SROC: A Speaker Recognition with Data Decision Level Fusion Method in Cloud Environment

摘要

Speaker recognition as one of biometrics techniques is to recognize speaker's identity. A robust method for speaker recognition with high accuracy of recognition rate is the aim for all relevant researchers. With the rapid development of cloud computing, many complicated tasks in speaker recognition system, such as machine learning, data processing, and information recording, can be implemented in cloud. Meanwhile, speaker recognition can be used as a security and privacy service which are extremely important for the popularization of cloud computing. In this paper, we propose a data decision level fusion method for speaker recognition in cloud environment. After introducing the basic processing of speech recognition process and describing the composition of the speech recognition system based on Dempster-Shafer Evidence Theory of decision level data fusion method, we present a speaker recognition system of cloud computing (SROC) architecture. Through experimental evaluation, SROC can improve the recognition rate and accuracy greatly.