http://cslt.org/mediawiki/index.php?action=history&feed=atom&title=Lantian_Li_2015-03-16 2026-04-09T06:26:41Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://cslt.org/mediawiki/index.php?title=Lantian_Li_2015-03-16&diff=14244&oldid=prev 2015-03-16T09:14:12Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2015年3月16日 (一) 09:14的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第9行：</td> <td colspan="2" class="diff-lineno">第9行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>The experimental results show that: global CMVN without speaker CMVN performs the best which meets the expectations.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>The experimental results show that: global CMVN without speaker CMVN performs the best which meets the expectations.</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>3. Train a text-content-based neural networks and extract d-vectors from these networks. But results show this method does not work.</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>3. Train a text-content-based <ins class="diffchange diffchange-inline">(block-mask) </ins>neural networks and extract d-vectors from these networks. But results show this method does not work.</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>Next Week</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>Next Week</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>1. Go on the task1 and task2.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>1. Go on the task1 and task2.</div></td></tr> </table>

Lilt http://cslt.org/mediawiki/index.php?title=Lantian_Li_2015-03-16&diff=14243&oldid=prev 2015-03-16T09:13:34Z

<p>以“Weekly Summary 1. Explore the generalization of d-vector for text-indedenpent Speaker Recognition. The experimental results show that: d-vector performs better tha...”为内容创建页面</p> <p><b>新页面</b></p><div>Weekly Summary<br /> <br /> 1. Explore the generalization of d-vector for text-indedenpent Speaker Recognition.<br /> <br /> The experimental results show that: d-vector performs better than i-vector only under cosine distance. While LDA and PLDA do not work for d-vector. <br /> <br /> 2. Explore the impact of CMNV on the d-vector for Speaker Recognition. <br /> <br /> The experimental results show that: global CMVN without speaker CMVN performs the best which meets the expectations.<br /> <br /> 3. Train a text-content-based neural networks and extract d-vectors from these networks. But results show this method does not work.<br /> <br /> Next Week<br /> <br /> 1. Go on the task1 and task2.</div>

Lilt