混合语音信号盲分离的算法研究-计算机应用技术专业论文.docxVIP

摘要盲信号分离技术是近年来信号处理领域的一个研究热点，由于其能够从观测 摘要 盲信号分离技术是近年来信号处理领域的一个研究热点，由于其能够从观测 的混合信号中恢复出原始信号，而对原始信号和混合系统的先验知识要求很少， 因此在无线通信、医学信号处理、图像增强和语音分离方面有着广泛的应用。 混合语音信号的分离是该技术的研究初衷，也是信号处理领域中的一个难 题。本文阐述了盲源分离的基本理论知识，研究了各种混合模型下语音分离的主 要算法以及实际环境下的语音分离问题。本文的主要工作如下： 1．探讨了频域盲分离算法中实际环境下的混响长度与快速傅立叶变换(FFT)长 度之nU的关系．突破了以往算法对混响环境下要求FFT长度要大于混响冲 击响应的长度的限制，研究表明并非越大长度的FIR滤波器所得分离效果 越好。 2．本文尝试将一种新的定点ICA算法用于分离多通道混合语音信号，给出了 一种基于FIR矩阵代数技术的时频域的新算法，实验证明了算法的有效性 和较快的收敛速度。 3．基于传统优化算法的BSS算法，在分离实际环境下所采集的语音信号时， 由于回响的存在，往往会因其全局收敛性能较差而使分离性能下降，本文 将全局收敛性较好的免疫算法用于语音盲分离算法的优化阶段，得到了较 好的分离效果。 关键词：盲源分离(BSS)，独立分量分析(ica)，混叠语音信号，多通道盲反卷 积，免疫算法。 AbstractDuring Abstract During the past decade，Blind Source Separmion—BSS has been a focus in the research area of signal processing．Ranging from wireless communication to medical signals processing，to image enhancement and to audio mixtures separation，BSS is a powerful tool to tackle those problems because it can reconstruct the original signals from the observed signals without any prior knowledge of the mixing system and source signals． BSS for audio mixtures is original intention of BSS technique，and also is a challenging problem in signal processing realm．The fundamental theories of BSS and main methods for audio separation are introduced and investigated in this thesis． Research works ofthis thesis are as follows： 1．The relation of FFT size and the length of reverberation in BSS implementation in frequency domain and its influence on the performance of separation are investigated． 2．A new fixed—point ICA algorithm is introduced into BSS for audio mixtures，and an algorithm of BSS based on FIR matrix algebra with block implementation is given．The experiments demonstrate the efficiency ofthe new algorithm． 3．A new algorithm based on Immunity Algorithm with good global convergence， which can overcome the defect of the existing algorithms for separation of audio mixtures in reverberant environment is proposed． Keywords：Blind sources separation，Independent component analysis，Audio mixtu