“Asr-nsfc-weekly-2016-11-28”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第24行: 第24行:
 
|民大
 
|民大
 
||  
 
||  
*   
+
选择藏蒙书面语发音文本各50000条左右
 +
*  校对拉萨话发音词典1000条左右
 
||  
 
||  
*   
+
* 对藏语书面发音文本进行triphone计算,挑选6000句左右的正式发音文本
 +
*  藏语拉萨话发音词典的校对
 +
*  蒙语词典录入  
 
|-
 
|-
 
|}
 
|}

2016年11月29日 (二) 02:02的版本


Date People Last Week This Week
2016.11.28
清华
  • 确定了训练集匹配问题、语料domain不符等问题
  • 等待数据和语料的进一步更新,重新训练声学模型和语言模型
新大
  • additional Kazak acoustic rules are discussed with experts, and new rules are determined.
  • lost Kazak utterances are extracted and make-up preparation works are done.
  • Kazak irregular acoustic dictionary going to be prepared manually again.
  • recording of Kazak utterances will go on.
民大
  • 选择藏蒙书面语发音文本各50000条左右
  • 校对拉萨话发音词典1000条左右
  • 对藏语书面发音文本进行triphone计算,挑选6000句左右的正式发音文本
  • 藏语拉萨话发音词典的校对
  • 蒙语词典录入




Date People Last Week This Week
2016.11.21
清华
  • 哈语声学模型(TDNN)训练完毕
  • 哈语语料训练语言模型,并用于解码[1]:语料与训练集的domain符合度有待检查
  • 获取合适的语料训练语言模型,完成baseline
新大
  • Kazak language vocabulary extraction and acoustic dictionary building tool are finished, can be shared along with Uyghur tools
  • There are still never ending problems with Kazak acoustic rules and spelling, we spent a lot of time on correcting.
  • We built tools of character and acoustic layers of corpora compilation for Uyghur and Kazak. We hope to have a common structure for every language.
  • We plan to conclude a relatively complete syllable structure and use it for spell checking and correcting various corpora.
  • We appointed students to make a double directional text-numeric transformation tool.
  • A third layer of morphological analyzer tool is designed for multilingual purpose first for Uyghur and Kazak language, mainly for sub-word analysis.
民大
  • 确定了口语发音文本
  • 校对拉萨话发音词典300条
  • 选择书面语发音文本
  • 藏语拉萨话发音词典的校对
  • 蒙语词典录入