Delivery-2016

来自cslt Wiki
2017年1月7日 (六) 16:24Cslt（讨论 | 贡献）的版本

跳转至： 导航、 搜索

Technical report

  1. Memoryless Document Vector, Dongxu Zhang, Dong Wang
  2. TRP-20160032 Can Machine Generate Traditional Chinese Poetry? A Turing Test, Qixin Wang, Tianyi Luo, Dong Wang
  3. TRP-20160031 OC16-CE80: A Chinese-English Mixlingual Database and A Speech Recognition Baseline, Dong Wang, Zhiyuan Tang, Difei Tang and Qing Chen
  4. TRP-20160030 Collaborative Joint Training with Multi-task Recurrent Model for Speech and Speaker Recognition, Zhiyuan Tang, Lantian Li, Dong Wang and Ravichander Vipperla
  5. TRP-20160029 Multi-task Recurrent Model for Speech and Speaker Recognition, Zhiyuan Tang, Lantian Li and Dong Wang
  6. TRP-20160028 Multi-task Recurrent Model for True Multilingual Speech Recognition, Zhiyuan Tang, Lantian Li and Dong Wang
  7. TRP-20160027 Collaborative Learning for Language and Speaker Recognition, Lantian Li, Zhiyuan Tang, Dong Wang, Yang Feng and Shiyue Zhang
  8. TRP-20160026 Weakly Supervised PLDA Training, Lantian Li, Dong Wang, Yixiang Chen and Chenghui Zhao
  9. TRP-20160025 Local Training for PLDA in Speaker Verification, Chenghui Zhao, Lantian Li, Dong Wang and April Pu
  10. TRP-20160024 Decision Making Based on Cohort Scores for Speaker Verification, Lantian Li, Renyu Wang, Gang Wang, Caixia Wang and Thomas Fang Zheng
  11. TRP-20160023 AP16-OL7: A Multilingual Database for Oriental Languages and A Language Recognition Baseline, Dong Wang, Lantian Li, Difei Tang and Qing Chen
  12. TRP-20160022 System Combination for Short Utterance Speaker Recognition, Lantian Li, Dong Wang and Thomas Fang Zheng
  13. TRP-20160021 Improving Short Utterance Speaker Recognition by Modeling Speech Unit Classes, Lantian Li, Dong Wang, Chenhao Zhang and Thomas Fang Zheng
  14. TRP-20160020 Feature Transformation For Speaker Verification Under Speaking Rate Mismatch Condition, Askar Rozi, Lantian Li, Dong Wang and Thomas Fang Zheng
  15. TRP-20160019 Language-aware PLDA for Multilingual Speaker Recognition, Askar Rozi, Dong Wang, Lantian Li and Thomas Fang Zheng
  16. TRP-20160018 Chinese Song Iambics Generation with Neural Attention-based Model, Qixin Wang, Tianyi Luo, Dong Wang
  17. TRP-20160017 How to Config Kaldi nnet3 (in Chinese), Zhiyuan Tang and Dong Wang
  18. TRP-20160016 How to deploy joint training in Kaldi (in Chinese), Hang Luo, Zhiyuan Tang and Dong Wang
  19. TRP-20160015 How to run ASR system for Kazak (in Chinese), Ying Shi, Zhiyuan Tang，Nurbolat and Dong Wang
  20. TRP-20160014 Exploring The Role of Deep Speaker Features for Speaker Verification, Lantian Li and Dong Wang
  21. TRP-20160013 Sparse Discriminative Analysis and Its Application in Distraction Classification, Dong Wang
  22. TRP-20160012 i-vector system in Kaldi (in Chinese) Yixang Chen, Lantian Li and Dong Wang
  23. TRP-20160011 基于说话人信道相关的录音重放检测若干方法探究 Lantian Li, Yixiang Chen and Dong Wang
  24. TRP-20160010 Highly Restricted Keyword Selection Based on Sparse Analysis for Uyghur Text Categorization, Dong Wang, Askar Humdulla, Rayilam Parhat, Javier Tejedor
  25. TRP-20160009: RNNG Code User Guide, Shiyue Zhang and Yang Feng
  26. TRP-20160008: Different styles of poetry generation based on memory model, Jiyuan Zhang,Yang Feng and Dong Wang
  27. TRP-20160007: Distraction Detection Using Sparse Discriminative Analysis, Dong Wang and Guozhen Zhao
  28. TRP-20160006: Visualization Analysis for Recurrent Networks, Zhiyuan Tang, Ying Shi and Dong Wang
  29. TRP-20160005: Distributed Representation Learning for Knowledge Graphs with Entity Descriptions; Miao Fan, Qiang Zhou, Thomas Fang Zheng, Ralph Grishman
  30. TRP-20160004: A Review of Neural QA, Tianyi Luo and Dong Wang
  31. TRP-20160003: A study of Similar Word Model for Unfrequent Word Enhancement in Speech Recognition, Xi Ma, Dong Wang and Javier Tejedor
  32. TRP-20160002: Low-Frequency Words Embedding, Chao Xing, Yiqiao Pan, Dong Wang
  33. TRP-20160001: Max-margin metric learning for speaker recognition, Lantian Li, Chao Xing, Dong Wang

Patent

  1. 郑方 李蓝天 邬晓钧 别凡虎 王军 语音重放检测方法和装置 2016100073590 [D-ear] 交底书
  2. 郑方 李蓝天 邬晓钧 王刚 刘乐 基于声纹识别、人脸识别以及同步活体检测的身份认证方法及系统 2015108119085 [D-ear] 交底书
  3. 王东 邢超 张之勇 赵梦原 一种面向混合语言的语音合成方法 [FreeNeb] 交底书
  4. 王东 张之勇 赵梦原 黄伟明 李国强，一种日语语音识别系统训练方法 [同方] 交底书
  5. 汪洋，王东，刘荣 在线强化学习交易策略 [张露] 文底书
  6. 王东，白紫薇，冯洋，杜新凯，游士学，基于LSTM模型的现代文到古诗的转换技术 [汇联] 交底书
  7. 王东，张记袁，冯洋，杜新凯，游士学， 一种基于共同语义空间的个性化音乐生成技术 [汇联] 交底书

Talks

Date Speaker Title Materials On duty
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
2016/11/12 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

Database

name type size dir description
ASVspoof 2017 wav - corpora/lilt/ASVspoof 2017 ASVspoof 2017 data (from INTERSPEECH) collected by Lantian Li
CSLT_China300 wav - corpora/lilt/CSLT_China300 300 chinese speakers data for SRE collected by Lantian Li
CSLT_Replay wav - corpora/lilt/CSLT_Replay CSLT replay spoofing data collected by Lantian Li
CSLT_Digit wav - corpora/lilt/CSLT_Digit Digit string data for SRE collected by Lantian Li
Idiap_avspoof wav - corpora/lilt/Idiap_avspoof Idiap Avspoof data collected by Lantian Li
RedDots wav - corpora/lilt/RedDots RedDots data for SRE collected by Lantian Li
SITW wav - corpora/lilt/SITW SITW data for SRE collected by Lantian Li
VCTK wav - corpora/lilt/VCTK VCTK data for ASR and SRE collected by Lantian Li
VoxForge wav - corpora/lilt/VoxForge VoxForge data for ASR and SRE collected by Lantian Li
lyric text - corpora/art/lyric song lyric data collected by Jiyuan Zhang
poem text - corpora/art/poem Traditional Chinese poem data collected by Qixin Wang and Jiyuan Zhang
cnsong text - corpora/art/song Chinese Song sentences collected by Aiting Liu
factordb transaction - corpora/finance/factordb Factor database collected by Wangyang

Code

Code Name Author Description
viewExp Wang Yang The experiment platform of the Finance team link
vvBeam Wang Dong Beamforming using superdirective array link

Model and System

取自“http://cslt.org/mediawiki/index.php?title=Delivery-2016&oldid=25672”