“2018”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“* 2014-12-28 APSIPA paper reading *[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recogni...”为内容创建页面)
 
VPR
 
(11位用户的42个中间修订版本未显示)
第1行: 第1行:
*[[ VPR | 于嘉威 | 2014-12-28 APSIPA paper reading]]
+
2018-2019
  
*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recognition with Recurrent Neural Networks]
 
  
*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]
+
== ASR ==
  
*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]
+
*[[媒体文件:语音识别系统.pdf | 181107-吴嘉瑶-Overview of ASR]]
  
*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]
+
*[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==
 +
 
 +
*[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]
 +
 
 +
*[[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==
 +
 
 +
*[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]]
 +
 
 +
*[[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==
 +
 
 +
*[[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]
 +
 
 +
==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


ASR

VPR

LRE

Scoring

Text generation


Conversational system


Deep architecture and mechanism

Learning theory


Platform and tool

NLP language model

Medical Image

User Guide of Fault Detection

User Guide of Cry Detection