Separation of Multiple Speech Signals by Using Triangular Microphone Array 15 Separation of Multiple Speech Signals by Using Triangular Microphone Array

Speech source separation has been an important topic to realize speech-based human-machine inter-faces or high quality hand-free communication with machines. For source separation, Independent Com-ponent Analysis (ICA) and time-frequency masking are powerful methods as a tool of Blind Source Sepa-ration (BSS) of speech mixtures. The latter method is based on the assumption called “W-Disjoint Or-thogonality ” which implies the cell component spar-sity of speech in the time-frequency domain. One of the topics treated in this article is to introduce the time-frequency masking scheme is applied to the equilateral triangular array where the three delay es-timates from each microphone pairs are obtained. In addition, it is used to improve histogram-mapping al-gorithm by integrate and coordinate transformation of three delay estimates. Some experiments in real environment for separating multiple sources are per-formed to verify the effectiveness