“ASR Status Report 2016-12-12”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第18行： 第18行：
 
|Hang Luo
 
|Hang Luo
 
||  
 
||  
−
*  
+
* Compared mono-language model and bi-language model decode result.
 +
* Read paper of WFST.
 
||  
 
||  
−
*  
+
* Use different corpus or generate mix-lingual corpus to run experiments
 
|-
 
|-
  

2016年12月12日 (一) 12:35的版本

Date People Last Week This Week
2016.12.12


Yanqing Wang
  • read a paper about driving distraction detection task
  • show normal/distraction patterns of a driver with one class and two class SVM
Hang Luo
  • Compared mono-language model and bi-language model decode result.
  • Read paper of WFST.
  • Use different corpus or generate mix-lingual corpus to run experiments
Ying Shi
  • work from Chao Xing down
  • kazak lm
    • got some corpus from a student who study in Minzu University of China.But the corpus is short (about 10000) so the ppl is also poor.
    • spider
  • kazak lm
Yixiang Chen
  • Complete the replay task experiment and report
  • learning tensorflow coding DNN and CNN net
Lantian Li
Zhiyuan Tang
  • interim report done;
  • PPT for APSIPA16;
  • language mask[1]
  • Jeju for APSIPA16.
Date People Last Week This Week
2016.11.28


Yanqing Wang
  • finish building GUI of one-class-SVM in Visual Studio
  • learn about deep learning
  • process data with the GUI of one-class-SVM
Hang Luo
  • Experiments about fixed language model, find language information almost has no improve in ASR so far
  • share one paper
  • Experiments on smaller language model,128 cells still has great result
  • Try different language model or other direction
  • Paper about joint training
Ying Shi
  • some work about kazak LM
  • DNN for Chao Xing
  • ml-book check to cvs
  • share two papers
  • some work about kazak lm(try to reduce the ppl)
  • paper about activation function
  • DNN for Chao Xing
Yixiang Chen
  • According to the weighted filter replay test
  • fitting warping function and use piecewise function for warping
  • complete replay test
  • learning tensorfloat
Lantian Li
  • LRE on AP16-OL7. [2]
    • The deep model still can not beat the i-vector model.
  • Emotion challenge in CCPR. --> Done.
  • Replay detection. --> Done.
  • Phd forum. --> Done
  • LRE task.
  • Write replay detection technical report.
  • oral PPT for APSIPA 2016.
Zhiyuan Tang
  • materials for PhD Dissertations,
  • materials for paper accepted by TASLP;
  • language mask[3]
  • scans the TASLP paper for several times,
  • oral PPT for APSIPA 2016.
取自“http://index.cslt.org/mediawiki/index.php?title=ASR_Status_Report_2016-12-12&oldid=24736”