Abstract: This paper presents parameters of SVM were optimized by a chaos artificial fish swarm algorithm. By using some test functions, it is proved that combining with chaotic model can improve the behavior of artificial fish swarm algorithm. The optimized parameters are used into a speech recognition system of non-specific persons and isolated words. The experimental results show that convergence rates and speech recognition correct rates based on SVM using chaos artificial fish swarm algorithm are better than those by artificial fish swarm algorithm optimization parameters under different low SNRs and different words.