“2018”版本间的差异
来自cslt Wiki
（→VPR） |
|||
| （10位用户的27个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
| + | 2018-2019 | ||
| − | |||
| − | + | == ASR == | |
| + | *[[媒体文件:语音识别系统.pdf | 181107-吴嘉瑶-Overview of ASR]] | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/38/Unsupervised_pre-training_for_speech_recognition.pdf 190515-董文伟-Unsupervised_pre-training_for_speech_recognition]] | ||
==VPR== | ==VPR== | ||
| − | *[ | + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/4a/Yjw_SRE_pre.pdf 181107-于嘉威-Overview of VPR] |
*[https://arxiv.org/pdf/1808.00158.pdf 181114-VPR from raw waveform] | *[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] | ||
| + | |||
| + | ==LRE== | ||
| + | |||
| + | *[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/80/Zero-resource_LID.pdf 190529-于嘉威-Zero-resource-LID]] | ||
| + | |||
| + | ==Scoring== | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5c/190117-DWW-Scoring.pptx 190117-董文伟-Overview of Scoring]] | ||
| + | |||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bc/Kandeng-English-scoring.pdf 190425-邓侃-English Evaluation techniques]] | ||
==Text generation== | ==Text generation== | ||
| 第29行： | 第42行： | ||
*[[媒体文件:Tensor factorization neural net.pdf | 181212-何丹-Tensor factorization neural net]] | *[[媒体文件:Tensor factorization neural net.pdf | 181212-何丹-Tensor factorization neural net]] | ||
| + | |||
| + | *[[媒体文件:Ensemble_2019.5.8.pdf | 190508-吴嘉瑶-ensemble of NN]] | ||
| + | |||
| + | *[[媒体文件:Knowledge_distillation_19.5.29.pdf | 190529-吴嘉瑶-knowledge distillation]] | ||
==Learning theory== | ==Learning theory== | ||
| 第40行： | 第57行： | ||
*[[媒体文件:181117-张阳-Linux.pdf | 181117-张阳-Linux]] | *[[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] | ||
| + | |||
| + | ==NLP language model== | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/07/Bert%E7%AE%80%E4%BB%8B.pdf Bert模型简介] | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/6f/Punc_prediction_%E6%80%BB%E7%BB%93.pdf bert based punctuation_prediction 实验总结] | ||
| + | |||
| + | ==Medical Image== | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b1/%E7%AD%94%E8%BE%A92.pdf 190522-刘逸博-基于人工智能的乳腺癌诊断] | ||
| + | |||
| + | ==User Guide of Fault Detection== | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/32/How_to_let_the_fault_detection_work_on_your_Raspberry_Pi.pdf 190802-孙浩然-异常检测树莓派配置教程] | ||
| + | |||
| + | ==User Guide of Cry Detection== | ||
| + | *[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/8c/Cry_detection_guide.pdf 190918-武烜宇-基于svm模型的哭声检测使用指南] | ||
2019年10月4日 (五) 12:19的最后版本
2018-2019
目录
ASR
VPR
LRE
Scoring
Text generation
Conversational system
- Overview-2018-Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogue and Chatbots: A Unified View slides
Deep architecture and mechanism
Learning theory
