Improved Method of Blind Speech Separation with Low Computational Complexity

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="765429.fig.005a" src="https://static.hindawi.com/articles/aav/volume-2011/765429/figures/765429.fig.005a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Determinant</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="765429.fig.005b" src="https://static.hindawi.com/articles/aav/volume-2011/765429/figures/765429.fig.005b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>Trace</td></tr></table></td></tr></table>

<table>Estimated DOA via the determinant/trace selection criteria.</table>

Advances in Acoustics and Vibration

fig5

Figure 5

Figure 5: Improved Method of Blind Speech Separation with Low Computational Complexity 