“Asr-progress 2016.11”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（3位用户的4个中间修订版本未显示）
第172行： 第172行：
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  || some work about HCLG.fst
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  || some work about HCLG.fst
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||
+
|Hang luo || 9:30am  || 7:30pm  || 10h  || Read Inter Speech paper
 
|-
 
|-
 
|Yixiang Chen || 9:30am  ||  7:30pm  ||  10h  || processing data for replay
 
|Yixiang Chen || 9:30am  ||  7:30pm  ||  10h  || processing data for replay
第183行： 第183行：
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  ||4 experiment for kazak decoding the result is poor maybe we need new corpus for lm
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  ||4 experiment for kazak decoding the result is poor maybe we need new corpus for lm
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30pm  || 7:30am  || 10h  ||  Try simple language model and find its accuracy
 
|-
 
|-
 
|Yixiang Chen || 9:30pm  ||  7:30pm  || 10h ||  dividing frequency band test
 
|Yixiang Chen || 9:30pm  ||  7:30pm  || 10h ||  dividing frequency band test
第194行： 第194行：
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  || some work about kazak speech recognition LM   
 
|Ying Shi ||  9:30pm  ||  9:30pm  || 12h  || some work about kazak speech recognition LM   
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30am  || 7:30pm  || 10h  ||  Fixed LRE model and do experiments
 
|-
 
|-
 
|Yixiang Chen ||  12:30am  ||  7:30pm  ||  7h  ||  dividing Mel frequency band test
 
|Yixiang Chen ||  12:30am  ||  7:30pm  ||  7h  ||  dividing Mel frequency band test
第216行： 第216行：
 
|Ying Shi ||  2:30pm  || 6:00pm ||  3.5h  || check corpus with teacher SAMAHAN  
 
|Ying Shi ||  2:30pm  || 6:00pm ||  3.5h  || check corpus with teacher SAMAHAN  
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30pm || 6:30am  || 9h  ||  Read LRE code and modify configuration
 
|-
 
|-
−
|Yixiang Chen ||  9:30pm ||  8:00pm  ||  10h30min  || Complete the comparison of Frequency and Mel
+
|Yixiang Chen ||  9:30am ||  8:00pm  ||  10h30min  || Complete the comparison of Frequency and Mel
 
|-
 
|-
 
|Yanqing Wang || 9:00 pm  || 10:30 pm  ||  13h30min  ||  Learn to use Qt Creator
 
|Yanqing Wang || 9:00 pm  || 10:30 pm  ||  13h30min  ||  Learn to use Qt Creator
第227行： 第227行：
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  paper about visualization
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  paper about visualization
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30am  || 6:30pm  || 9h  ||  Run the changed model
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen || 9:30am  || 7:30pm  || 10h  || To prepare UBM database,join replay data
 
|-
 
|-
 
|Yanqing Wang || 9:00am  ||  8:00pm  ||  11h  ||  learn to create Qt project in Visual Studio and Qt creator
 
|Yanqing Wang || 9:00am  ||  8:00pm  ||  11h  ||  learn to create Qt project in Visual Studio and Qt creator
第238行： 第238行：
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  data cleaning about kazak speech paper about visualization
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  data cleaning about kazak speech paper about visualization
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 2:00pm  || 7:00pm  || 5h  ||  Summay readed paper
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen ||9:30am  || 8:30pm  || 11h  || To find the best configuration(num_bin) and the experiment
 
|-
 
|-
 
|Yanqing Wang ||    ||    ||    ||   
 
|Yanqing Wang ||    ||    ||    ||   
第249行： 第249行：
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  new dnn model with different activation function (Sigmod Tanh relu pnorm)   
 
|Ying Shi ||  9:30  || 9:30  || 12h  ||  new dnn model with different activation function (Sigmod Tanh relu pnorm)   
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30am  || 6:30pm  || 9h  ||  Share 4 papers
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen || 9:30am  || 8:30pm  || 11h  || To find the best configuration and the experiment
 
|-
 
|-
 
|Yanqing Wang ||    ||    ||    ||   
 
|Yanqing Wang ||    ||    ||    ||   
第260行： 第260行：
 
|Ying Shi ||  9:30  ||  6：00|| 8：30h  ||  new dnn model with different activation function (Sigmod Tanh relu pnorm) and finish the ML book
 
|Ying Shi ||  9:30  ||  6：00|| 8：30h  ||  new dnn model with different activation function (Sigmod Tanh relu pnorm) and finish the ML book
 
|-
 
|-
−
|Hang luo ||   ||   ||   ||   
+
|Hang luo || 9:30am  ||   6:30pm || 9h  ||  Continue doing experiments on fixed LRE model
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen ||9:30am  || 8:30pm  || 11h  || Comparative experiments on linear and MEL effect
 
|-
 
|-
 
|Yanqing Wang ||    ||    ||    ||   
 
|Yanqing Wang ||    ||    ||    ||   
第295行： 第295行：
 
|Hang luo ||    ||    ||    ||   
 
|Hang luo ||    ||    ||    ||   
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen || 9:30am || 5:30pm  || 8h  || dividing frequency band and compute EER of bank
 
|-
 
|-
 
|Yanqing Wang ||  9:00am  || 11:00pm  || 14h  || continue to implement the LibSVM toolkit in Visual Studio
 
|Yanqing Wang ||  9:00am  || 11:00pm  || 14h  || continue to implement the LibSVM toolkit in Visual Studio
第306行： 第306行：
 
|Hang luo ||    ||    ||    ||   
 
|Hang luo ||    ||    ||    ||   
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen || 9:30am  || 7:30pm  || 10h ||compare baseline and weight , warping  test
 
|-
 
|-
 
|Yanqing Wang ||    ||    ||    ||
 
|Yanqing Wang ||    ||    ||    ||
第313行： 第313行：
 
|-
 
|-
 
| rowspan="4"|2016.11.30
 
| rowspan="4"|2016.11.30
−
|Ying Shi ||    ||   ||   ||   
+
|Ying Shi ||9:30am   || 9:30pm  || 12h  ||  upload ml-book to cvs paper reading
 
|-
 
|-
 
|Hang luo ||    ||    ||    ||   
 
|Hang luo ||    ||    ||    ||   
 
|-
 
|-
−
|Yixiang Chen ||   ||   ||   ||
+
|Yixiang Chen ||9:30am  || 7:30pm  || 10h ||compare warping and weight
 
|-
 
|-
 
|Yanqing Wang ||    ||    ||    ||
 
|Yanqing Wang ||    ||    ||    ||
第330行： 第330行：
 
|Ying Shi    || 1+0.5
 
|Ying Shi    || 1+0.5
 
|-
 
|-
−
|Hang luo    || 0.5+1
+
|Hang luo    || 0.5+1+0.5+2
 
|-
 
|-
 
|Yixiang Chen|| 1+1+1+1
 
|Yixiang Chen|| 1+1+1+1

2016年12月5日 (一) 06:29的最后版本

Daily Report

Date Person start leave hours status
2016.11.1 Ying Shi 10:00am 8:30pm 8h ML-book
Hang luo 9:30am 7:30pm 10h Related work about joint training
Yixiang Chen 10:00am 8:30pm 8h30min ML-book
Yanqing Wang
2016.11.2 Ying Shi 9:20am 9:30pm 12h10min bimonthly report ;paper
Hang luo 9:40am 7:20pm 9h40min bimonthly report, Read Inter Speech paper
Yixiang Chen 9:30am 7:30pm 9h30min bimonthly report,check PPT
Yanqing Wang
2016.11.3 Ying Shi 9:20am 9:30pm 12h10min check worklist for zhiyong zhang
Hang luo 9:30am 9:30pm 12h paper reading report
Yixiang Chen 10:00am 10:30pm 12h30min check worklist ,data processing
Yanqing Wang
2016.11.4 Ying Shi 9:30am 9:30am 12h kazak speech recognition
Hang luo 10:30am 6:30pm 8h lexicon checking
Yixiang Chen Exam Review
Yanqing Wang
2016.11.5 Ying Shi 1:30pm 9:30pm 8h kazak speech recognition
Hang luo
Yixiang Chen
Yanqing Wang
2016.11.6 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo
Yixiang Chen
Yanqing Wang
2016.11.7 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo 9:30am 7:30pm 10h Read paper about DNN highway connection
Yixiang Chen Exam
Yanqing Wang
2016.11.8 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo 11:30am 7:30am 8h Get Know to multi-task and read papers
Yixiang Chen 9:30am 5:30am 8h read paper and MLbook
Yanqing Wang
2016.11.9 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo 9:30am 8:30pm 11h Read multi-task paper, but there are many confuses.
Yixiang Chen
Yanqing Wang
2016.11.10 Ying Shi
Hang luo 9:30am 6:00pm 8.5h Think about new direction of joint training
Yixiang Chen
Yanqing Wang
2016.11.11 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo 9:30am 3:30pm 6h Read adversirial joint training paper
Yixiang Chen 9:30am 7:00pm 9h30min MLbook
Yanqing Wang
2016.11.12 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition
Hang luo
Yixiang Chen 1:00pm 7:30pm 6h30min learing MFCC
Yanqing Wang
2016.11.13 Ying Shi
Hang luo
Yixiang Chen
Yanqing Wang
2016.11.14 Ying Shi 9:30pm 9:30pm 12h kazak speech recognition AM down some work about decode
Hang luo 9:30am 7:30pm 10h Know language model and ready for experiments
Yixiang Chen 9:30am 10:00pm 12h30min replay test ready
Yanqing Wang
2016.11.15 Ying Shi 9:30pm 9:30pm 12h prepare LM for kazak speech recongition
Hang luo
Yixiang Chen 9:30am 7:30pm 10h finish MLbook chapter 7
Yanqing Wang
2016.11.16 Ying Shi 9:30pm 9:30pm 12h some work about HCLG.fst
Hang luo 9:30am 7:30pm 10h Read Inter Speech paper
Yixiang Chen 9:30am 7:30pm 10h processing data for replay
Yanqing Wang
2016.11.17 Ying Shi 9:30pm 9:30pm 12h 4 experiment for kazak decoding the result is poor maybe we need new corpus for lm
Hang luo 9:30pm 7:30am 10h Try simple language model and find its accuracy
Yixiang Chen 9:30pm 7:30pm 10h dividing frequency band test
Yanqing Wang
2016.11.18 Ying Shi 9:30pm 9:30pm 12h some work about kazak speech recognition LM
Hang luo 9:30am 7:30pm 10h Fixed LRE model and do experiments
Yixiang Chen 12:30am 7:30pm 7h dividing Mel frequency band test
Yanqing Wang
2016.11.19 Ying Shi
Hang luo
Yixiang Chen 12:30am 7：30pm 7h change weight on Frequency and replay test
Yanqing Wang
2016.11.21 Ying Shi 2:30pm 6:00pm 3.5h check corpus with teacher SAMAHAN
Hang luo 9:30pm 6:30am 9h Read LRE code and modify configuration
Yixiang Chen 9:30am 8:00pm 10h30min Complete the comparison of Frequency and Mel
Yanqing Wang 9:00 pm 10:30 pm 13h30min Learn to use Qt Creator
2016.11.22 Ying Shi 9:30 9:30 12h paper about visualization
Hang luo 9:30am 6:30pm 9h Run the changed model
Yixiang Chen 9:30am 7:30pm 10h To prepare UBM database,join replay data
Yanqing Wang 9:00am 8:00pm 11h learn to create Qt project in Visual Studio and Qt creator
2016.11.23 Ying Shi 9:30 9:30 12h data cleaning about kazak speech paper about visualization
Hang luo 2:00pm 7:00pm 5h Summay readed paper
Yixiang Chen 9:30am 8:30pm 11h To find the best configuration(num_bin) and the experiment
Yanqing Wang
2016.11.24 Ying Shi 9:30 9:30 12h new dnn model with different activation function (Sigmod Tanh relu pnorm)
Hang luo 9:30am 6:30pm 9h Share 4 papers
Yixiang Chen 9:30am 8:30pm 11h To find the best configuration and the experiment
Yanqing Wang
2016.11.25 Ying Shi 9:30 6：00 8：30h new dnn model with different activation function (Sigmod Tanh relu pnorm) and finish the ML book
Hang luo 9:30am 6:30pm 9h Continue doing experiments on fixed LRE model
Yixiang Chen 9:30am 8:30pm 11h Comparative experiments on linear and MEL effect
Yanqing Wang
2016.11.26 Ying Shi
Hang luo
Yixiang Chen
Yanqing Wang
2016.11.27 Ying Shi 11：00am 8：50pm work at home some work about new dnn and cnn visualization
Hang luo
Yixiang Chen
Yanqing Wang
2016.11.28 Ying Shi 9:40am 9:40pm 12h cnn visualization sparsity of network.There are too many point on the matlab figure so it can't be open,I will try another way.
Hang luo
Yixiang Chen 9:30am 5:30pm 8h dividing frequency band and compute EER of bank
Yanqing Wang 9:00am 11:00pm 14h continue to implement the LibSVM toolkit in Visual Studio
2016.11.29 Ying Shi 9:30am 9:00pm 11h30m the coming visulization job will focus on activation function so I read some paper about activation function(cnn sparsity will be finish in this week)
Hang luo
Yixiang Chen 9:30am 7:30pm 10h compare baseline and weight , warping test
Yanqing Wang
2016.11.30 Ying Shi 9:30am 9:30pm 12h upload ml-book to cvs paper reading
Hang luo
Yixiang Chen 9:30am 7:30pm 10h compare warping and weight
Yanqing Wang

Time Off Table

Name Days off
Ying Shi 1+0.5
Hang luo 0.5+1+0.5+2
Yixiang Chen 1+1+1+1
取自“http://index.cslt.org/mediawiki/index.php?title=Asr-progress_2016.11&oldid=24536”