BLIND SEPARATION AND DECONVOLUTION FOR REAL CONVOLUTIVE MIXTURE OF TEMPORALLY CORRELATED ACOUSTIC SIGNALS USING SIMO-MODEL-BASED ICA
BLIND SEPARATION AND DECONVOLUTION FOR REAL CONVOLUTIVE MIXTURE OF TEMPORALLY CORRELATED ACOUSTIC SIGNALS USING SIMO-MODEL-BASED ICA
复制标题
DOI：
--
复制
发表时间：
2003-04
期刊：
影响因子：
--
通讯作者：
H. Saruwatari;T. Takatani;H. Yamajo;T. Nishikawa;K. Shikano
中科院分区：
文献类型：
--
作者：
H. Saruwatari;T. Takatani;H. Yamajo;T. Nishikawa;K. Shikano
针对时间相关信号的真实卷积混合，提出了一种新的两阶段盲分离和反卷积（BSD）算法，该算法将一种新的基于单输入多输出（SIMO）模型的ICA （SIMO-ICA）和盲多通道反滤波相结合。SIMO-ICA由多个ICA和一个保真度控制器组成，每个ICA在整个分离系统的保真度控制下并行运行。SIMO-ICA可以将混合信号分离，而不是将其分离为单声源信号，而是将其分离为来自麦克风的独立源的基于simo模型的信号。因此，SIMOICA的分离信号可以保持每个声源的空间品质。经过SIMO- ica分离后，在混频系统为非最小相位系统且各源信号时间相关的情况下，SIMO模型可以采用基于多通道反滤波的简单盲反褶积技术。混响条件下的实验结果表明，该方法分离信号的音质优于传统的基于ica的BSD。
We propose a new novel two-stage blind separation and deconvolution (BSD) algorithm for a real convolutive mixture of temporally correlated signals, in which a new Single-Input Multiple-Output (SIMO)-model-based ICA (SIMO-ICA) and blind multichannel inverse filtering are combined. SIMO-ICA consists of multiple ICAs and a fidelity controller, and each ICA runs in parallel under fidelity control of the entire separation system. SIMO-ICA can separate the mixed signals, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMOICA can maintain the spatial qualities of each sound source. After the separation by SIMO-ICA, a simple blind deconvolution technique based on multichannel inverse filtering for the SIMO model can be applied even when the mixing system is the nonminimum phase system and each source signal is temporally correlated. The experimental results obtained under the reverberant condition reveal that the sound quality of the separated signals in the proposed method is superior to that in the conventional ICA-based BSD.