CAJ | 학술논문

在欠定语音盲分离中,W-分离正交性假设通常使问题简化,但这种简化是以降低分离性能为代价.在语音信号满足近似W-分离正交性的假设下,提出利用主分量分析(PCA)检测只有一个源信号存在的时频点,检测出的时频点均满足W-分离正交性,因此提高了混合矩阵的估计精度.通过从混合矩阵中估计源信号的波达方向,可以较好地解决置换模糊问题.仿真结果表明,提出的方法与经典的DUET方法相比具有更优的性能,平均信干比提高了2.77dB.
재흠정어음맹분리중,W-분리정교성가설통상사문제간화,단저충간화시이강저분리성능위대개.재어음신호만족근사W-분리정교성적가설하,제출이용주분량분석(PCA)검측지유일개원신호존재적시빈점,검측출적시빈점균만족W-분리정교성,인차제고료혼합구진적고계정도.통과종혼합구진중고계원신호적파체방향,가이교호지해결치환모호문제.방진결과표명,제출적방법여경전적DUET방법상비구유경우적성능,평균신간비제고료2.77dB.
The assumption of W-disjoint orthogonality (W-DO) can simplify the problem of blind separation for un-der-determined mixed speech signals at the cost of decreasing the separation performance. A method based on principal component analysis (PCA) is proposed to detect the time-frequency cells where only one source exists, under the as-sumption of approximate W-DO of speech signal. All the detected time frequency cells satisfy the W-DO, so that the estimation precision of the mixing matrix is improved. The direction of arrival (DOA) of sources is estimated from the mixing matrix and is exploited to solve the permutation ambiguity problem. Simulation results demonstrate that the proposed method outperforms the typical DUET method, the average signal to interference (SIR) is improved by 2.77dB.