High-fidelity blind separation for convolutive mixture of acoustic signals using SIMO-model-based independent component analysis

We propose a novel blind separation framework for Single­ Input Multiple-Output (SIMO)守nodel-based acoustic sig­ nals using the extended ICA algorithm， SIMO-ICA. The SIMO-ICA consists of multiple ICAs and a 日delity con­ troller， and each ICA runs in parallel under the日delity con­ trol of the entire separation system. The SIMO-ICA can separate the mixed signals， not into monaural source sig­ nals but into SIMO叩odel-based signals from independent sources as they are at the microphones. Thus， the separated signals of SIMO-ICA can maintain the spatial qualities of each sound source. In order to evaluate its effectiveness， separation experiments are carried out under a reverberant condition. The experimental results reveal that (1) the sig­ nal separation performance of the proposed SIMO-ICA is the same as that of the conventional ICA-based method， and that (2) the spatial quality of the separated sound in SIMO-ICA is remarkably superior to that of the conven­ tional method.