Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
Blind Separation and Deconvolution for Convolutive Mixture of Speech Combining SIMO-Model-Based ICA and Multichannel Inverse Filtering Hiroshi SARUWATARI Hiroaki YAMAJO Tomoya TAKATANI Tsuyoki NISHIKAWA Kiyohiro SHIKANO Publication IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol.E88-A No.9 pp.2387-2400 Publication Date: 2005/09/01 Online ISSN: DOI: 10.1093/ietfec/e88-a.9.2387 Print ISSN: 0916-8508 Type of Manuscript: PAPER Category: Engineering Acoustics Keyword: blind source separation, blind deconvolution, independent component analysis, SIMO model, Full Text: PDF(1MB)>>
Summary: We propose a new two-stage blind separation and deconvolution strategy for multiple-input multiple-output (MIMO)-FIR systems driven by colored sound sources, in which single-input multiple-output (SIMO)-model-based ICA (SIMO-ICA) and blind multichannel inverse filtering are combined. 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. After the separation by the SIMO-ICA, a blind deconvolution technique for the SIMO model can be applied even when each source signal is temporally correlated and the mixing system has a nonminimum phase property. The simulation results reveal that the proposed algorithm can successfully achieve separation and deconvolution of a convolutive mixture of speech, and outperforms a number of conventional ICA-based BSD methods. | ||||||||||
| ||||||||||
