cslt Wiki - 用户贡献 [zh-cn]

文件:Paper-outline-0611.pdf

2019-06-28T10:24:31Z

Qizhaodi：Qizhaodi上传“文件:Paper-outline-0611.pdf”的新版本

文件:Paper-outline-0611.pdf

2019-06-11T11:58:11Z

Qizhaodi：

文件:Paper-1.pdf

2019-06-11T01:13:07Z

Qizhaodi：

文件:Paper-1修改.docx

2019-06-11T01:06:24Z

Qizhaodi：

文件:Paper-1.docx

2019-06-11T00:54:17Z

Qizhaodi：

文件:实验报告4-adapt domain.pdf

2019-06-03T10:33:52Z

Qizhaodi：

2019-05-31

2019-05-31T00:05:59Z

Qizhaodi：

{| 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
||
*
||
*
||
*
|-

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

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

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

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

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

|}

文件:Png-1.png

2019-05-30T10:35:38Z

Qizhaodi：

2019-05-24

2019-05-23T23:59:29Z

Qizhaodi：

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

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

|-
|Xiuqi Jiang
||
* Compiling the data of planning and training set, unifying data formats
||
* Re-plan training set using planning results
* Doing summary work
||
*
|-

|-
|Jiayao Wu
||
* made further research on sentence-level resample boosting and trying frame-level method.
||
* prepare for the weekly report.
*keep on doing frame-level research.
||
*
|-

|-
|Zhaodi Qi
||
* Do experiment on Multi-language BN
||
* Summary of the experiment
||
*
|-

|-
|Jiawei Yu
||
* Done part of ivector and dvector in-set LID experiment.
* Experimented different test utterance lengths(1s, 3s, full length) for zero-resource LID.
||
* Test the in-set language for different test utterance length(1s, 3s).
||
*
|-

|-
|Wenwei Dong
||
* -
||
* Try speaker level correlation.
* Collect different language background speaker's English data to train info-GAN.
||
*
|-

|-
|Xueyi Wang
||
* reproducing the experiments of v-vector and c-vector; result is close to the one in the paper
||
* get down to unsupervised PLDA
||
*
|-

|-
|Ziya Zhou
||
* Downloaded videos of 258 celebrities
* Complete the downloading task by next Monday
||
* Edit the videos
||
*
|-

|-
|kaicheng li
||
* Collect celebrity audio data （100）
||
* Continue collecting celebrity audio data
||
*
|-

|-
|Haolin Chen
||
* Maths: statistical inference, integer programming
||
* Continue learning statistics
||
*
|-

|-
|Haoran Sun
||
* Completed the testing table of asr engine
||
* Test the concurrence of asr engine
||
*
|-

|}

文件:Bnf-xvector.png

2019-05-22T11:49:27Z

Qizhaodi：

文件:Xvector-qzd.png

2019-05-22T11:47:22Z

Qizhaodi：

文件:实验报告2-Multi scale information-190517.pdf

2019-05-20T11:29:27Z

Qizhaodi：

2019-05-17

2019-05-16T11:10:42Z

Qizhaodi：

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

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

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

|-
|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
||
*
||
*
||
*
|-

|-
|Wenwei Dong
||
*
||
*
||
*
|-

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

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

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

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

|}

文件:Fig-9.png

2019-05-16T10:42:50Z

Qizhaodi：

文件:Fig-8.png

2019-05-16T10:42:27Z

Qizhaodi：

文件:Fig-7.png

2019-05-12T04:50:51Z

Qizhaodi：

2019-05-10

2019-05-10T06:02:58Z

Qizhaodi：

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

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

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

|-
|Jiayao Wu
||
*
||
*
||
*
|-

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

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

|-
|Dan He
||
*
||
*
||
*
|-

|-
|Wenwei Dong
||
*
||
*
||
*
|-

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

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

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

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

|}

文件:Fig-6.png

2019-05-09T04:43:52Z

Qizhaodi：

文件:Fig-5.png

2019-05-08T01:11:32Z

Qizhaodi：

文件:实验报告1.pdf

2019-05-07T01:10:21Z

Qizhaodi：

文件:Fig-4b.png

2019-05-06T05:53:21Z

Qizhaodi：

文件:Fig-4a.png

2019-05-06T05:52:50Z

Qizhaodi：

文件:Fig-2c.png

2019-04-29T09:05:06Z

Qizhaodi：

文件:Fig-2b.png

2019-04-29T09:04:00Z

Qizhaodi：

文件:Fig-2a.png

2019-04-29T09:03:23Z

Qizhaodi：

文件:Fig-3b.png

2019-04-29T09:00:20Z

Qizhaodi：

文件:Fig-3a.png

2019-04-29T08:59:51Z

Qizhaodi：

文件:Fig-1.png

2019-04-29T08:24:27Z

Qizhaodi：

2018

2019-04-19T01:00:24Z

Qizhaodi：

== ASR ==

*[[媒体文件:181107-ASR-WJY.pptx | 181107-吴嘉瑶-Overview of ASR]]

==VPR==

*[[媒体文件:181107-SRE-YJW.pptx | 181107-于嘉威-Overview of VPR]]

*[https://arxiv.org/pdf/1808.00158.pdf 181114-VPR from raw waveform]

*[[媒体文件:190306-zy-report.pptx | 190306-张阳 experiments report]]*

*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/82/I-vector_representation_based_on_GMM_and_DNN.pdf 190418-齐诏娣-I-vector_representation_based_on_GMM_and_DNN]

==Scoring==
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5c/190117-DWW-Scoring.pptx 190117-董文伟-Overview of Scoring]]

==Text generation==

*[https://arxiv.org/pdf/1803.07133.pdf Overview-2018-Neural Text Generation: Past, Present and Beyond]

==Conversational system==
*[https://arxiv.org/pdf/1809.08267.pdf Overview-2018-Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogue and Chatbots: A Unified View] [https://www.microsoft.com/en-us/research/uploads/prod/2018/07/neural-approaches-to-conversational-AI.pdf slides]

==Deep architecture and mechanism==

*[https://arxiv.org/pdf/1510.00149.pdf 181114-deep compression]

*[[媒体文件:Tensor factorization neural net.pdf | 181212-何丹-Tensor factorization neural net]]

==Learning theory==

*[[媒体文件:181205 Meta-Learning and Zero-Shot Learning JXQ.pdf | 181205 姜修齐 Meta-Learning and Zero-Shot Learning]]

==Platform and tool==

*[[媒体文件:181116-张阳-Conda_&_Python.pdf | 181116-张阳-Conda & Python]]

*[[媒体文件:181117-张阳-Linux.pdf | 181117-张阳-Linux]]

*[https://pan.baidu.com/s/13qf-GqOSE4DK7q5VjbtWNA PyTorch 1.0 - Bringing research and production together Presentation]

2018

2019-04-19T01:00:06Z

Qizhaodi：

== ASR ==

*[[媒体文件:181107-ASR-WJY.pptx | 181107-吴嘉瑶-Overview of ASR]]

==VPR==

*[[媒体文件:181107-SRE-YJW.pptx | 181107-于嘉威-Overview of VPR]]

*[https://arxiv.org/pdf/1808.00158.pdf 181114-VPR from raw waveform]

*[[媒体文件:190306-zy-report.pptx | 190306-张阳 experiments report]]*

*[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/82/I-vector_representation_based_on_GMM_and_DNN.pdf 190418-齐诏娣-I-vector_representation_based_on_GMM_and_DNN]]

==Scoring==
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5c/190117-DWW-Scoring.pptx 190117-董文伟-Overview of Scoring]]

==Text generation==

*[https://arxiv.org/pdf/1803.07133.pdf Overview-2018-Neural Text Generation: Past, Present and Beyond]

==Conversational system==
*[https://arxiv.org/pdf/1809.08267.pdf Overview-2018-Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogue and Chatbots: A Unified View] [https://www.microsoft.com/en-us/research/uploads/prod/2018/07/neural-approaches-to-conversational-AI.pdf slides]

==Deep architecture and mechanism==

*[https://arxiv.org/pdf/1510.00149.pdf 181114-deep compression]

*[[媒体文件:Tensor factorization neural net.pdf | 181212-何丹-Tensor factorization neural net]]

==Learning theory==

*[[媒体文件:181205 Meta-Learning and Zero-Shot Learning JXQ.pdf | 181205 姜修齐 Meta-Learning and Zero-Shot Learning]]

==Platform and tool==

*[[媒体文件:181116-张阳-Conda_&_Python.pdf | 181116-张阳-Conda & Python]]

*[[媒体文件:181117-张阳-Linux.pdf | 181117-张阳-Linux]]

*[https://pan.baidu.com/s/13qf-GqOSE4DK7q5VjbtWNA PyTorch 1.0 - Bringing research and production together Presentation]

2018

2019-04-19T00:59:42Z

Qizhaodi：

== ASR ==

*[[媒体文件:181107-ASR-WJY.pptx | 181107-吴嘉瑶-Overview of ASR]]

==VPR==

*[[媒体文件:181107-SRE-YJW.pptx | 181107-于嘉威-Overview of VPR]]

*[https://arxiv.org/pdf/1808.00158.pdf 181114-VPR from raw waveform]

*[[媒体文件:190306-zy-report.pptx | 190306-张阳 experiments report]]*

*[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/82/I-vector_representation_based_on_GMM_and_DNN.pdf |190418-齐诏娣-I-vector_representation_based_on_GMM_and_DNN]]

==Scoring==
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5c/190117-DWW-Scoring.pptx 190117-董文伟-Overview of Scoring]]

==Text generation==

*[https://arxiv.org/pdf/1803.07133.pdf Overview-2018-Neural Text Generation: Past, Present and Beyond]

==Conversational system==
*[https://arxiv.org/pdf/1809.08267.pdf Overview-2018-Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogue and Chatbots: A Unified View] [https://www.microsoft.com/en-us/research/uploads/prod/2018/07/neural-approaches-to-conversational-AI.pdf slides]

==Deep architecture and mechanism==

*[https://arxiv.org/pdf/1510.00149.pdf 181114-deep compression]

*[[媒体文件:Tensor factorization neural net.pdf | 181212-何丹-Tensor factorization neural net]]

==Learning theory==

*[[媒体文件:181205 Meta-Learning and Zero-Shot Learning JXQ.pdf | 181205 姜修齐 Meta-Learning and Zero-Shot Learning]]

==Platform and tool==

*[[媒体文件:181116-张阳-Conda_&_Python.pdf | 181116-张阳-Conda & Python]]

*[[媒体文件:181117-张阳-Linux.pdf | 181117-张阳-Linux]]

*[https://pan.baidu.com/s/13qf-GqOSE4DK7q5VjbtWNA PyTorch 1.0 - Bringing research and production together Presentation]

文件:I-vector representation based on GMM and DNN.pdf

2019-04-19T00:56:37Z

Qizhaodi：

2019-02-27

2019-02-27T05:14:27Z

Qizhaodi：

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

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

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

|-
|Jiayao Wu
||
*
||
*
||
*
|-

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

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

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

|-
|Dan He
||
*
||
*
||
*
|-

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

|-
|Wenwei Dong
||
*
||
*
||
*
|-

|}

2019-02-20

2019-02-20T04:20:40Z

Qizhaodi：

{| 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
||
* improve the system ，because the results is 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
||
*
|-

|}

2019-02-20

2019-02-20T04:17:59Z

Qizhaodi：

{| 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
||
*
||
*
||
*
|-

|}

2019-02-04

2019-01-24T06:03:27Z

Qizhaodi：

$ Happy new year :) $

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

|-
|Yibo Liu
||

||

||

|-

|-
|Xiuqi Jiang
||

||

||

|-

|-
|Jiayao Wu
||
1月25日
||
2月12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
||

||

||

|-

|}

2019-01-23

2019-01-23T04:26:53Z

Qizhaodi：

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

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

|-
|Xiuqi Jiang
||
* Designed a better code structure for further experiments.
* Improved vivi2.0 and made some adjustments to .sh script.
||
* Build codes under the new structure.
||
*
|-

|-
|Jiayao Wu
||
* do experiments on node_sparseness and update it on cvss
* re-label some data
||
* keep on doing experiments on pruning
* get familiar with pytorch
||
*
|-

|-
|Zhaodi Qi
||
* Reduce the lid model and test the results
* Test test set of different channels
* Wrote a model based on asr(tdnn-f)-lid(tdnn) (similar to PTN) to solve channel inconsistency
||
* Complete the asr-lid model
||
*
|-

|-
|Jiawei Yu
||
* wrote a tensorflow learning document, and I have not completed it.
* read some papers about attention and find some attention code in GitHub.
||
* try to run these attention code figure out mechanism of this code.
||
*
|-

|-
|Yunqi Cai
||
*1,figured out how the Bert model create the pretraining data and do the pretraining.
*2,try to use the Bert to do the error correction of a text sentence.
*3,re-label some ASR data
*4,Test vivi2.0 model
||
*Construct a Text sentence error correction model
||
*
|-

|-
|Dan He
||
*Do experiments on comparing test time and update it on cvss

||
*
||
*
|-

|-
|Yang Zhang
||
* 1. remodified nginx configuration and changed the server networking structure
* 2. tried to learn vae and did a [https://github.com/hwalsuklee/tensorflow-mnist-VAE test] in wolf server
||
* continue to learn and test VAE
||
*
|-

|}

2019-01-16

2019-01-16T04:46:47Z

Qizhaodi：

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

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

|-
|Xiuqi Jiang
||
* Focused back on the quatrain generation, thinking of the drawbacks of current model.
* Tried to weaken the attention mechanism between sentences.
||
* Add VAE into model and try to generate instead of predicting.
||
*
|-

|-
|Jiayao Wu
||
*continue doing sparse-node experiment using the mask method
||
*run through the first experiment
||
*
|-

|-
|Zhaodi Qi
||
* Finish the speech language recognition of speech book.
* Compared the experiments of tdnn model under different duration test sets
* Research on model acceleration and model compression
||
* Do experiments to make the lid model smaller and faster
||
*
|-

|-
|Jiawei Yu
||
* Finish the speech emotion recognition of speech book.
* Learning the tensorflow tutorial.
||
* keep learning tensorflow and do some experiment.
||
*
|-

|-
|Yunqi Cai
||
*1.Run through the bert model. 2.study the details of the bert model.
||
*
||
*
|-

|-
|Dan He
||
*Doing some comparative experiments about TT-decompositions.
||
*Summarize the results of the comparative experiments and initially complete the relevant research on TT-decomposition.
||
*
|-

|-
|Yang Zhang
||
* exam week.
||
* (I will finish all my exams on Friday night)
||
*
|-

|}

Speech book

2019-01-14T00:59:36Z

Qizhaodi：/* 语种识别（诏娣） */

'''《语音识别基本法》'''

*[[媒体文件:20190113a speech book.pdf | Version 20190113a]]

*[[媒体文件:20190113 speech book.pdf | Version 20190113]]

*[[媒体文件:20181226 speech book.pdf | Version 20181226]]

*[[媒体文件:20181225 speech book.pdf | Version 20181225]]

*[[媒体文件:20181224 speech book.pdf | Version 20181224]]

*Tex on [https://gitlab.com/tzyll/speech_book GitLab]

=语音识别基础 (阿汤)=
==语音是什么==
==语音识别方法==
==语音识别工具==

=语音识别基本流程（阿汤）=
==实验先行==
==前端处理==
==训练与解码==

=语音识别实际问题=
==说话人自适应（启明）==
[[媒体文件:Spk.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/spk-adapt.rar latex]

==噪声对抗与环境鲁棒性（启明）==

[[媒体文件:Noise.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/noise-robust.rar latex]

==新词处理与领域泛化（文强）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ef/New_word_du.pdf pdf]

==小语种识别（石颖）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Minority_20190109.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/02/Minority_asr.rar LaTex]

==关键词唤醒与嵌入式系统（嘉瑶）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/70/Kws.rar Latex]

=前沿课题=
==说话人识别（蓝天）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Sre.pdf pdf]

==语种识别（诏娣）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Lid.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9e/LID-speekbook.rar latex]

==情绪识别（嘉威）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/28/语音情绪识别.pdf pdf]

==语音合成（启明）==

[[媒体文件:Tts.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/tts.rar latex]

Speech book

2019-01-14T00:15:09Z

Qizhaodi：/* 语种识别（诏娣） */

'''《语音识别基本法》'''

*[[媒体文件:20190113a speech book.pdf | Version 20190113a]]

*[[媒体文件:20190113 speech book.pdf | Version 20190113]]

*[[媒体文件:20181226 speech book.pdf | Version 20181226]]

*[[媒体文件:20181225 speech book.pdf | Version 20181225]]

*[[媒体文件:20181224 speech book.pdf | Version 20181224]]

*Tex on [https://gitlab.com/tzyll/speech_book GitLab]

=语音识别基础 (阿汤)=
==语音是什么==
==语音识别方法==
==语音识别工具==

=语音识别基本流程（阿汤）=
==实验先行==
==前端处理==
==训练与解码==

=语音识别实际问题=
==说话人自适应（启明）==
[[媒体文件:Spk.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/spk-adapt.rar latex]

==噪声对抗与环境鲁棒性（启明）==

[[媒体文件:Noise.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/noise-robust.rar latex]

==新词处理与领域泛化（文强）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ef/New_word_du.pdf pdf]

==小语种识别（石颖）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Minority_20190109.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/02/Minority_asr.rar LaTex]

==关键词唤醒与嵌入式系统（嘉瑶）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/70/Kws.rar Latex]

=前沿课题=
==说话人识别（蓝天）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Sre.pdf pdf]

==语种识别（诏娣）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Lid.pdf pdf]
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9e/LID-speekbook.rar latex]

==情绪识别（嘉威）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/28/语音情绪识别.pdf pdf]

==语音合成（启明）==

[[媒体文件:Tts.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/tts.rar latex]

文件:LID-speekbook.rar

2019-01-14T00:13:44Z

Qizhaodi：

Speech book

2019-01-11T09:05:28Z

Qizhaodi：/* 语种识别（嘉威） */

'''《语音识别基本法》'''

*[[媒体文件:20181226 speech book.pdf | Version 20181226]]

*[[媒体文件:20181225 speech book.pdf | Version 20181225]]

*[[媒体文件:20181224 speech book.pdf | Version 20181224]]

=语音识别基础知识(阿汤)=
==语音是什么==
==语音识别方法==
==语音识别工具==

=语音识别基本流程（阿汤）=
==语音识别流程速览==
==声学特征==
==GMM-HMM==
==DNN==
==解码器==

=语音识别实际问题=
==说话人自适应（启明）==
[[媒体文件:Spk.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/spk-adapt.rar latex]

==噪声对抗与环境鲁棒性（启明）==

[[媒体文件:Noise.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/noise-robust.rar latex]

==新词处理与领域泛化（文强）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ef/New_word_du.pdf pdf]

==小语种识别（石颖）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Minority_20190109.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/02/Minority_asr.rar LaTex]

==关键词唤醒与嵌入式系统（嘉瑶）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/70/Kws.rar Latex]

=前沿课题=
==说话人识别（蓝天）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Sre.pdf pdf]

==语种识别（诏娣）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Lid.pdf pdf]

==情绪识别（嘉威）==

==语音合成（启明）==

Speech book

2019-01-11T09:02:46Z

Qizhaodi：/* 情绪识别（诏娣） */

'''《语音识别基本法》'''

*[[媒体文件:20181226 speech book.pdf | Version 20181226]]

*[[媒体文件:20181225 speech book.pdf | Version 20181225]]

*[[媒体文件:20181224 speech book.pdf | Version 20181224]]

=语音识别基础知识(阿汤)=
==语音是什么==
==语音识别方法==
==语音识别工具==

=语音识别基本流程（阿汤）=
==语音识别流程速览==
==声学特征==
==GMM-HMM==
==DNN==
==解码器==

=语音识别实际问题=
==说话人自适应（启明）==
[[媒体文件:Spk.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/spk-adapt.rar latex]

==噪声对抗与环境鲁棒性（启明）==

[[媒体文件:Noise.pdf|pdf]]

[http://wangd.cslt.org/book/kaldi/noise-robust.rar latex]

==新词处理与领域泛化（文强）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ef/New_word_du.pdf pdf]

==小语种识别（石颖）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Minority_20190109.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/02/Minority_asr.rar LaTex]

==关键词唤醒与嵌入式系统（嘉瑶）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf pdf]

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/70/Kws.rar Latex]

=前沿课题=
==说话人识别（蓝天）==

[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Sre.pdf pdf]

==语种识别（嘉威）==
==情绪识别（嘉威）==

==语音合成（启明）==

文件:Lid.pdf

2019-01-11T09:01:16Z

Qizhaodi：

2019-01-09

2019-01-09T03:12:53Z

Qizhaodi：

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

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

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

|-
|Jiayao Wu
||
* finished the speech book -- [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf kws]
* doing experiment of node -pruning on WSJ chain model
||
* keep on node-pruning research
||
*
|-

|-
|Zhaodi Qi
||
* Run LID (about Chinese English and Japanese) and Control configs_size within 20M，But it still running.
* Data segmentation completed, and Waiting for test.
||
* Finish the speech book
* Completion the tdnn system performance comparison of test sets of different lengths
||
*
|-

|-
|Jiawei Yu
||
* Done for max-margin recipe.
* write the speech book.
* learn to use Tensorflow for attention experiment.
||
* finish the emotion recognition speech book.
* Keep learning the Tensorflow and move max-margin experiment to this platform.
||
*
|-

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

|-
|Dan He
||
* Compared the inference time, but the results is not well.
*After TT decomposing the two full-connection layers, it is found that the testing accuracy is very low.
||
*According to some problems found in the experiment, continue to do comparative experiments and analyze the reasons.
||
*
|-

|-
|Yang Zhang
||
* Wrote a brief [https://github.com/zyzisyz/VPR-wx-client document]
* submited the source code to [https://gitlab.com/zyzisyz/nebula-listen GitLab].
||
* revise for my school subjects and prepare for the final-term examinations.
||
*
|-

|}

2019-01-09

2019-01-09T03:11:29Z

Qizhaodi：

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

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

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

|-
|Jiayao Wu
||
* finished the speech book -- [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Kws.pdf kws]
* doing experiment of node -pruning on WSJ chain model
||
* keep on node-pruning research
||
*
|-

|-
|Zhaodi Qi
||
* Run LID (about Chinese English and Japanese) and Control configs_size within 20M，But the results are still running.
* Data segmentation completed, and Waiting for test.
||
* Finish the speech book
* Completion the tdnn system performance comparison of test sets of different lengths
||
*
|-

|-
|Jiawei Yu
||
* Done for max-margin recipe.
* write the speech book.
* learn to use Tensorflow for attention experiment.
||
* finish the emotion recognition speech book.
* Keep learning the Tensorflow and move max-margin experiment to this platform.
||
*
|-

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

|-
|Dan He
||
* Compared the inference time, but the results is not well.
*After TT decomposing the two full-connection layers, it is found that the testing accuracy is very low.
||
*According to some problems found in the experiment, continue to do comparative experiments and analyze the reasons.
||
*
|-

|-
|Yang Zhang
||
* Wrote a brief [https://github.com/zyzisyz/VPR-wx-client document]
* submited the source code to [https://gitlab.com/zyzisyz/nebula-listen GitLab].
||
* revise for my school subjects and prepare for the final-term examinations.
||
*
|-

|}

ML book

2019-01-07T08:03:38Z

Qizhaodi：

'''Introduction to Modern Machine Learning Technology, by Dong Wang, [http://mlbook.cslt.org Official website].
'''

----

Reading notes of interns
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a6/CSLTBOOK读书笔记.pdf Jiayao Wu (吴嘉瑶)]
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ec/读书笔记——于嘉威.pdf Jiawei Yu (于嘉威)]
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b1/机器学习读书笔记_姜修齐.pdf Xiuqi Jiang (姜修齐)]
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/ac/ML学习笔记_何丹.pdf Dan He (何丹)]
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/36/MLbooknotes_liuyibo.pdf Yibo Liu (刘逸博)]
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/30/ML%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0-%E9%BD%90%E8%AF%8F%E5%A8%A3.pdf Zhaodi Qi (齐诏娣)]

文件:ML学习笔记-齐诏娣.pdf

2019-01-07T08:02:06Z

Qizhaodi：

2019-01-02

2019-01-03T04:23:21Z

Qizhaodi：

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

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

|-
|Xiuqi Jiang
||
* Made further adjustments to code, deleting unnecessary files and uploading generated samples to dir 'predict/results'.
* More models have been trained and compared.
* Collated notes on ML book and uploaded them on wiki.
||
* Try to train a model generating length-unfixed texts.
||
*
|-

|-
|Jiayao Wu
||
* read some papers about kws and write the chapter before this weekend.
* carding the TDNN-F structure and count the lines of weights to prune and do value prune first.
||
* finish the assigned chapter of Speech book
* finish the value prune experiment
||
*
|-

|-
|Zhaodi Qi
||
* read some papers about DID and other
* Run language recognition task
||
* Continue to complete the language recognition task
||
*
|-

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

|-
|Yunqi Cai
||
*Run through the Thchs30 data, think about the research plan.
||
*Get to know every step of the ASR processes, and investigate the RNN LM.
||
*
|-

|-
|Dan He
||
*Compared the size of a fully connected layer after tt decomposition through experiment, at the same time compared the train loss, validation loss and test accuracy between the two case.
||
*Further compared the inference speed, the precision after retrain.
*Try to decompose more layers of fully connected layers.
||
*
|-

|-
|Yang Zhang
||
* Released and published our WeChat app(星云听).
* cleaned my code
* wrote document for this project (have not finished yet).
||
* continue to write document.
||
*
|-

|}

2019-01-02

2019-01-03T04:18:17Z

Qizhaodi：

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

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

|-
|Xiuqi Jiang
||
* Made further adjustments to code, deleting unnecessary files and uploading generated samples to dir 'predict/results'.
* More models have been trained and compared.
* Collated notes on ML book and uploaded them on wiki.
||
* Try to train a model generating length-unfixed texts.
||
*
|-

|-
|Jiayao Wu
||
* read some papers about kws and write the chapter before this weekend.
* carding the TDNN-F structure and count the lines of weights to prune and do value prune first.
||
* finish the assigned chapter of Speech book
* finish the value prune experiment
||
*
|-

|-
|Zhaodi Qi
||
* read some papers about DID
*
||
* Continue to complete the language recognition task
||
*
|-

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

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

|-
|Dan He
||
*Compared the size of a fully connected layer after tt decomposition through experiment, at the same time compared the train loss, validation loss and test accuracy between the two case.
||
*Further compared the inference speed, the precision after retrain.
*Try to decompose more layers of fully connected layers.
||
*
|-

|-
|Yang Zhang
||
* Released and published our WeChat app(星云听).
* cleaned my code
* wrote document for this project (have not finished yet).
||
* continue to write document.
||
*
|-

|}