Difference between revisions of "Publication-trp"

From cslt Wiki
Jump to: navigation, search
 
(15 intermediate revisions by 5 users not shown)
Line 1: Line 1:
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Connection_Sparseness.pdf TRP-20170002 Experiments of Connection Sparseness (in Chinese), Yanqing Wang ]
+
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f4/Technical_report_-_poetry_generation.pdf TRP-20190001 A Rhythm Model for Chinese Poetry Generation, Yibo Liu, Dong Wang]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b3/ASR_trp.pdf TRP-20180002 A Research of ASR, Jiayao Wu]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e9/TRP-20180001_Review_of_LID%2C_Zhaodi_Qi.pdf TRP-20180001 Review of LID, Zhaodi Qi]
 +
[[文件:hedge.png|300px]]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/26/Dynamic_Hedge_using_RNN.pdf TRP-20170005 Dynamic Hedge Using RNN, Xin Jing ]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5f/Neural_sparseness.pdf TRP-20170004 Neural Sparseness in Speech Recognition Based on Kaldi (in Chinese), Yanqing Wang, Zhiyuan Tang, Dong Wang ]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f0/Long-term_dropconnect.pdf TRP-20170003 Long-term DropConnect in Speech Recognition (in Chinese), Yanqing Wang, Zhiyuan Tang, Dong Wang ]
 +
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/ff/Connection_sparseness.pdf TRP-20170002 Connection Sparseness in Speech Recognition Based on Kaldi (in Chinese), Yanqing Wang, Zhiyuan Tang, Dong Wang ]
 
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e3/TRP-201700011.pdf TRP-20170001 重叠语音与原始语音关系的研究与分析 唐辉]
 
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e3/TRP-201700011.pdf TRP-20170001 重叠语音与原始语音关系的研究与分析 唐辉]
 
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/53/TRP-20160039.pdf TRP-20160039 Speaker Segmentation Using Deep Speaker Vectors for Fast Speaker Change Scenarios, Renyu Wang, Mingliang Gu, Lantian Li, Mingxing Xu, Thomas Fang Zheng]
 
*[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/53/TRP-20160039.pdf TRP-20160039 Speaker Segmentation Using Deep Speaker Vectors for Fast Speaker Change Scenarios, Renyu Wang, Mingliang Gu, Lantian Li, Mingxing Xu, Thomas Fang Zheng]

Latest revision as of 23:34, 8 November 2019

Hedge.png


Future.jpg

Memoryless.png

Turing-test.png

Mix-lingual.png

Multi-lingual.jpg


Dis.png


Dkeyword.png

Rnng user guide.png

Memory attention model.jpg

Distraction.png

Visual fig.png

FIG-TRP2016.png

Aikefu.bmp

Simpair.png

Low-freq.png

Maxmargin.png


Lowv.png

Adamax.png

Ptrnets.png

Dvad.png

Uyghur.jpg

Nnpre.jpg

Mmargin.png

Binary.jpg

Rnnrl.png


Dplda.png


Jsrl.png


Listnet.png


Segvector.png


Vmclass.png


Tlearn.png

Songcisample.png

Database.jpg

Thchs.png


Su.jpg

Dv.png

Dark.png

PBE.png

Fst-fw.png

Cdae.png

Vmfsne.png

Ros.png

Dnnvadstru.png

Uyghur-training.png

Beam-forming.png

Clipping-speaker.png

Semi-dynamic-embedding.png

Speaker-discriminative-score.png

Noisy-traiing.png

English-scroing.png


CSLT-TRP latex template