http://index.cslt.org/mediawiki/index.php?action=history&feed=atom&title=Sinovoice-2016-3-17 2026-04-13T11:13:42Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://index.cslt.org/mediawiki/index.php?title=Sinovoice-2016-3-17&diff=19394&oldid=prev 2016-03-17T07:50:10Z

<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;">2016年3月17日 (四) 07:50的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第13行：</td> <td colspan="2" class="diff-lineno">第13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>:* 120h labeled ready</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>:* 120h labeled ready</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 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;">==Model training==</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;"><div>===Big-Model Training===</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>===Big-Model Training===</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;"><div>* 16k-10000h DNN training 7*1024-10000</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>* 16k-10000h DNN training 7*1024-10000</div></td></tr> </table>

Zhangzy http://index.cslt.org/mediawiki/index.php?title=Sinovoice-2016-3-17&diff=19393&oldid=prev 2016-03-17T07:32:27Z

<p>以“==Data== *16K LingYun :* 2000h data ready :* 4300h real-env data to label * YueYu :* Total 250h(190h-YueYu + 60h-English) :* CER: 75% * WeiYu :* 50h for training...”为内容创建页面</p> <p><b>新页面</b></p><div>==Data==<br /> <br /> *16K LingYun<br /> :* 2000h data ready<br /> :* 4300h real-env data to label<br /> <br /> * YueYu<br /> :* Total 250h(190h-YueYu + 60h-English)<br /> :* CER: 75%<br /> <br /> * WeiYu<br /> :* 50h for training<br /> :* 120h labeled ready<br /> <br /> ===Big-Model Training===<br /> * 16k-10000h DNN training 7*1024-10000<br /> :* MPE training to be done<br /> :* Performance about 1 point worse than 7*2048-1000<br /> :* The decoding speed is similar with old-nnet1 version<br /> :* 7*2048-1000 net weight-matrix factoring, to improve the decoding speed --SVD<br /> <br /> * TDNN+LSTM chain training<br /> :* Beam-13 performance, chain is better, but beam-9 worse.<br /> <br /> * 8K<br /> :* HuaWei<br /> ::* 5000h 7*1024-XENT be training, performance is similar to 7*2048<br /> ::* To train MPE base on current XENT-model<br /> <br /> ===Embedding===<br /> * 10000h-chain 5*400+800 DONE.<br /> :* To confirm the beam affection on the performance<br /> <br /> ===SinSong Robot===<br /> * Test based on 10000h(7*2048-xent) model<br /> ------------------------------------------------<br /> condition | clean | replay(0.5m) | real-env<br /> ------------------------------------------------<br /> wer | 3 | 18(mpe-14) | too-bad<br /> ------------------------------------------------<br /> <br /> * Recording <br /> <br /> ===Character LM===<br /> *Except Sogou-2T, 9-gram has been done.<br /> *Worse than word-lm(9%-&gt;6%)<br /> *Merge Character-LM &amp; word-LM<br /> :* Union<br /> :* Compose<br /> <br /> ===Path Emphasize===<br /> * Script Done.<br /> <br /> ==SID==<br /> ===Digit===<br /> * Same Channel test EER: 100% <br /> :* Speaker confirm<br /> :* phone channel<br /> <br /> * Cross Channel<br /> :* Mic-wav PLDA adaptation EER from 9% to 7% (20-30 persons)</div>

Zhangzy