cslt Wiki - 用户贡献 [zh-cn]

2019-05-31

2019-05-31T00:06:31Z

Dongwenwei：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Yibo Liu
||
*
||
*
||
*
|-

|-
|Xiuqi Jiang
||
*
||
*
||
*
|-

|-
|Jiayao Wu
||
*prepare for the weekly report
*made a researh of different sampling method
||
* evaluate the model based on "frame accuracy"
||
*
|-

|-
|Zhaodi Qi
||
* prepare for the weekly report
* do some experiment about adapt domain
||
* continue to explore about adapt domain
||
*
|-

|-
|Jiawei Yu
||
* prepare for the weekly report.
* the in-set experiment for different test utterance length(1s, 3s) have been completed.
||
* test performance of different enroll utterance length and verification results.
||
*
|-

|-
|Wenwei Dong
||
* try speaker level scoring
* train infogan on big dataset
||
* test infogan and use different native background data train infogan
||
*
|-

|-
|Xueyi Wang
||
*
||
*
||
*
|-

|-
|Ziya Zhou
||
*
||
*
||
*
|-

|-
|kaicheng li
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|}

2019-05-17

2019-05-17T00:14:14Z

Dongwenwei：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Yibo Liu
||
*
||
*
||
*
|-

|-
|Xiuqi Jiang
||
* Recompiled the 1031k dataset and retrained the Seq2seq model.
||
* Justify the loss and fix the rhyme part.
||
*
|-

|-
|Jiayao Wu
||
*did some experiments of adaboost on ASR and have some basic results
*working on the speechbook
||
*keep on doing experiments on larger data_set.
||
*
|-

|-
|Zhaodi Qi
||
* Do experiment on Mult-scale information.
||
* Do experiment on Multi-language BN
||
*
|-

|-
|Jiawei Yu
||
* Did data preparation for zero-resource language recognition
||
* Continue to improve the experiment of zero-resource recognition
||
*
|-

|-
|Wenwei Dong
||
* prepare the report and use KL distance to predict score of L2 sentences
||
* add training data and try different languages
||
*
|-

|-
|Xueyi Wang
||
*
*
||
*
*
||
*
|-

|-
|Ziya Zhou
||
* Revised the speech book
* Made a list of 1,000 celebrities and downloaded videos of over 30 of them.
||
* Continue downloading and editing videos of another 150 celebrities.
||
*
|-

|-
|kaicheng li
||
*
*
||
*
*
||
*
|-

|-
|Haolin Chen
||
*
*
||
*
||
*
|-

|-
|Haoran Sun
||
* did some tests on Fn asr engine
* corrected some errors in the speech-book
||
* continue testing on the robustness of Fn asr engine
||
*
|-

|}

2019-05-10

2019-05-10T06:16:35Z

Dongwenwei：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Yibo Liu
||
*
||
*
||
*
|-

|-
|Xiuqi Jiang
||
* Merge code with Yibo and clean up current Vivi
||
* Polish up baselines and add extra regularizations to seq2seq loss
||
*
|-

|-
|Jiayao Wu
||
*made a summary of formal experiment
*prepare for the weekly report
*make a further try of Adaboost on ASR on chain model(to get rid of the influence of priors,no priors in chain model)
||
*try more experiments on Adaboost ASR
*modify the speech book
||
*
|-

|-
|Zhaodi Qi
||
* Summarized the previous experiments and explored new methods.
||
* Complete the experiment of Mult-scale information and Modify the speech book
||
*
|-

|-
|Jiawei Yu
||
*
||
*
||
*
|-

|-
|Wenwei Dong
||
* use frame fbank feature to train infogan, draw t-sne
||
*use gmm to learn the distribution of different dataset
||
*
|-

|-
|Xueyi Wang
||
*
*
||
*
||
*
|-

|-
|Ziya Zhou
||
*
||
*
*
*
||
*
|-

|-
|kaicheng li
||
*
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
*
||
*
*
||
*
|-

|}

文件:批注 2019-05-09 210801.png

2019-05-09T11:58:33Z

Dongwenwei：

文件:批注 2019-04-30 142743.png

2019-04-30T05:38:45Z

Dongwenwei：

文件:批注 2019-04-30 142537.png

2019-04-30T05:38:02Z

Dongwenwei：

文件:批注 2019-03-28 110115.png

2019-03-28T02:04:12Z

Dongwenwei：

文件:批注 2019-03-28 110047.png

2019-03-28T02:02:54Z

Dongwenwei：

文件:B536f2cd58d15907a7bc858612664c7200.png

2019-03-20T07:08:23Z

Dongwenwei：

文件:64c425151431519ddb5786ec6ed7ee6200.png

2019-03-20T07:07:53Z

Dongwenwei：

文件:911bd34eb0bd958189440602c5f1016100.png

2019-03-20T07:06:37Z

Dongwenwei：

文件:4c7bac6ff62c30bdae8bff04bbc84ef100.png

2019-03-20T07:06:05Z

Dongwenwei：

文件:1553069336(1).png

2019-03-20T07:00:28Z

Dongwenwei：

文件:1551670224(1).png

2019-03-04T02:22:13Z

Dongwenwei：

文件:1551670105(1).png

2019-03-04T02:21:25Z

Dongwenwei：

文件:1551669999(1).png

2019-03-04T02:20:34Z

Dongwenwei：

文件:D56dc4429100bc019335bb413128abc.png

2019-02-28T05:23:15Z

Dongwenwei：

2019-02-27

2019-02-28T03:23:59Z

Dongwenwei：

{| class="wikitable"
!People !! Last Week !! This Week !! Task Tracking (DeadLine)
|-

|-
|Yibo Liu
||
*
||
*
||
*
|-

|-
|Xiuqi Jiang
||
*
||
*
||
*
|-

|-
|Jiayao Wu
||
*did some experiments on small model & node_sparse model.
*research different layers' importance in noise environment on simple DNN using prune_node_method and waiting for the results.
||
*change environment and research layers' importance in different factors.
||
*
|-

|-
|Zhaodi Qi
||
* Did some experiments on xvector
||
* Adjust training data and continue experiment
||
*
|-

|-
|Jiawei Yu
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Dan He
||
*Study code about TTlayer
*Collect the latest information about tensor train decompositions
||
*Directly perform a TT-decomposition on a fully connected layer trained parameter
||
*
|-

|-
|Yang Zhang
||
* read two papers
* build a vae in tensorflow
* trained some model, and did some test in d/x -vector
||
* continue to train and test my model
||
*
|-

|-
|Wenwei Dong
||
* did some GAN experiment
||
*test model
||
*
|-

|}

文件:F8097ce403be326e6971b888d3e09f4.png

2019-02-27T08:19:02Z

Dongwenwei：

文件:222222.png

2019-02-27T08:14:41Z

Dongwenwei：

文件:1.png

2019-02-27T08:13:20Z

Dongwenwei：Dongwenwei上传“文件:1.png”的新版本

文件:1551082660(1).png

2019-02-25T07:08:53Z

Dongwenwei：

文件:1550818256.png

2019-02-22T05:41:51Z

Dongwenwei：

2019-02-20

2019-02-20T04:20:36Z

Dongwenwei：

{| class="wikitable"
!People !! Last Week !! This Week !! Task Tracking (DeadLine)
|-

|-
|Yibo Liu
||
*
||
*
||
*
|-

|-
|Xiuqi Jiang
||
*
||
*
||
*
|-

|-
|Jiayao Wu
||
*finished several experiments on node-sparseness
||
*keep on doing experiments
||
*
|-

|-
|Zhaodi Qi
||
* finished x-vector system
||
* adjust the parameters for situations where the results are bad.
||
*
|-

|-
|Jiawei Yu
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*1,use the ASR test_data set ref.txt to test the original bert and then compare with the fine-tuned Bert.
*2,compare the difference between hyp.text which comes from ASR test results, and investigate how to mask the error in the sentence of the ASR result.
*3,set a rule among all the result(hyp.text) to find out the error to be masked.
||
*
||
*
|-

|-
|Dan He
||
*
||
*Continue to study the time complexity of TT-decomposition
||
*
|-

|-
|Yang Zhang
||
*
||
*
||
*
|-

|-
|Wenwei Dong
||
*ivector+fbank as feature compare with fbank in GOP
||
*read papers, find some new speaker adaptation methods
||
*
|-

|}

2019-02-04

2019-01-24T10:18:22Z

Dongwenwei：

$ Happy new year :) $

{| class="wikitable"
!People !! Day home !! Day back !! Life Tracking
|-

|-
|Yibo Liu
||

||

||

|-

|-
|Xiuqi Jiang
||

||

||

|-

|-
|Jiayao Wu
||
1月25日
||
2月13日
||

|-

|-
|Zhaodi Qi
||
1月31日
||
预计2月13日（抢票中）
||

|-

|-
|Jiawei Yu
||
1月30号
||
预计2月10号（不过还没抢到票）
||

|-

|-
|Yunqi Cai
||

||

||

|-

|-
|Dan He
||

||

||

|-

|-
|Yang Zhang
||

||

||

|-

|-
|Wenwei Dong
||
1月30号
||
预计2月14号
||

|-

|}