhang2389.52
Hui Sun3148.66