8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Blind Separation and Deconvolution for Convolutive Mixture of Speech Using SIMO-Model-Based ICA and Multichannel Inverse Filtering

Hiroaki Yamajo, Hiroshi Saruwatari, Tomoya Takatani, Tsuyoki Nishikawa, Kiyohiro Shikano

Nara Institute of Science and Technology, Japan

We propose a new two-stage blind separation and deconvolution (BSD) algorithm for a convolutive mixture of speech, in which a new 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 SIMO-ICA, a simple blind deconvolution technique for the SIMO model can be applied even when each source signal is temporally correlated. The simulation results reveal that the proposed method can successfully achieve the separation and deconvolution for a convolutive mixture of speech.

Full Paper

Bibliographic reference.  Yamajo, Hiroaki / Saruwatari, Hiroshi / Takatani, Tomoya / Nishikawa, Tsuyoki / Shikano, Kiyohiro (2003): "Blind separation and deconvolution for convolutive mixture of speech using SIMO-model-based ICA and multichannel inverse filtering", In EUROSPEECH-2003, 537-540.