Eigennoise Speech Recovery in Adverse Environments with Joint Compensation of Additive and Convolutive Noise

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/aav/volume-2015/170183/figures/170183.fig.004a.svgz" name="170183.fig.004a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Training noise-independent eigennoise model</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/aav/volume-2015/170183/figures/170183.fig.004b.svgz" name="170183.fig.004b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Adapting noise-dependent models</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/aav/volume-2015/170183/figures/170183.fig.004c.svgz" name="170183.fig.004c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Clean speech recovery</td></tr></table>

<div>Eigennoise training and conversion.</div>

Advances in Acoustics and Vibration

fig4

Figure 4

Figure 4: Eigennoise Speech Recovery in Adverse Environments with Joint Compensation of Additive and Convolutive Noise 