FreeNeb Status Report 2017-06-19 - 版本历史

2017年6月19日 (一) 02:08 Zhaomy

2017-06-19T02:08:39Z

2017年6月19日 (一) 02:07 Zhaomy

2017-06-19T02:07:55Z

2017年6月19日 (一) 01:22 Zhangzy

2017-06-19T01:22:18Z

2017年6月19日 (一) 01:21 Zhangzy

2017-06-19T01:21:55Z

2017年6月19日 (一) 01:21 Zhaomy

2017-06-19T01:21:15Z

2017年6月19日 (一) 01:19 Zhaomy

2017-06-19T01:19:36Z

2017年6月19日 (一) 01:17 Zhaomy

2017-06-19T01:17:59Z

2017年6月19日 (一) 00:39 Cslt

2017-06-19T00:39:14Z

2017年6月19日 (一) 00:36 Ruanmr

2017-06-19T00:36:51Z

Zhaomy：以“This Week: {| class="wikitable" !People !! Last Week !! This Week !! Next Week !! Task Tracing(DeadLine) |- |Mengyuan Zhao || * Tonghuashun...”为内容创建页面

2017-06-19T00:09:29Z

以“This Week: {| class="wikitable" !People !! Last Week !! This Week !! Next Week !! Task Tracing(DeadLine) |- |Mengyuan Zhao || * Tonghuashun...”为内容创建页面

新页面

This Week:
{| class="wikitable"
!People !! Last Week !! This Week !! Next Week !! Task Tracing(DeadLine)
|-
|Mengyuan Zhao ||
* Tonghuashun
# Prepare 3rd period delivery.
* Embedded ASR
# Clean up code, finished.
* Roobo
# Cross-compilation.
||
* Embedded ASR
# Try to add nnet3.
||
||
* Tonghuashun
# confirm general testset (20170512)
* Embedded ASR
# Add nnet3 (20170622)
|-
|Zhiyong Zhang ||
* Finished phoneme-based TTS test
||
* To revise the text-linguistic feature extraction to avoid the multi-pronunciation problem
||
* Test LSTM-base KALDI-TTS
||
* To finish the phoneme-based KALDI-TTS(20170616);

|-
|Yang Wei ||
* Learn RNN language model training principle and tool.
||
* Read the source code of RNNLM tool
||

||
* Similar-pair on Tonghuashun's LM.
|-
|Dong Wang||
* Second phase payment done
* Some discussion for Awer
||
* keep an eye on Tonghuashun delivery
||

||

|-
|Mingrui Ruan||
* about FreeNeb
||
* 云服务器备案相关
* 同花顺的项目节点及推进
* 与爱维尔合作相关
* 拜访一个客户
||

||

|-
|Zhenlong Han||
* Traing both uni and bi CTC model on data 1000h.
* 1000h dnn model has been trained to complete.
* Wake up with LM and phone-loop model has been test.
* Write XenC documentation.
||
* Adjust weight on phone-loop model.
||
* Wake up.
||
* Test various output level of CTC
# LSTM layer number (20170515)
# Frame skipping (20170515)
* Roobo
# First version of "wake up".
|-
|}

@@ 第32行： / 第32行： @@
 |Yang Wei ||
 * Crawl 530M universal corpus from zhihu.com(crawler list: https://docs.google.com/spreadsheets/d/1VNtgnnRiez8HjjhpwDXqBvewQZp-tkivOUVA5qk0rPg/edit#gid=0)
 * Read source code of LM rescore
 ||

@@ 第27行： / 第27行： @@
 * Hold
 ||
-* To finish the phoneme-based KALDI-TTS</font>(<font color="red">20170616</font>,<font color="red">20170616</font>);
+* To finish the phoneme-based KALDI-TTS</font>(<font color="red">20170616</font>,<font color="red">20170623</font>);
 |-

@@ 第21行： / 第21行： @@
 |-
 |Zhiyong Zhang ||
-* Finished phoneme-based TTS test
+* Finished the run-pass for the phone-based TTS, but poor performance.
 ||
-* To revise the text-linguistic feature extraction to avoid the multi-pronunciation problem
+* To remove the silence from linguistic feature extraction
 ||
-* Test LSTM-base KALDI-TTS
+* Hold
 ||
-* To finish the phoneme-based KALDI-TTS</font>(<font color="red">20170616</font>);
+* To finish the phoneme-based KALDI-TTS</font>(<font color="red">20170616</font>,<font color="red">20170616</font>);
 |-

@@ 第31行： / 第31行： @@
 |-
 |Yang Wei ||
-* Crawl 530M universal corpus from zhihu.com
+* Crawl 530M universal corpus from zhihu.com(crawler list: https://docs.google.com/spreadsheets/d/1VNtgnnRiez8HjjhpwDXqBvewQZp-tkivOUVA5qk0rPg/edit#gid=0)
 * Read source code of LM rescore
 ||

@@ 第31行： / 第31行： @@
 |-
 |Yang Wei ||
-* Crawl 530M universal corpus from zhihu.com(crawler list: https://docs.google.com/spreadsheets/d/1VNtgnnRiez8HjjhpwDXqBvewQZp-tkivOUVA5qk0rPg/edit#gid=0)
+* Learn RNN language model training principle and tool.
-* Read source code of LM rescore
 ||
 * Read the source code of RNNLM tool
@@ 第63行： / 第62行： @@
 |Zhenlong Han||
 * Traing both uni and bi CTC model on data 1000h.
-* 1000h dnn model has been trained to complete.
+* 1000h ctc-uni model has been trained to complete.
-* Wake up with LM and phone-loop model has been test.
-* Write XenC documentation.
 ||
-* Adjust weight on phone-loop model.
+* Modify dnn output pdf. but it does not work, I check the code many times, it's seems like the code is no bugs.
 ||
 * Wake up.

@@ 第40行： / 第40行： @@
 |-
 |Dong Wang||
-* Second phase payment done
+* Some discussion about the partner ship
-* Some discussion for Awer
 ||
-* keep an eye on Tonghuashun delivery
+* Start the first partnership project
 ||

@@ 第52行： / 第52行： @@
 * about FreeNeb
 ||
-* 云服务器备案相关
+* 官网建设的商讨
 * 同花顺的项目节点及推进
-* 与爱维尔合作相关
+* 与爱维尔合作的协议
 * 拜访一个客户
 ||