“2018-12-19”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
第36行: 第36行:
 
|Jiayao Wu
 
|Jiayao Wu
 
||  
 
||  
*
+
*run through the baseline for AISHELL2 finally
 +
*read some papers about compression especially TT compression
 
||
 
||
*  
+
*do experiments on TT compression.
 
||  
 
||  
 
*  
 
*  

2018年12月19日 (三) 04:22的最后版本

People Last Week This Week Task Tracking (DeadLine)
Yibo Liu
Xiuqi Jiang
  • Reconstructed codes and made adjustments on training part.
  • Focus on generating Song Iambics.
Jiayao Wu
  • run through the baseline for AISHELL2 finally
  • read some papers about compression especially TT compression
  • do experiments on TT compression.
Zhaodi Qi
  • 1. Completed 1th and 2th steps of the DID system.
  • 1th : Data preparation (train dev test (1/5 data selected from dev) wav.lst & word.txt) and Dictionary preparation, dict.txt
  • 2th : Generate batch data and feed it to the next acoustic model framework
  • 1. Reference paper completes acoustic model of dialect
  • paper : 2015, Baiguang Shi et.al, An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
Jiawei Yu
  • Run the attention baseline
  • Read several new papers about attention
  • Read statistics extraction component and statistics pooling component of x-vector
  • try to add the higher-order statistics for x-vectors
  • run attention baseline for d-vector
Yunqi Cai
Dan He
  • Run the experimental code of the paper about tensorizing nerual networks
  • Have not finished yet
  • Contiune running the code
  • Understand the experimental code
Yang Zhang
  • 1. investigated VPR service and wrote a investigation report.
  • 2. Tested Microsoft and SpeakIn's VPR interface.
  • try to release a stable WeChat APP at the end of this month.