Direct Recovery of Clean Speech Using a Hybrid Noise Suppression Algorithm for Robust Speech Recognition System

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="306305.fig.002a" src="https://static.hindawi.com/articles/isrn/volume-2012/306305/figures/306305.fig.002a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Clean</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="306305.fig.002b" src="https://static.hindawi.com/articles/isrn/volume-2012/306305/figures/306305.fig.002b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>Noisy Speech</td></tr></table></td></tr><tr class="fig-image" id="c"><td><img alt="306305.fig.002c" src="https://static.hindawi.com/articles/isrn/volume-2012/306305/figures/306305.fig.002c.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(c) </b> Processed by SS</td></tr></table></td></tr></table>

<table>Speech PDF of Mel channel log-power for digital string “3Z82”.</table>

International Scholarly Research Notices

fig2

Figure 2

Figure 2: Direct Recovery of Clean Speech Using a Hybrid Noise Suppression Algorithm for Robust Speech Recognition System 