基于FastICA盲源分离算法的语音增强系统

摘要

论文在分析现有语音增强系统中采用的传统算法的缺点基础上,提出了一种基于FastICA盲源分离算法设计的语音增强算法,并将其移植到嵌入式语音增强系统上.该系统实时增强语音,通过四元麦克风阵列采集空间中的声音信号,并通过内置语音增强算法将其中的语音源信号和噪声源信号分离,能够抑制有同声道噪声在内的有源噪声和残余背景噪声.算法在PC平台上的测试结果分析表明本系统达到设计要求,效果好.%Based on analyzing the drowbacks of troditional algorithm of existing speech enhancement system, a speech enhancement algorithm is proposed based on FastICA blind source separation algorithm design, and it is transplanted to embedded speech enhancement system.The system has real-time speech enhancement, four element microphone array is used to sample the space of sound signal and the built-in speech enhancement algorithm is used to separate the voice source signal and noise source signal, capable of suppressing co channel noise, active noise and residual background noise.Based on the test results of the algorithm on PC platform, the system meets the design requirements and the effect is good.