“Hulan-2013-12-13”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以内容“=ASR= ==ASR Kernel development== http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/2013-1213 ASR group weekly report ==TTS== * This week :* 2000 utterances ...”创建新页面)
 
Statistical approach
第24行: 第24行:
 
:* Tested edit distance to solve unmatched similar words. A little performance gain was obtained, but not quite significant.  
 
:* Tested edit distance to solve unmatched similar words. A little performance gain was obtained, but not quite significant.  
  
 +
<pre>
 
n-best original edit-distance
 
n-best original edit-distance
 
1 0.604 0.605
 
1 0.604 0.605
第33行: 第34行:
 
7 0.879 0.883
 
7 0.879 0.883
 
8 0.887 0.899
 
8 0.887 0.899
 
+
</pre>
 
+
  
 
==Template matching==
 
==Template matching==

2013年12月13日 (五) 08:51的版本

ASR

ASR Kernel development

[ASR group weekly report]

TTS

  • This week
  • 2000 utterances recording finished, on labeling silence
  • Design/implement the online stream service
  • Solve the problem of signal English letter pronunciation.
  • CGI server finished
  • Next week
  • Deliver new male/female voice

Dialog system

Statistical approach

  • Word2Vector seems use the same training approach of NN LM, however we do not know the training object. Will clarify this next Monday.
  • Word2Vector can be used to expand queries based on semantic distance.
  • Tested edit distance to solve unmatched similar words. A little performance gain was obtained, but not quite significant.
n-best	original	edit-distance
1	0.604		0.605
2	0.740		0.744
3	0.806		0.810
4	0.842		0.845
5	0.858		0.862
6	0.870		0.873
7	0.879		0.883
8	0.887		0.899

Template matching