基于遗传优化RBF神经网络声纹识别研究-模式识别与智能系统专业论文.docxVIP

摘要 摘要 II II A Abstract III III Abstract Speech is to realize the communication between people is the most direct and the most convenient means, and how to realize the computer and between the smooth operator voice communications, has been to pursue a dream, speech recognition is the key technology of dream. Along with the people to the identification and safety have become increasingly demanding, biometric authentication technology for its unique advantages, increasingly shows its value. And other biometric technology, voice recognition is not lost, no need to remember and easy to use. At the same time, voiceprint recognition also has its own unique advantages, is the first to voice as recognition features, non contact and nature is the important reason for users to accept; secondly, voiceprint recognition using equipment cost is very low, due to the telephone network and a microphone, computer integration, can say the required hardware cost is almost zero; for remote applications and mobile Internet environment, at present, voiceprint recognition is likely to be the only solution, the speaker recognition technology has become the peoples daily life and work of an important and popular authentication mode. Although voiceprint recognition research for half a century, but the existing voice system there are still many problems, not up to the community for its practical requirements. In essence, the speaker recognition technology can be divided into two part feature extraction and recognition model. Therefore, in a sense, the root of the problem can be reduced by the feature extraction and recognition model limitations caused by. How to seek new more characteristics of expressive force, has stronger robust speech feature, or to the existing feature selection, optimization of fusion, compensation and other methods to enhance the performance of existing systems. This paper presents a RBF neural network optimization based on Genetic Algorithm in voice recognition algorith