http://www.cslt.org/mediawiki/index.php?action=history&feed=atom&title=2014-03-28 2026-04-04T01:47:28Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://www.cslt.org/mediawiki/index.php?title=2014-03-28&diff=9519&oldid=prev 2014-03-28T02:17:13Z

<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;">2014年3月28日 (五) 02:17的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第38行：</td> <td colspan="2" class="diff-lineno">第38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;"></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>* gfbank on Tentent 100h</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>* gfbank on Tentent 100h</div></td></tr> <tr><td colspan="2">&#160;</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><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2">&#160;</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><ins style="font-weight: bold; text-decoration: none;">===Denoising====</ins></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;"></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> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=2014-03-28&diff=9518&oldid=prev 2014-03-28T02:13:45Z

<p>以内容“==Resoruce Building== * Current text resource has been re-arranged and listed == Leftover questions== * Asymmetric window: Great improvement on training set(WER 34% to...”创建新页面</p> <p><b>新页面</b></p><div>==Resoruce Building==<br /> * Current text resource has been re-arranged and listed<br /> <br /> == Leftover questions==<br /> * Asymmetric window: Great improvement on training set(WER 34% to 24%), however the improvement is lost on test. Overfitting? <br /> * Multi GPU training: Error encountered<br /> * Multilanguage training<br /> * Investigating LOUDS FST. <br /> * CLG embedded decoder plus online compiler.<br /> * DNN-GMM co-training<br /> <br /> == AM development ==<br /> <br /> === Sparse DNN ===<br /> * GA-based block sparsity<br /> :* 88% element-sparsity: 25.09 <br /> :* 80% block-sparsity: 25.5<br /> <br /> ===Noise training===<br /> :* More experiments with no-noise<br /> :* More experiments with additional noise types<br /> <br /> <br /> ===AMR compression re-training===<br /> <br /> * 1700h MPE adaptation<br /> <br /> :* iter1:<br /> amr: %WER 13.40 [ 6398 / 47753, 252 ins, 829 del, 5317 sub ]<br /> wav: %WER 11.19 [ 5343 / 47753, 178 ins, 710 del, 4455 sub ]<br /> <br /> :* iter2:<br /> amr: %WER 13.31 [ 6358 / 47753, 255 ins, 798 del, 5305 sub ]<br /> wav: %WER 11.33 [ 5409 / 47753, 180 ins, 732 del, 4497 sub ]<br /> <br /> <br /> ===GFbank===<br /> <br /> * gfbank on Tentent 100h<br /> <br /> <br /> ==Word to Vector==<br /> <br /> * LDA baseline (sogou 1700*9 training set)<br /> :* Memory usage more than 20G<br /> <br /> * Word-vector classification on going<br /> :* Model based on category wordvector clustering<br /> <br /> <br /> <br /> ==LM development==<br /> <br /> ===NN LM===<br /> <br /> * Character-based NNLM (6700 chars, 7gram), 500M data training done.<br /> :* boundary-involved char NNLM training done<br /> <br /> * Investigate MS RNN LM training<br /> <br /> <br /> ==Pronunciation scoring==<br /> * 8k model delivered<br /> * MLP-based scoring completed<br /> <br /> <br /> ==QA==<br /> <br /> ===FST-based matching===<br /> :* Char FST<br /> :* Prepare FST-based QA patent<br /> <br /> ===Speech QA===<br /> *Class LM QA<br /> :* Now find that with smaller weight to the class FST, better performance is obtained<br /> :* Now it is very difficult to retrieve the words that can not be found by the original FST<br /> :* Test negative weights</div>

Cslt