“Weekly meeting”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（43位用户的573个中间修订版本未显示）
第1行： 第1行：
 +
*Location: FIT-1-304
 +
 +
 
{| class="wikitable"
 
{| class="wikitable"
 
! Date !! Speaker!! Title !! Materials !! On duty
 
! Date !! Speaker!! Title !! Materials !! On duty
 
|-
 
|-
−
| 2012/08/27  ||Dong Wang  || Heterogeneous Convolutive Non-negative Sparse Coding || [http://homepages.inf.ed.ac.uk/v1dwang2/public/pdf/cslt-presentation.2012.8.27.pdf slides] [http://homepages.inf.ed.ac.uk/v1dwang2/public/pdf/inerspeech2012-hetero.pdf paper] ||
+
| 2012/08/27  ||Dong Wang  || Heterogeneous Convolutive Non-negative Sparse Coding ||[[媒体文件:Heterogeneous_convolutive_non-negative_sparse_coding.pdf|slides]] [http://homepages.inf.ed.ac.uk/v1dwang2/public/pdf/inerspeech2012-hetero.pdf paper] ||
 
|-
 
|-
−
| rowspan="2"|2012/09/03  ||??|| || ||
+
|2012/09/03  ||NO Meeting|| || ||
 
|-
 
|-
−
|??|| || ||
+
|2012/09/10  || NO Meeting|| || ||
 
|-
 
|-
−
| rowspan="2"|2012/09/10 ||WALEED ABDULLA|| Gamma-tone features for speaker recognition || ||
+
|2012/09/17 ||WALEED ABDULLA||Auditory Based Feature Vectors for Speech Recognition ||[[媒体文件:AuditoryBasedFeatureVectors.pdf|slides]]||范淼
 
|-
 
|-
−
|??|| || ||
+
| rowspan="2"|2012/09/24  ||刘超|| N-gram FST indexing for Spoken Term Detection || [[媒体文件:120924-N_gram_FST_indexing_for_Spoken_Term_Detection-LC-0.pdf|slides]] ||尹聪
 
|-
 
|-
−
| rowspan="2"|2012/09/17  ||??|| || ||
+
|范淼||Micro-blogging, Wikipedia, Folksonomy, What's Next? ||[[媒体文件:120924-Micro-blogging, Wikipedia, Folksonomy, What's Next-FM--01-FM-.pdf|slides]] ||
 
|-
 
|-
−
|??|| || ||
+
| 2012/10/08 ||NO Meeting|| || ||
 
|-
 
|-
−
| rowspan="2"|2012/09/24 ||刘超|| || ||
+
| 2012/10/15 ||NO Meeting|| || ||
 
|-
 
|-
−
|范淼|| || ||
+
|2012/10/22||Wu Xiaojun||speaker recognition in CSLT ||[[媒体文件:VPR_in_CSLT.pdf|slides]]||卡尔
 
|-
 
|-
−
| rowspan="2"|2012/10/08 ||??|| || ||
+
| rowspan="1"|2012/10/29 ||王军||An overview of Automatic Speaker Diarization Systems || [[媒体文件:121027-Speaker Diarization-WJ.pdf|slides]] ||别凡虎
 
|-
 
|-
−
|??|| || ||
+
| rowspan="1"|2012/11/05  ||别凡虎||Experiments on Emotional Speaker Recognition||[[媒体文件:121104-Experiments_on_Emotional_Speaker_Recognition-BFH.pdf|slides]] ||刘超
 
|-
 
|-
−
| rowspan="2"|2012/10/15 ||唐国瑜|| || ||
+
| rowspan="1"|2012/11/12 ||唐国瑜||Statistical Word Sense Improves Document Clustering ||[[媒体文件:121112_Statistical_Word_Sense_Improves_Document_Clustering_TGY.pdf‎ |slides]]||邱晗
 
|-
 
|-
−
|王俊俊|| || ||
+
| rowspan="1"|2012/11/19  ||张陈昊||TDSR with Long-term Features Based on Functional Data Analysis||[[媒体文件:121118-ISCSLP-FDA_SR-ZCH.pdf|slides]] ||王俊俊
 
|-
 
|-
−
| rowspan="2"|2012/10/22 ||别凡虎|| || ||
+
| rowspan="1"|2012/11/26 ||王琳琳||Time-Varying Speaker Recognition: An Introduction||[[媒体文件:121126-Time_Varying_Speaker_Recognition_I-Wll.pdf‎|slides]] ||龚宬
 
|-
 
|-
−
|龚宬|| || ||
+
| rowspan="1"|2012/12/03  ||No meeting|| || ||
 
|-
 
|-
−
| rowspan="2"|2012/10/29 ||邱晗|| || ||
+
| rowspan="1"|2012/12/10 ||No meeting|| || ||
 
|-
 
|-
−
|王军|| || ||
+
| rowspan="1"|2012/12/17  ||No meeting|| || ||
 +
 
 
|-
 
|-
−
| rowspan="2"|2012/11/05 ||??|| || ||
+
| rowspan="1"|2012/01/07 || || || ||
 
|-
 
|-
−
|??|| || ||
+
|2012/01/07  ||王军||基于DF-MAP的说话人模型训练方法||[[媒体文件:130107-基于DFMAP的说话人模型训练方法-WJ.pdf|slides]] ||唐国瑜
 
|-
 
|-
−
| rowspan="2"|2012/11/12 ||王琳琳|| || ||
+
| rowspan="1"|2012/01/14 ||王东|| Computing in CSLT ||[[媒体文件:Computing_in_CSLT.pdf|slides]] ||王琳琳
 
|-
 
|-
−
|唐国瑜|| || ||
+
 
 
|-
 
|-
−
| rowspan="2"|2012/11/19 ||龚宬|| || ||
+
| rowspan="1"|2013/03/04 ||王军||Sequential Adaptive Learning for Speaker Verification ||[[媒体文件:130301-Sequential adaptive learning for speaker verification-WJ.pdf|slides]] ||别凡虎
 
|-
 
|-
−
|张陈昊|| || ||
+
| rowspan="1"|2013/03/11  || Du Jinle|| VAD stuff || ||
 
|-
 
|-
−
| rowspan="2"|2012/11/26 ||??|| || ||
+
| rowspan="1"|2013/03/18 || || || ||
 
|-
 
|-
−
|??|| || ||
+
| rowspan="1"|2013/03/25  || || || ||
 
|-
 
|-
−
| rowspan="2"|2012/12/03 ||唐国瑜|| || ||
+
| rowspan="1"|2013/04/01 || || || ||
 
|-
 
|-
−
|王琳琳|| || ||
+
| rowspan="1"|2013/04/08  || 张陈昊|| A Fishervoice based Feature Fusion Method for SUSR ||[[媒体文件:130408-FisherVoice-ZCH.pdf|slides]] ||谢仲达
 
|-
 
|-
−
| rowspan="2"|2012/12/10 ||??|| || ||
+
| rowspan="1"|2013/04/15 ||龚宬|| An Exploration on Influence Factors of VAD's Performance in Speaker Recognition ||[[媒体文件:130415-An_Exploration_on_Influence_Factors_of_VAD-GC.pdf|slides]] ||
 
|-
 
|-
−
|??|| || ||
+
| rowspan="1"|2013/04/22  ||王俊俊 || Understanding the Query: THCIB and THUIS at NTCIR-10 Intent Task ||[[媒体文件:130422-Understanding_the_Query-WJJ.pdf|slides‎]] ||
 
|-
 
|-
−
| rowspan="2"|2012/12/17 ||王军|| || ||
+
| rowspan="1"|2013/04/29 || || || ||
 
|-
 
|-
−
|别凡虎|| || ||
+
| rowspan="1"|2013/05/06  ||别凡虎 ||MLLR on Emotional Speaker Recognition ||[[媒体文件:130506-MLLR on Emotional Speaker Recognition-BFH.pdf|slides]] ||
 
|-
 
|-
−
| rowspan="2"|2012/12/24 ||龚宬|| || ||
+
| rowspan="1"|2013/05/13 ||刘超 || The Use of Deep Neural Network for Speech Recognition || [[媒体文件:130513-the_use_of_dnn_for_asr-lc.pdf|slides]] ||
 
|-
 
|-
−
|王俊俊|| || ||
+
| rowspan="1"|2013/05/20  || || || ||
 
|-
 
|-
−
| rowspan="2"|2012/01/07 ||王琳琳|| || ||
+
| rowspan="1"|2013/05/27 ||王琳琳|| 说话人识别中的时变鲁棒性问题研究 || [[媒体文件:130527-TVSV-Wll.pdf|slides]] ||
 
|-
 
|-
−
|张陈昊|| || ||
+
| rowspan="1"|2013/06/03  ||王俊俊|| 汉语搜索结果聚类系统研究与实现 || [[媒体文件:130601-毕业答辩-02-WJJ.pdf|slides]] ||
 
|-
 
|-
−
| rowspan="2"|2012/01/14  ||邱晗|| || ||
+
| rowspan="1"|2013/06/10  || || || ||
 +
|-
 +
| rowspan="1"|2013/06/17  ||范淼 || Relation Extraction ||[[媒体文件:130617-relation_extraction-fm.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2013/06/24  ||唐国瑜 || Incorporating Statistical Word Senses in Topic Model  ||[[媒体文件:130624_Incorporating Statistical Word Senses in Topic Model_TGY.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2013/07/01  || || || ||
 +
|-
 +
| rowspan="1"|2013/07/08  ||  || || ||
 +
|-
 +
| rowspan="1"|2013/07/15  || || || ||
 +
|-
 +
| rowspan="1"|2013/09/09  ||王东 || Research Frontier in Speech Technology||[[媒体文件:Research Frontier in Speech Technology.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2013/09/16  || || || ||
 +
|-
 +
| rowspan="1"|2013/09/23  || || || ||
 +
|-
 +
| rowspan="1"|2013/09/30  || || || ||
 +
|-
 +
| rowspan="1"|2013/10/07  || || || ||
 +
|-
 +
| rowspan="1"|2013/10/14  || || || ||
 +
|-
 +
| rowspan="1"|2013/10/21  ||范淼 ||Transduction Classification with Matrix Completion （中文报告）||[[媒体文件: Transduction_Classifiction_with_Matrix_Completion.pdf‎|slides]] [http://pages.cs.wisc.edu/~jerryzhu/pub/mc4ssl_FINAL.pdf paper]|| 李蓝天
 +
|-
 +
| rowspan="1"|2013/10/28  || || || ||
 +
|-
 +
| rowspan="1"|2013/11/04  || 王军 || 基于i-vector的intersession补偿及打分方法(综述) || [[媒体文件:131104-ivecto下intersession补偿及打分方法--01-WJ-.pdf‎|slides]]||
 +
|-
 +
| rowspan="1"|2013/11/11  ||张陈昊 ||PLDA介绍及PLDA在说话人识别中的应用 ||[[媒体文件:PLDA.pdf|slides]] || 唐国瑜
 +
|-
 +
| rowspan="1"|2013/11/18  ||别凡虎 ||i-vector理论介绍（讨论）||[[媒体文件:131118-i-vector_and_GMM-UBM-BFH.pdf|slides]]‎  ||王军
 +
|-
 +
| rowspan="1"|2013/11/25  ||刘超 || Pruning Neural Networks By Optimal Brain Damage(综述)||[[媒体文件:131125-OBD-LC-01.pdf|slides]] ||范淼
 +
|-
 +
| rowspan="1"|2013/12/02  ||范淼 ||Distant Supervision for Relation Extraction with Matrix Completion （英文报告）||[[媒体文件:131202-DRMC-FM-01.pdf|slides]] || 李蓝天
 +
|-
 +
| rowspan="1"|2013/12/09  || Dong Wang|| Introduction to the HMM-based speech synthesis||[http://hts.sp.nitech.ac.jp/archives/2.2/HTS_Slides.zip slides] ||
 +
|-
 +
| rowspan="1"|2013/12/16  ||张陈昊 ||语音研究中的基元介绍 ||[[媒体文件:131215-Phonology-ZCH.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2013/12/23  || Dong Wang|| Introduction to the HMM-based speech synthesis (2)||[http://hts.sp.nitech.ac.jp/archives/2.2/HTS_Slides.zip slides] ||
 +
|-
 +
| rowspan="1"|2013/12/23  || || || ||
 +
|-
 +
| rowspan="1"|2013/12/30  ||刘荣 || continuous space language model||[[媒体文件:Cslm-cslt.pdf|slides]]  ||刘超
 +
|-
 +
| rowspan="1"|2014/01/06  || || || ||
 +
|-
 +
| rowspan="1"|2014/01/13  || || || ||
 +
|-
 +
| rowspan="1"|2014/01/20  || || || ||
 +
|-
 +
| rowspan="1"|2014/02/24  || || || ||
 +
|-
 +
| rowspan="1"|2014/03/03  || || || ||
 +
|-
 +
| rowspan="1"|2014/03/10  ||范淼|| Distant Supervision for Information Extraction (英文报告)|| || 李蓝天
 +
|-
 +
| rowspan="1"|2014/03/17  ||唐国瑜 || Topic Models Incorporating Statistical Word Senses || [[媒体文件:TMISWS_For_CICLing2014.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2014/03/24  ||孟祥涛 || Noisy training for Deep Neural Networks|| ||
 +
|-
 +
| rowspan="1"|2014/03/31  ||范淼|| Translating Embeddings for Modeling Multi-relational Data （中文报告） || [https://www.hds.utc.fr/everest/lib/exe/fetch.php?id=en%3Atranse&cache=cache&media=en:cr_paper_nips13.pdf paper]||李蓝天
 +
|-
 +
| rowspan="1"|2014/04/07  || || || ||
 +
|-
 +
| rowspan="1"|2014/04/14 || Wang Jun|| I-vector and PLDA in depth ||[[媒体文件:131104-ivector-microsoft-wj.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2014/04/21 || 邱晗||汉语事件句式规范化处理 ||[[媒体文件:140421-汉语事件句式规范化-QH.pdf‎|slides]] ||
 +
|-
 +
| rowspan="1"|2014/04/28  || 唐国瑜|| Some papers in　CICLing2014 ||[[媒体文件:Some_papers_in_CICling2014.pdf|slides]]  ||刘超
 +
|-
 +
| rowspan="1"|2014/05/05  || || || ||
 +
|-
 +
| rowspan="1"|2014/05/12  || 卡尔|| paper introduction || [[媒体文件:Acoustic Factor Analysis.pdf|slides]] || 邱晗
 +
|-
 +
| rowspan="2"|2014/05/19  || 邱晗|| 汉语事件句式CCG推导树重构 ||[[媒体文件:140519-CCG_reConstruction.pdf‎|slides]]‎|| 卡尔
 +
|-
 +
|Liu Chao|| master proposal: sparse and deep neural networks || [[媒体文件:140519-proposal-LC-01.pdf|slides]] ||
 +
|-
 +
| rowspan="1"| || Liu Chao|| 2nd master proposal: sparse and deep neural networks|| ||
 +
|-
 +
| rowspan="1"|2014/06/16  || 别凡虎 || Truncated Wave based VPR and Some Recent Work || [[媒体文件:140614-Truncated_Speech_based_VPR.pdf‎|slides]]‎ || 别凡虎
 +
|-
 +
| rowspan="1"|2014/06/23  || 别凡虎 || Block-wise training for I-vector || [[媒体文件:140623-Block-wise training for I-vector.pdf‎|slides]]‎ || 别凡虎
 +
|-
 +
| rowspan="1"| 2014/07/07||王军 ||Discriminative Scoring for Speaker Recognition Based on I-vectors || [[媒体文件:140707-work_report.pdf|slides]]|| 王军
 +
|-
 +
| rowspan="1"| 2014/09/01|| || || ||
 +
|-
 +
| rowspan="1"|2014/09/09 ||别凡虎 ||Reseach on Truncated Wave based VPR||[[媒体文件:140909-Truncated Speech based VPR.pdf|slides]] || 别凡虎
 +
|-
 +
| rowspan="1"| 2014/09/15|| || || ||
 +
|-
 +
| rowspan="1"|2014/09/22  || Miao Fan|| Large-scale Entity Relation Extraction based on Low-dimensional Representations (中文报告，博士开题)
 +
||[[媒体文件:基于低维表示的大规模实体关系挖掘技术.pdf‎|slides]] || Lan TianLi
 +
|-
 +
| rowspan="1"| 2014/09/29 || || || ||
 +
|-
 +
| rowspan="1"|2014/10/13  || Miao Fan|| The Frontier of Knowledge Embedding （英文报告）|| [[媒体文件:The_Frontier_of_Knowledge_Embedding.pdf‎|slides]]|| Lan TianLi
 +
|-
 +
| rowspan="1"|2014/10/20  || || || ||
 +
|-
 +
| rowspan="1"|2014/10/27  || Li Yi || Phonemes, Features, and Syllables: Converting Onset and Rime Inventories to Consonants and Vowels||[[媒体文件:Lanzhou Phonemes, Features, and Syllables- fianl.pdf|paper]] [[媒体文件:Syllables and phonemes - 20141027.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2014/11/3  || 米吉提|| Automatic Speech Recognition of Agglutinative Language based on Lexicon Optimization||[[媒体文件:Mijit-slides-清华大学-2014-11-3.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2014/11/10  || || || ||
 +
|-
 +
| rowspan="1"|2014/11/17  ||Dong Wang || Highly restricted keyword spotting for Uyghur using sparse analysis|| [[媒体文件:Highly Restricted Keyword Selection Based on Sparse Analysis.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2014/11/24  || || || ||
 +
|-
 +
| rowspan="1"|2014/12/1  ||ZhongDa Xie ||Incorporating Fine-Grained Ontological Relations in Medical Document Ranking || [[媒体文件:Fine-grained_relations.pdf|slides]]|| Lantian Li
 +
|-
 +
| rowspan="1"|2014/12/8  || || || ||
 +
|-
 +
| rowspan="1"|2014/12/15  || 唐国瑜 || 跨语言话题分析关键技术研究 ||[[媒体文件:141205-答辩-TGY.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2014/12/22  || || || ||
 +
|-
 +
| rowspan="1"|2014/12/29  || Askar || Language Mismatch in Speaker Recognition System||[[媒体文件:141229--askar.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/1/5  ||Lantian Li || Deep Neural Networks for Speaker Recognition || [[媒体文件:150104_Deep_Neural_Networks_for_Speaker_Recognition_LLT.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2015/1/12  || || || ||
 +
|-
 +
| rowspan="1"|2015/1/19  || Dong Wang || Machine Learning Paradigms for Speech Recognition||[[媒体文件:Machine Learning Paradigms for Speech Recognition.pdf|slides]]  [http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6423821 paper] ||
 +
|-
 +
| rowspan="1"|2015/1/26  || Chen Guorong || Information Transmission and Distribution on Web ||[[媒体文件:An_introduction_of_complex_network1.pdf|slides]] ||
 +
|-
 +
| rowspan="1" |2015/3/9 || Dong Wang || Joint Deep Learning || [[媒体文件:Joint Deep Learning.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/3/16  || Dongxu Zhang || Knowledge learning from text data and knowledge bases || [[媒体文件:Joint Deep Learning.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/4/13  || Xuewei Zhang || Lasso-based Reverberation Suppression In Automatic Speech Recognition || [[媒体文件:Lasso-based Reverberation Suppression In Automatic Speech Recognition.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/5/11  || Dong Wang ||ASR and SID Research Frontier ||[[媒体文件:ASR and SID Research Frontier.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/11/23  || Zhiyuan Tang|| CTC learning|| [[媒体文件:CTC.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/11/30  || Mengyuan Zhao|| CNN-based music removal|| [[媒体文件:Music Removal by Convolutional Denoising.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2015/12/3  || Zhiyuan Tang|| Networks of Memory|| [[媒体文件:Memory_net.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/12/7  || Yiqiao Pan|| Document Classification with Spherical Word Vectors||[[媒体文件:Document Classification with Spherical Word Vectors.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/12/14  || Dong Wang || Transfer Learning for Speech and Language Processing ||[[媒体文件:Transfer_Learning_for_Speech_and_Language_Processing.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2015/12/21  || Qixin Wang || Attention for poem generation ||[[媒体文件:Ijcai 2016.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2015/12/28  || Lantian Li || Max-margin metric learning for speaker recognition || [[媒体文件:Max-margin-Metric-Learning.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2016/1/4  || Zhiyong Zhang || Parallel training,MPE and natural gradient||[[媒体文件:20160104_张之勇_Large-scale Parallel Training in Speech Recognition.pdf|slides]]|| 
 +
|-
 +
| rowspan="1"|2016/1/18  || Dongxu Zhang || Memoryless Document Vector ||[[媒体文件:Memoryless_document_vector.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2016/3/14  || Zhiyuan Tang|| Oral presentation for "vMF-SNE: Embedding for Spherical Data"|| [[媒体文件:embedding.pdf|slides]] || 
 +
|-
 +
| rowspan="1"|2016/3/28  || Tianyi Luo || Review for Neural QA || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/29/CSLT_Weekly_Report--20160328.pdf slides] || 
 +
|-
 +
| rowspan="1"|2016/4/11  || Rong Liu || Recommendation in Youku || [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Cslt%E5%AE%9E%E9%AA%8C%E5%AE%A4%E4%BA%A4%E6%B5%81.pptx slides] || 
 +
|-
 +
| rowspan="1"|2016/5/09 || Miao Fan || Learning contextual embeddings of knowledge base with entity descriptions.|| [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9c/Techreport_CSLT_2016_M.F..pdf slides]  ||
 +
|-
 +
| rowspan="1"|2016/5/16 || Yang Wang || Research on conversation thread detection. || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bb/%E6%B1%AA%E6%B4%8B-%E6%AF%95%E8%AE%BE-CSLT.pdf slides]  ||
 +
|-
 +
| rowspan="1"|2016/5/20 || Yang Wang &  Maoning Wang || Research on portfolio selection. || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/89/%E6%B1%AA%E6%B4%8B-%E9%87%91%E8%9E%8D%E7%AC%AC%E4%B8%80%E6%AC%A1%E5%88%86%E4%BA%AB.pdf slides1]  [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bb/%E6%B1%87%E6%8A%A5_%E8%B5%84%E4%BA%A7%E7%BB%84%E5%90%88%E4%B8%AD%E5%87%A0%E4%B8%AA%E8%AF%84%E4%BB%B7%E6%8C%87%E6%A0%87%E7%9A%84%E8%A7%A3%E9%87%8A.pdf slides2]||
 +
|-
 +
| rowspan="1"|2016/5/20  || Zhiyuan Tang || ICASSP 2016 summary || [[媒体文件:Note icassp16.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2016/5/23 || Dong Wang || graphical model and neural model || [[媒体文件:Graphic Model and Neural Model.pdf|slides]] [[媒体文件:Generative-Pdf.rar|papers]]  ||
 +
|-
 +
| rowspan="1"|2016/8/02 || Zhiyuan Tang || Visualizing, Measuring and Understanding Neural Networks: A Brief Survey|| [[媒体文件:Nn analysis.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2016/8/03 || Yang Wang || Neural networks and genetic programming for financial forecasting || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/79/GeneticNN.pdf slides] ||
 +
|-
 +
| rowspan="1"|2016/11/05 || Yang Wang || Reinforcement Learning Models and Simulations || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/RRL_and_sim.pdf slides] ||
 +
|-
 +
| rowspan="1"|2016/11/08 || April Pu || SOFTWARE DEVELIPMENT METHODOLOGIES || [http://wangd.cslt.org/talks/pdf/april_software.pptx slides] ||
 +
|-
 +
| rowspan="1"|2016/11/12 || Yang Wang || Generative Adversarial Nets || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Generative_adversarial_network.pdf slides] ||
 +
|-
 +
| rowspan="1"|2016/11/22 || Zhiyuan Tang || INTERSPEECH 2016 summary || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/65/Interspeech16_review.pdf slides] ||
 +
|-
 +
| rowspan="1"|2016/11/30 || Dong Wang || Deep and sparse learning in speech and language: an overview || [http://wangd.cslt.org/talks/pdf/bics2016.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/2/17 || Yang Wang || Review understanding deep learning requires rethinking generalization || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/3b/Review_understanding_deep_learning_requires_rethinking_generalization.pdf slides] ||
 +
|-
 +
| rowspan="1"|2017/6/5 || Dong Wang || Deep speech factorization || [http://wangd.cslt.org/talks/pdf/Deep-Speech-Factorization.pdf slides] ||
 +
|-
 +
| rowspan="1"|2017/6/8 || Shiyue Zhang || Convolutional Sequence to Sequence Learning  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f3/Conv_seq2seq.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/6/12 || Shiyue Zhang || Memory-augmented Neural Machine Translation || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/36/Memory-augmented_Neural_Machine_Translation_.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/6/21 || Shiyue Zhang || Attention Is All You Need  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/68/Attention_is_all_you_need.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/6/26 || Jiyuan Zhang || Chinese poem generation using neural model  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Flexible_and_Creative_Chinese_Poetry_Generation_Using_Neural_Memory_.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/6/21 || Miao Zhang || Speaker recognition on cough,laugh and wei  ||
 +
[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f6/Zm_cough.pdf slides] 
 +
||
 +
|-
 +
| rowspan="1"|2017/7/10 || Aodong Li || Enhanced Neural Machine Translation by Learning from Draft  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/Learning_from_draft.pptx slides] ||
 +
|-
 +
| rowspan="1"|2017/7/17 || Lantian Li || Study on Speaker Recognition  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ec/170716-Study_on_SRE.pdf slides] ||
 +
|-
 +
| rowspan="1"|2018/12/6 || Xiuqi Jiang ||  Meta-Learning and Zero-Shot Learning  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/18/181205_Meta-Learning_and_Zero-Shot_Learning_JXQ.pdf slides] ||
 +
|-
 +
| rowspan="1"|2018/12/12 || Dan He ||  Tensor factorization neural net  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/3d/Tensor_factorization_neural_net.pdf slides] ||
 +
|-
 +
| rowspan="1"|2018/12/26 || Dong Wang || Towards deep statistical speaker representation  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/48/V.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/01/04 || Dong Wang || Speech in NIPS 2017/2018  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c8/Speech_in_NIPS_2017.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/07/17 || Dong Wang || Deep Feature Learning and Normalization for Speaker Recognition  || [http://wangd.cslt.org/talks/pdf/india.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/08/19 || Sitong Cheng & Pengyuan Zhang || Periodic Report of Celebrity Video Data Collection.  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/08/C-STAR.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/08/19 || Dong Wang|| Continuous Learning for Neural Nets || [[媒体文件:Continuous Learning for Neural Nets.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2019/09/11 || Dong Wang || Language Recognition in ICASSP 2019  || [http://wangd.cslt.org/talks/pdf/LRE-ICASSP-2019.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/09/11 || Sitong Cheng || Language Recognition in Interspeech 2019  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a9/Language_Recognition_in_Interspeech_2019.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/10/14 || Haoran Sun || Dimension Reduction  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/7b/DimensionReduction.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/10/27 || Dong Wang || Back to Matrix  || [[媒体文件:Back to Matrix.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/11/11 || Dong Wang || Helmholtz Machine & The ML criterion  || [[媒体文件:Helmholtz Machine & The ML criterion.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/12/02 || Jiawen Kang || Gan Laten Space Manipulation & Flow Application Papers  || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/ca/GAN_Lantent_Space_manunipulation_%26_Flow_Application.pdf slides] ||
 +
|-
 +
| rowspan="1"|2019/12/09 || Dong Wang || Style transfer and information factorization || [[媒体文件:Style Transfer with Generative Models.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/12/16 || Zhiyuan Tang ||  Conditional Generative Flow  ||  [[媒体文件:Conditional GLow.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/12/23 || Lantian Li ||  Deep Generative Model in Speaker Recognition || [[媒体文件:Deep Generative Model in Speaker Recognition.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/12/30 || Wenqiang Du ||  Cross-bandwidth Train || [[媒体文件:Cross-bandwidth_Train.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/01/06 || Yunqi Cai ||  Do Deep Generative Models Know What They Don't Know ?|| [[媒体文件:2020.1.6_group_meeting.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2019/01/10 || Haoran Sun ||  Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design || [[媒体文件:Flow++.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/01/13 || Ying Shi ||  Deep Generative Model Energy Based Model || [[媒体文件:Deep_Generative_Model.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/02/10 || Dong Wang ||  Deep Generative Models for Discriminative Tasks || [[媒体文件:Re-Thinking for Discriminative and Generative Models.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2020/02/17 || Zhiyuan Tang ||  Unsupervised Learning of Disentangled Representations  || [[媒体文件:20200217 Unsupervised disentanglement.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/02/24 || Lantian Li ||  Weakly- & Self-Supervised Learning || [[媒体文件:Weakly-_%26_Self-Supervised_Learning.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/03/02 || Yunqi Cai ||  Deep Normalization for Speaker Vectors|| [[媒体文件:Deep_Normalization_for_Speaker_Vectors_.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2020/03/09 || Ying Shi ||  Speech Enhancement base on Double Flow || [[媒体文件:Speech_Enhancement_base_on_Double_Flow.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2020/03/16 || Dong Wang ||  Bayesian scoring and uncertainty manipulation || [[媒体文件:Uncertainty Propagation.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2020/03/23 || Zhiyuan Tang || Classifier involves Energy Based Model  || [[媒体文件:200323 energy model.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/03/30 || Lantian Li ||  Bayesian scoring in speaker verification || [[媒体文件:Bayesian_scoring_in_speaker_verification.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2020/04/06 || Yunqi Cai ||  Posterior Collapse|| [[媒体文件:Posterior_Collapse.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2020/04/13 || Lantian Li || NDA in ASV || [[媒体文件:NDA_in_ASV.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2020/04/20 || Ying Shi ||  Speech_Enhancement_base_on_Flow ||[[媒体文件:Speech_Enhancement_base_on_Flow.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/05/11 || Dong Wang  ||  Real DNF || [[媒体文件:Real_DNF.pdf|Slide]]  ||
 +
|-
 +
| rowspan="1"|2020/05/26 || Sitong Cheng ||  ASR-Free Pronunciation Assessment || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9a/ASR-Free_Pronunciation_Assessment.pdf slides] ||
 +
|-
 +
| rowspan="1"|2020/05/26 || Jiawen Kang ||  RobustMAML || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/8e/RobustMAML.pdf slides] ||
 +
|-
 +
| rowspan="1"|2020/05/26 || Jiawen Kang ||  Domain adaptation review || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/6d/Presentation-Meta-learning.pdf slides] ||
 +
|-
 +
| rowspan="1"|2020/05/26 || Jiawen Kang ||  SOTA models for VPR || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d2/SOTA_models_for_VPR.pdf slides] ||
 +
|-
 +
| rowspan="1"|2020/06/01 || Dong Wang || How MAML succeeded?  || [https://arxiv.org/pdf/1909.09157.pdf][https://pdfs.semanticscholar.org/e6e9/c9d50b11ced939faf42f1c65bf9360eefd73.pdf][https://arxiv.org/pdf/1706.05806.pdf] ||
 +
|-
 +
| rowspan="1"|2020/06/09 || Zhiyuan Tang  ||  Flow Wheels || [[媒体文件:20200408 flow wheels.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/06/15 || Lantian Li  ||  Uncertainty Modeling and Inference || [[媒体文件:200615-Uncertainty.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/06/22 || Lantian Li  ||  Gaussians in High Dimension || [[媒体文件:High-dimensioaln-Gaussian.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/06/22 || Dong Wang  ||  Self training for SE and ASR || [[媒体文件:Self-Training.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/06/29 || Ying Shi  ||  Speech enhancement & separation || [[媒体文件:Speech-Separation-and-Enhancement.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/07/06 || Haolin Chen  ||  Self-supervised Learning in Speech Processing || [[媒体文件:Self-Supervised.pptx|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/07/13 || Zhiyuan Tang  || Exploding inverse in INN || [[媒体文件:20200713 dig into flow.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/07/20 || Lantian Li  || Principle Solution for Enroll-Test Mismatch || [[媒体文件:200720-mismatch.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/08/17 || Dong Wang  || Decoupled scoring || [[媒体文件:Decoupled.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2020/08/24 || Zhiyuan Tang || G & D Acoustic model ||  [[媒体文件:20200824 flow asr.pdf | slides]]  ||
 +
|-
 +
| rowspan="1"|2020/09/01 || Lantian Li || Decoupled NL || [[媒体文件:200831-DE-NL.pdf | slides]]  ||
 +
|-
 +
| rowspan="1"|2020/09/07 || Yunqi Cai ||Deep generative model based Anomaly detection||[[媒体文件:Anomaly_detection.pdf | slides]]||
 +
|-
 +
| rowspan="1"|2020/09/14 || Dong Wang || How we factorize speech? || [[媒体文件:Factorization.pdf|slides]]      ||
 +
|-
 +
| rowspan="1"|2020/10/05 || Dong Wang || Remarks on DNF || [[媒体文件:Remakrs on DNF.pptx|slides]]      ||
 +
|-
 +
| rowspan="1"|2020/10/12 || Dong Wang || Paper Reading: Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations || [[媒体文件:Challenge-disentanglement.pptx|slides]]  [http://proceedings.mlr.press/v97/locatello19a/locatello19a.pdf paper link]      ||
 +
|-
 +
| rowspan="1"|2020/10/19 || Haoran Sun || Informational Speech Factorization by Factorial Discriminative Normalization Flow || [[媒体文件:Informational_Speech_Factorization.pdf|slides]]      ||
 +
|-
 +
| rowspan="1"|2020/10/27 || Jiao Han || Experimental report mainly based on DNF models || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e9/Experimental_report_mainly_based_on_DNF_models.pdf slides]    ||
 +
|-
 +
| rowspan="1"|2020/11/02 || Lantian Li || INTERSPEECH 2020 (SRE) || [[媒体文件:201102-INTERSPEECH_2020-SRE-LLT.pdf|slides]]      ||
 +
|-
 +
| rowspan="1"|2020/11/09 || Yunqi Cai || Deep normalization_V1 || [[媒体文件:Deep_norm_trilogy_v1.pdf|slides]] [http://caiyq.cslt.org/doc/deepnorm_v1.mp4 video]    ||
 +
|-
 +
| rowspan="1"|2020/11/16 || Yunqi Cai || Deep normalization_V2 || [http://caiyq.cslt.org/doc/deep-norm-trilogy_v2.pptx slides] [http://caiyq.cslt.org/doc/deepnorm_v2.mp4 video]    ||
 +
|-
 +
| rowspan="1"|2020/11/17 || Di Wang || Statistics decomposition for NL Scoring || [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/97/Statistics_decomposition_for_NL_Scoring.pdf slides]    ||
 +
|-
 +
| rowspan="1"|2020/11/23 || Yunqi Cai || Deep normalization_V3 || [http://caiyq.cslt.org/doc/deep-norm-trilogy_v3.pptx slides] [http://caiyq.cslt.org/doc/deepnorm_v3.mp4 video]    ||
 +
|-
 +
| rowspan="1"|2020/12/08 || Yunqi Cai || From materials science to perceptual intelligence || [http://caiyq.cslt.org/doc/perceptual_intelligence.pptx slides] [http://caiyq.cslt.org/doc/**.mp4 video]    ||
 +
|-
 +
| rowspan="1"|2020/12/08 || Dong Wang || From noise injection to Bayes PLDA || [[媒体文件:Bayes-plda.ppt|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/12/21 || Lantian Li || Speech in NIPS 2019/2020 || [[媒体文件:Speech in NIPS 19&20.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2020/12/28 || Pengqi Li || Domain generalization via robust optimization || [[媒体文件:201228-Device_Generalization.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/01/07 || Dong Wang || What we believe || [[媒体文件:What we believe.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/01/14 || Dong Wang || Reparametric trick || [[媒体文件:Reparametric.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/02/01 || Dong Wang || Data augmentation as regularization || [[媒体文件:Data-augmentation.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/02/22 || Lantian Li || Ensemble and Distillation || [[媒体文件:2012.09816.pdf|paper]] [[媒体文件:Ensemble_And_Distillation.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/03/08 || Dong Wang || HIERARCHICAL GENERATIVE MODELING FOR CONTROLLABLE SPEECH SYNTHESIS || [https://arxiv.org/pdf/1810.07217.pdf paper] [[媒体文件:HIERARCHICALGENERATIVEMODELING FORCONTROLLABLESPEECHSYNTHESIS.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/03/15 || Dong Wang || 第三代人工智能 || [http://scis.scichina.com/cn/2020/SSI-2020-0204.pdf  paper] [[媒体文件:第三代人工智能.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/03/22 || Chao Xing || Complexity neural net in speech enhancement || [http://web.cse.ohio-state.edu/~wang.77/papers/WWW.taslp20.pdf paper1][https://openreview.net/pdf?id=SkeRTsAcYm paper2] [https://arxiv.org/pdf/2008.00264.pdf paper3] ||
 +
|-
 +
| rowspan="1"|2021/03/29 || Ying Shi || Some methods about speech enhancement || [[媒体文件:SPEECH ENHANCMENGT.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/04/05 || Jiyuan Zhang || 推理 & 知识推理调研 || [[媒体文件:知识推理相关调研.pdf|slides]]  ||
 +
|-
 +
| rowspan="1"|2021/04/12 || Zicheng Qiu || Some work on minorlingual speech recognition||  ||
 +
|-
 +
| rowspan="1"|2021/04/19 || Shiyue Zhang || Text summarization||  ||
 +
|-
 +
| rowspan="1"|2021/04/26 || Dong Wang || Paper reading: Metadata normalization || [[媒体文件:Meta normalization.pdf|slides]] [https://arxiv.org/pdf/2104.09052.pdf paper]  ||
 +
|-
 +
| rowspan="1"|2021/05/10 || Lantian Li || Explainable ML || [[媒体文件:Explainable_ML.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/05/17 || Jie Li || Tea cake Re-identification || [[媒体文件:Tea-cake.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2021/05/24 || Dong Wang || Deep speech prior|| [[媒体文件:Deep speech prior.pptx|slides]]||
 +
|-
 +
| rowspan="1"|2021/06/28 || Haoran Sun || Information Bottleneck and Deep Learning || [[媒体文件:Information_bottleneck.pdf|slides]] [[媒体文件:IBpapers.pdf|papers]] ||
 +
|-
 +
| rowspan="1"|2021/07/05 || Chen Chen || Speech Enhancement Overview || [[媒体文件:SpeechEnhancementOverview.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/07/19 || JiaWen Kang || Diseaseof detection from speech signal ||  ||
 +
|-
 +
| rowspan="1"|2021/07/26 || 毛丽旦 || Characters of Uygher in learning Chinese || [[媒体文件:L2-03.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/08/02 || ChaoXing ||  Multi-Modal Speech Interaction||  ||
 +
|-
 +
| rowspan="1"|2021/08/16 || Dong Wang || Training Mutual Information|| [[媒体文件:Information max.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/09/06 || Jie Li || Detection of object falling  || ||
 +
|-
 +
| rowspan="1"|2021/09/13 || Zhiyuan Tang|| Construction of Ke speech database || ||
 +
|-
 +
| rowspan="1"|2021/09/20 || Shiyue Zhang || Objective evaluation for text summarization || [[媒体文件:Summarization_shiyue.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/10/11 || Chao Xing  || Speech MLP || ||
 +
|-
 +
| rowspan="1"|2021/10/18 || Haoran Sun || CycleFlow: PURIFY INFORMATION FACTORS BY CYCLE LOSS ||[[媒体文件:211018.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2021/10/25 || Lantian Li || Real Additive Margin Softmax for Speaker Verification || [[媒体文件:RAM-Softmax.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/11/01 || Chao Xing || Knowedge-driven small foootprint backbone ||  ||
 +
|-
 +
| rowspan="1"|2021/11/08 || Xingliang Cheng || Anti-spoofing in Replay Attack || [[媒体文件:211108-重放检测问题的深入分析.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2021/11/22 || Yunqi Cai || Autonomous Experimentation Systems For Materials Development || [[媒体文件:Autonomous_experiments_systems.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2021/11/29 || Ying Shi || End-to-End kws || [[媒体文件:Kws.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2021/12/06 || Dong Wang || Things that Neural Nets Learn ||[[媒体文件:Network Stitching.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2021/12/13 || Xuewei Zhang || Research advances on Ali Speech Technology || [[媒体文件:Ali_Speech.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2021/12/20 || Yang Wang || Quantitative Finance || ||
 +
|-
 +
| rowspan="1"|2021/12/27 || 吾买尔江 || 基于子带互相关的非同步信号检测方法 || [[媒体文件:基于子带互相关的非同步信号检测方法.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/1/10 || Zhiyong Zhang || Advances on KWS/CMD || [[媒体文件:Keyword-spotting-202201.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2022/1/17 || Jiyuan Zhang || Advances on fake news || [[媒体文件:虚假新闻相关调研 张记袁 20220117.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2022/1/24 || Shi Yin || Additive neural net|| ||
 +
|-
 +
| rowspan="1"|2022/2/19 || Tianyi Luo || Fairness on semi-supervised learning  || ||
 +
|-
 +
| rowspan="1"|2022/3/07 || Chao Xing || 神经网络的异构推理 || [[媒体文件:神经网络的异构推理.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/3/14 || Lantian Li || C-P Map: A Novel Evaluation Toolkit for Speaker Verification || [[媒体文件:CP-MAP.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/3/20 || Dong Wang || Factorization, Disentanglement, Self-supervised Learning and Data Augmentation || [[媒体文件:220320-Factorization_and_Disentanglement.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/4/11 || Weida Liang || Enhanced Exemplar Autoencoder for Any-to-One VC || [[媒体文件:Enhanced_exemplar_autoencoder.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/4/18 || Yong Qin || Audio Pattern Recognition || [[媒体文件:Acoustic_Scene_Classfication.pdf | slides]] ||
 +
|-
 +
| rowspan="1"|2022/4/25 || Dong Wang || Interpreting speech models || [[媒体文件:Interpreting Speech Models.pdf | slides]] || Additional materials[https://arxiv.org/abs/2102.12627][https://www.youtube.com/watch?v=cllFzkvrYmE&t=7s&ab_channel=YannicKilcher][https://baike.baidu.com/item/%E6%B4%9E%E7%A9%B4%E4%B9%8B%E5%96%BB/2822528][https://www.youtube.com/watch?v=6ufPpZDmPKA&ab_channel=Numenta]
 +
|-
 +
| rowspan="1"|2022/5/16 || Lantian Li || Open-source, Robust, Explainable Speaker Recognition || [[媒体文件:220525-博士后研究工作报告-LLT.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2022/5/23 || Ying Shi ||  ICASSP 2022: kws asr || [[媒体文件:ICASSP2022KWS_ASR.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2022/7/4 || Dong Wang ||  Group learning || [[媒体文件:Group learning.pptx|slides]]||
 +
|-
 +
| rowspan="1"|2022/7/11 || Hui Wang ||  TTS evaluation || [[媒体文件:TTS_Evaluation.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2022/7/18 || Renmiao Chen ||  Audio-visual biometric identification || ||
 +
|-
 +
| rowspan="1"|2022/7/25 || Yong Qin ||  Emotion & Age detection || ||
 +
|-
 +
| rowspan="1"|2022/8/1 || Pengqi Li ||  Post-hoc Explanation Methods|| [[媒体文件:Post-hoc-Explanation-Methods.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2022/9/26 || Dong Wang ||  Low Resource ASR|| [[媒体文件:Low Resource ASR.pptx|slides]]||
 +
|-
 +
| rowspan="1"|2022/10/10 || Dong Wang ||  Speech on AAAI|| [[媒体文件:Speech on AAAI 2022.pptx|slides]]||
 +
|-
 +
| rowspan="1"|2022/11/28 || Yong Qin ||  Dysarthria Speech  Processing  || ||
 +
|-
 +
| rowspan="1"|2022/12/19 || Shiwan Zhao ||  GPT introduction  || [https://www.zhihu.com/question/570189639/answer/2790968877]||
 +
|-
 +
| rowspan="1"|2023/1/2 || Guanyu Li/Senyan Li || Tibetan speech recognitoin and Kaldi 2  || ||
 +
|-
 +
| rowspan="1"|2023/1/9 || Dong Wang || Diffusion model  || [[媒体文件:Diffusion Model.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2023/2/6 || Zhiyuan Tang || Desentanglement & sparsity  ||  [[媒体文件:20230206 disentanglement-sparsity.pdf|slides]] ||
 +
|-
 +
| rowspan="1"|2023/2/13 || Renmiao Chen || Prompt based XT"A"  ||  [[媒体文件:230213-Prompt-based XT”A”-CRM.pptx|slides]] ||
 +
|-
 +
| rowspan="1"|2023/3/20 || Xipin Wei || Multi-instrument music generation  ||  ||
 +
|-
 +
| rowspan="1"|2023/3/27 || Yifan Wang, Jie Li || Tensor decomposition  || [[媒体文件:Tensor-decomposition.pptx|slides]]  ||
 +
|-
 +
| rowspan="1"|2023/4/3 || Jiaying Wang  ||  Ordered Binary Speaker Embedding  ||  [[媒体文件:230403 ordered binary speaker embedding.pdf|slides]]||
 +
|-
 +
| rowspan="1"|2023/4/10 || Pengqi Li ||  Visualizing data augmentation in deep speaker recognition  ||[[媒体文件:Visualizing data augmentation in deep speaker recognition-LPQ-0410-.pptx|slides]]  ||
 +
|-
 +
| rowspan="1"|2023/4/24 || Zicheng Qiu ||    ||  ||  
 
|-
 
|-
−
|王俊俊|| || ||
 
 
|}
 
|}
 +
 +
 +
 +
[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Weekly_reading See more related]

2023年4月20日 (四) 05:16的最后版本

  • Location: FIT-1-304


Date Speaker Title Materials On duty
2012/08/27 Dong Wang Heterogeneous Convolutive Non-negative Sparse Coding slides paper
2012/09/03 NO Meeting
2012/09/10 NO Meeting
2012/09/17 WALEED ABDULLA Auditory Based Feature Vectors for Speech Recognition slides 范淼
2012/09/24 刘超 N-gram FST indexing for Spoken Term Detection slides 尹聪
范淼 Micro-blogging, Wikipedia, Folksonomy, What's Next? slides
2012/10/08 NO Meeting
2012/10/15 NO Meeting
2012/10/22 Wu Xiaojun speaker recognition in CSLT slides 卡尔
2012/10/29 王军 An overview of Automatic Speaker Diarization Systems slides 别凡虎
2012/11/05 别凡虎 Experiments on Emotional Speaker Recognition slides 刘超
2012/11/12 唐国瑜 Statistical Word Sense Improves Document Clustering slides 邱晗
2012/11/19 张陈昊 TDSR with Long-term Features Based on Functional Data Analysis slides 王俊俊
2012/11/26 王琳琳 Time-Varying Speaker Recognition: An Introduction slides 龚宬
2012/12/03 No meeting
2012/12/10 No meeting
2012/12/17 No meeting
2012/01/07
2012/01/07 王军 基于DF-MAP的说话人模型训练方法 slides 唐国瑜
2012/01/14 王东 Computing in CSLT slides 王琳琳
2013/03/04 王军 Sequential Adaptive Learning for Speaker Verification slides 别凡虎
2013/03/11 Du Jinle VAD stuff
2013/03/18
2013/03/25
2013/04/01
2013/04/08 张陈昊 A Fishervoice based Feature Fusion Method for SUSR slides 谢仲达
2013/04/15 龚宬 An Exploration on Influence Factors of VAD's Performance in Speaker Recognition slides
2013/04/22 王俊俊 Understanding the Query: THCIB and THUIS at NTCIR-10 Intent Task slides‎
2013/04/29
2013/05/06 别凡虎 MLLR on Emotional Speaker Recognition slides
2013/05/13 刘超 The Use of Deep Neural Network for Speech Recognition slides
2013/05/20
2013/05/27 王琳琳 说话人识别中的时变鲁棒性问题研究 slides
2013/06/03 王俊俊 汉语搜索结果聚类系统研究与实现 slides
2013/06/10
2013/06/17 范淼 Relation Extraction slides
2013/06/24 唐国瑜 Incorporating Statistical Word Senses in Topic Model slides
2013/07/01
2013/07/08
2013/07/15
2013/09/09 王东 Research Frontier in Speech Technology slides
2013/09/16
2013/09/23
2013/09/30
2013/10/07
2013/10/14
2013/10/21 范淼 Transduction Classification with Matrix Completion （中文报告） slides paper 李蓝天
2013/10/28
2013/11/04 王军 基于i-vector的intersession补偿及打分方法(综述) slides
2013/11/11 张陈昊 PLDA介绍及PLDA在说话人识别中的应用 slides 唐国瑜
2013/11/18 别凡虎 i-vector理论介绍（讨论） slides‎ 王军
2013/11/25 刘超 Pruning Neural Networks By Optimal Brain Damage(综述) slides 范淼
2013/12/02 范淼 Distant Supervision for Relation Extraction with Matrix Completion （英文报告） slides 李蓝天
2013/12/09 Dong Wang Introduction to the HMM-based speech synthesis slides
2013/12/16 张陈昊 语音研究中的基元介绍 slides
2013/12/23 Dong Wang Introduction to the HMM-based speech synthesis (2) slides
2013/12/23
2013/12/30 刘荣 continuous space language model slides 刘超
2014/01/06
2014/01/13
2014/01/20
2014/02/24
2014/03/03
2014/03/10 范淼 Distant Supervision for Information Extraction (英文报告) 李蓝天
2014/03/17 唐国瑜 Topic Models Incorporating Statistical Word Senses slides
2014/03/24 孟祥涛 Noisy training for Deep Neural Networks
2014/03/31 范淼 Translating Embeddings for Modeling Multi-relational Data （中文报告） paper 李蓝天
2014/04/07
2014/04/14 Wang Jun I-vector and PLDA in depth slides
2014/04/21 邱晗 汉语事件句式规范化处理 slides
2014/04/28 唐国瑜 Some papers in　CICLing2014 slides 刘超
2014/05/05
2014/05/12 卡尔 paper introduction slides 邱晗
2014/05/19 邱晗 汉语事件句式CCG推导树重构 slides‎ 卡尔
Liu Chao master proposal: sparse and deep neural networks slides
Liu Chao 2nd master proposal: sparse and deep neural networks
2014/06/16 别凡虎 Truncated Wave based VPR and Some Recent Work slides‎ 别凡虎
2014/06/23 别凡虎 Block-wise training for I-vector slides‎ 别凡虎
2014/07/07 王军 Discriminative Scoring for Speaker Recognition Based on I-vectors slides 王军
2014/09/01
2014/09/09 别凡虎 Reseach on Truncated Wave based VPR slides 别凡虎
2014/09/15
2014/09/22 Miao Fan Large-scale Entity Relation Extraction based on Low-dimensional Representations (中文报告，博士开题) slides Lan TianLi
2014/09/29
2014/10/13 Miao Fan The Frontier of Knowledge Embedding （英文报告） slides Lan TianLi
2014/10/20
2014/10/27 Li Yi Phonemes, Features, and Syllables: Converting Onset and Rime Inventories to Consonants and Vowels paper slides
2014/11/3 米吉提 Automatic Speech Recognition of Agglutinative Language based on Lexicon Optimization slides
2014/11/10
2014/11/17 Dong Wang Highly restricted keyword spotting for Uyghur using sparse analysis slides
2014/11/24
2014/12/1 ZhongDa Xie Incorporating Fine-Grained Ontological Relations in Medical Document Ranking slides Lantian Li
2014/12/8
2014/12/15 唐国瑜 跨语言话题分析关键技术研究 slides
2014/12/22
2014/12/29 Askar Language Mismatch in Speaker Recognition System slides
2015/1/5 Lantian Li Deep Neural Networks for Speaker Recognition slides
2015/1/12
2015/1/19 Dong Wang Machine Learning Paradigms for Speech Recognition slides paper
2015/1/26 Chen Guorong Information Transmission and Distribution on Web slides
2015/3/9 Dong Wang Joint Deep Learning slides
2015/3/16 Dongxu Zhang Knowledge learning from text data and knowledge bases slides
2015/4/13 Xuewei Zhang Lasso-based Reverberation Suppression In Automatic Speech Recognition slides
2015/5/11 Dong Wang ASR and SID Research Frontier slides
2015/11/23 Zhiyuan Tang CTC learning slides
2015/11/30 Mengyuan Zhao CNN-based music removal slides
2015/12/3 Zhiyuan Tang Networks of Memory slides
2015/12/7 Yiqiao Pan Document Classification with Spherical Word Vectors slides
2015/12/14 Dong Wang Transfer Learning for Speech and Language Processing slides
2015/12/21 Qixin Wang Attention for poem generation slides
2015/12/28 Lantian Li Max-margin metric learning for speaker recognition slides
2016/1/4 Zhiyong Zhang Parallel training,MPE and natural gradient slides
2016/1/18 Dongxu Zhang Memoryless Document Vector slides
2016/3/14 Zhiyuan Tang Oral presentation for "vMF-SNE: Embedding for Spherical Data" slides
2016/3/28 Tianyi Luo Review for Neural QA slides
2016/4/11 Rong Liu Recommendation in Youku slides
2016/5/09 Miao Fan Learning contextual embeddings of knowledge base with entity descriptions. slides
2016/5/16 Yang Wang Research on conversation thread detection. slides
2016/5/20 Yang Wang & Maoning Wang Research on portfolio selection. slides1 slides2
2016/5/20 Zhiyuan Tang ICASSP 2016 summary slides
2016/5/23 Dong Wang graphical model and neural model slides papers
2016/8/02 Zhiyuan Tang Visualizing, Measuring and Understanding Neural Networks: A Brief Survey slides
2016/8/03 Yang Wang Neural networks and genetic programming for financial forecasting slides
2016/11/05 Yang Wang Reinforcement Learning Models and Simulations slides
2016/11/08 April Pu SOFTWARE DEVELIPMENT METHODOLOGIES slides
2016/11/12 Yang Wang Generative Adversarial Nets slides
2016/11/22 Zhiyuan Tang INTERSPEECH 2016 summary slides
2016/11/30 Dong Wang Deep and sparse learning in speech and language: an overview slides
2017/2/17 Yang Wang Review understanding deep learning requires rethinking generalization slides
2017/6/5 Dong Wang Deep speech factorization slides
2017/6/8 Shiyue Zhang Convolutional Sequence to Sequence Learning slides
2017/6/12 Shiyue Zhang Memory-augmented Neural Machine Translation slides
2017/6/21 Shiyue Zhang Attention Is All You Need slides
2017/6/26 Jiyuan Zhang Chinese poem generation using neural model slides
2017/6/21 Miao Zhang Speaker recognition on cough,laugh and wei

slides

2017/7/10 Aodong Li Enhanced Neural Machine Translation by Learning from Draft slides
2017/7/17 Lantian Li Study on Speaker Recognition slides
2018/12/6 Xiuqi Jiang Meta-Learning and Zero-Shot Learning slides
2018/12/12 Dan He Tensor factorization neural net slides
2018/12/26 Dong Wang Towards deep statistical speaker representation slides
2019/01/04 Dong Wang Speech in NIPS 2017/2018 slides
2019/07/17 Dong Wang Deep Feature Learning and Normalization for Speaker Recognition slides
2019/08/19 Sitong Cheng & Pengyuan Zhang Periodic Report of Celebrity Video Data Collection. slides
2019/08/19 Dong Wang Continuous Learning for Neural Nets slides
2019/09/11 Dong Wang Language Recognition in ICASSP 2019 slides
2019/09/11 Sitong Cheng Language Recognition in Interspeech 2019 slides
2019/10/14 Haoran Sun Dimension Reduction slides
2019/10/27 Dong Wang Back to Matrix slides
2019/11/11 Dong Wang Helmholtz Machine & The ML criterion slides
2019/12/02 Jiawen Kang Gan Laten Space Manipulation & Flow Application Papers slides
2019/12/09 Dong Wang Style transfer and information factorization slides
2019/12/16 Zhiyuan Tang Conditional Generative Flow slides
2019/12/23 Lantian Li Deep Generative Model in Speaker Recognition slides
2019/12/30 Wenqiang Du Cross-bandwidth Train slides
2019/01/06 Yunqi Cai Do Deep Generative Models Know What They Don't Know ? slides
2019/01/10 Haoran Sun Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design slides
2020/01/13 Ying Shi Deep Generative Model Energy Based Model slides
2020/02/10 Dong Wang Deep Generative Models for Discriminative Tasks slides
2020/02/17 Zhiyuan Tang Unsupervised Learning of Disentangled Representations slides
2020/02/24 Lantian Li Weakly- & Self-Supervised Learning slides
2020/03/02 Yunqi Cai Deep Normalization for Speaker Vectors slides
2020/03/09 Ying Shi Speech Enhancement base on Double Flow slides
2020/03/16 Dong Wang Bayesian scoring and uncertainty manipulation slides
2020/03/23 Zhiyuan Tang Classifier involves Energy Based Model slides
2020/03/30 Lantian Li Bayesian scoring in speaker verification slides
2020/04/06 Yunqi Cai Posterior Collapse slides
2020/04/13 Lantian Li NDA in ASV slides
2020/04/20 Ying Shi Speech_Enhancement_base_on_Flow slides
2020/05/11 Dong Wang Real DNF Slide
2020/05/26 Sitong Cheng ASR-Free Pronunciation Assessment slides
2020/05/26 Jiawen Kang RobustMAML slides
2020/05/26 Jiawen Kang Domain adaptation review slides
2020/05/26 Jiawen Kang SOTA models for VPR slides
2020/06/01 Dong Wang How MAML succeeded? [1][2][3]
2020/06/09 Zhiyuan Tang Flow Wheels slides
2020/06/15 Lantian Li Uncertainty Modeling and Inference slides
2020/06/22 Lantian Li Gaussians in High Dimension slides
2020/06/22 Dong Wang Self training for SE and ASR slides
2020/06/29 Ying Shi Speech enhancement & separation slides
2020/07/06 Haolin Chen Self-supervised Learning in Speech Processing slides
2020/07/13 Zhiyuan Tang Exploding inverse in INN slides
2020/07/20 Lantian Li Principle Solution for Enroll-Test Mismatch slides
2020/08/17 Dong Wang Decoupled scoring slides
2020/08/24 Zhiyuan Tang G & D Acoustic model slides
2020/09/01 Lantian Li Decoupled NL slides
2020/09/07 Yunqi Cai Deep generative model based Anomaly detection slides
2020/09/14 Dong Wang How we factorize speech? slides
2020/10/05 Dong Wang Remarks on DNF slides
2020/10/12 Dong Wang Paper Reading: Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations slides paper link
2020/10/19 Haoran Sun Informational Speech Factorization by Factorial Discriminative Normalization Flow slides
2020/10/27 Jiao Han Experimental report mainly based on DNF models slides
2020/11/02 Lantian Li INTERSPEECH 2020 (SRE) slides
2020/11/09 Yunqi Cai Deep normalization_V1 slides video
2020/11/16 Yunqi Cai Deep normalization_V2 slides video
2020/11/17 Di Wang Statistics decomposition for NL Scoring slides
2020/11/23 Yunqi Cai Deep normalization_V3 slides video
2020/12/08 Yunqi Cai From materials science to perceptual intelligence slides video
2020/12/08 Dong Wang From noise injection to Bayes PLDA slides
2020/12/21 Lantian Li Speech in NIPS 2019/2020 slides
2020/12/28 Pengqi Li Domain generalization via robust optimization slides
2021/01/07 Dong Wang What we believe slides
2021/01/14 Dong Wang Reparametric trick slides
2021/02/01 Dong Wang Data augmentation as regularization slides
2021/02/22 Lantian Li Ensemble and Distillation paper slides
2021/03/08 Dong Wang HIERARCHICAL GENERATIVE MODELING FOR CONTROLLABLE SPEECH SYNTHESIS paper slides
2021/03/15 Dong Wang 第三代人工智能 paper slides
2021/03/22 Chao Xing Complexity neural net in speech enhancement paper1paper2 paper3
2021/03/29 Ying Shi Some methods about speech enhancement slides
2021/04/05 Jiyuan Zhang 推理 & 知识推理调研 slides
2021/04/12 Zicheng Qiu Some work on minorlingual speech recognition
2021/04/19 Shiyue Zhang Text summarization
2021/04/26 Dong Wang Paper reading: Metadata normalization slides paper
2021/05/10 Lantian Li Explainable ML slides
2021/05/17 Jie Li Tea cake Re-identification slides
2021/05/24 Dong Wang Deep speech prior slides
2021/06/28 Haoran Sun Information Bottleneck and Deep Learning slides papers
2021/07/05 Chen Chen Speech Enhancement Overview slides
2021/07/19 JiaWen Kang Diseaseof detection from speech signal
2021/07/26 毛丽旦 Characters of Uygher in learning Chinese slides
2021/08/02 ChaoXing Multi-Modal Speech Interaction
2021/08/16 Dong Wang Training Mutual Information slides
2021/09/06 Jie Li Detection of object falling
2021/09/13 Zhiyuan Tang Construction of Ke speech database
2021/09/20 Shiyue Zhang Objective evaluation for text summarization slides
2021/10/11 Chao Xing Speech MLP
2021/10/18 Haoran Sun CycleFlow: PURIFY INFORMATION FACTORS BY CYCLE LOSS slides
2021/10/25 Lantian Li Real Additive Margin Softmax for Speaker Verification slides
2021/11/01 Chao Xing Knowedge-driven small foootprint backbone
2021/11/08 Xingliang Cheng Anti-spoofing in Replay Attack slides
2021/11/22 Yunqi Cai Autonomous Experimentation Systems For Materials Development slides
2021/11/29 Ying Shi End-to-End kws slides
2021/12/06 Dong Wang Things that Neural Nets Learn slides
2021/12/13 Xuewei Zhang Research advances on Ali Speech Technology slides
2021/12/20 Yang Wang Quantitative Finance
2021/12/27 吾买尔江 基于子带互相关的非同步信号检测方法 slides
2022/1/10 Zhiyong Zhang Advances on KWS/CMD slides
2022/1/17 Jiyuan Zhang Advances on fake news slides
2022/1/24 Shi Yin Additive neural net
2022/2/19 Tianyi Luo Fairness on semi-supervised learning
2022/3/07 Chao Xing 神经网络的异构推理 slides
2022/3/14 Lantian Li C-P Map: A Novel Evaluation Toolkit for Speaker Verification slides
2022/3/20 Dong Wang Factorization, Disentanglement, Self-supervised Learning and Data Augmentation slides
2022/4/11 Weida Liang Enhanced Exemplar Autoencoder for Any-to-One VC slides
2022/4/18 Yong Qin Audio Pattern Recognition slides
2022/4/25 Dong Wang Interpreting speech models slides Additional materials[4][5][6][7]
2022/5/16 Lantian Li Open-source, Robust, Explainable Speaker Recognition slides
2022/5/23 Ying Shi ICASSP 2022: kws asr slides
2022/7/4 Dong Wang Group learning slides
2022/7/11 Hui Wang TTS evaluation slides
2022/7/18 Renmiao Chen Audio-visual biometric identification
2022/7/25 Yong Qin Emotion & Age detection
2022/8/1 Pengqi Li Post-hoc Explanation Methods slides
2022/9/26 Dong Wang Low Resource ASR slides
2022/10/10 Dong Wang Speech on AAAI slides
2022/11/28 Yong Qin Dysarthria Speech Processing
2022/12/19 Shiwan Zhao GPT introduction [8]
2023/1/2 Guanyu Li/Senyan Li Tibetan speech recognitoin and Kaldi 2
2023/1/9 Dong Wang Diffusion model slides
2023/2/6 Zhiyuan Tang Desentanglement & sparsity slides
2023/2/13 Renmiao Chen Prompt based XT"A" slides
2023/3/20 Xipin Wei Multi-instrument music generation
2023/3/27 Yifan Wang, Jie Li Tensor decomposition slides
2023/4/3 Jiaying Wang Ordered Binary Speaker Embedding slides
2023/4/10 Pengqi Li Visualizing data augmentation in deep speaker recognition slides
2023/4/24 Zicheng Qiu


See more related

取自“http://index.cslt.org/mediawiki/index.php?title=Weekly_meeting&oldid=40108”