My SLT 2018 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.

Create a login based on your email (takes less than one minute)
Perform 'Paper Search'
Select papers that you desire to save in your personalized schedule
Click on 'My Schedule' to see the current list of selected papers
Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Clicking on the Add button next to a paper title will add that paper to your custom schedule.
Clicking on the Remove button next to a paper will remove that paper from your custom schedule.

ASR I

Session Type: Poster

Time: Wednesday, December 19, 10:00 - 12:00

Location: Kallirhoe Hall

1: HIGH-DEGREE FEATURE FOR DEEP NEURAL NETWORK BASED ACOUSTIC MODEL

Hoon Chung; Electronics and Telecommunications Research Institute

Sung Joo Lee; Electronics and Telecommunications Research Institute

Jeon Gue Park; Electronics and Telecommunications Research Institute

2: DENSENET BLSTM FOR ACOUSTIC MODELING IN ROBUST ASR

Maximilian Strake; Technische Universität Braunschweig

Pascal Behr; Technische Universität Braunschweig

Timo Lohrenz; Technische Universität Braunschweig

Tim Fingscheidt; Technische Universität Braunschweig

3: PHASE-BASED FEATURE REPRESENTATIONS FOR IMPROVING RECOGNITION OF DYSARTHRIC SPEECH

Siddharth Sehgal; University of Sheffield

Stuart Cunningham; University of Sheffield

Phil Green; University of Sheffield

4: EFFICIENT BUILDING STRATEGY WITH KNOWLEDGE DISTILLATION FOR SMALL-FOOTPRINT ACOUSTIC MODELS

Takafumi Moriya; NTT Corporation

Hiroki Kanagawa; NTT Corporation

Kiyoaki Matsui; NTT Corporation

Takaaki Fukutomi; NTT Corporation

Yusuke Shinohara; NTT Corporation

Yoshikazu Yamaguchi; NTT Corporation

Manabu Okamoto; NTT Corporation

Yushi Aono; NTT Corporation

5: ADVANCING MULTI-ACCENTED LSTM-CTC SPEECH RECOGNITION USING A DOMAIN SPECIFIC STUDENT-TEACHER LEARNING PARADIGM

Shahram Ghorbani; University of Texas at Dallas

Ahmet E. Bulut; University of Texas at Dallas

John H.L. Hansen; University of Texas at Dallas

6: DYNAMIC EXTENSION OF ASR LEXICON USING WIKIPEDIA DATA

Badr Abdullah; LORIA/INRIA

Irina Illina; LORIA/INRIA

Dominique Fohr; LORIA/INRIA

7: IMPROVING LF-MMI USING UNCONSTRAINED SUPERVISIONS FOR ASR

Hossein Hadian; Sharif University of Technology

Daniel Povey; Johns Hopkins University

Hossein Sameti; Sharif University of Technology

Jan Trmal; Johns Hopkins University

Sanjeev Khudanpur; Johns Hopkins University

8: ON TRAINING RECURRENT NETWORKS WITH TRUNCATED BACKPROPAGATION THROUGH TIME IN SPEECH RECOGNITION

Hao Tang; Massachusetts Institute of Technology

James Glass; Massachusetts Institute of Technology

9: LEARNING NOISE-INVARIANT REPRESENTATIONS FOR ROBUST SPEECH RECOGNITION

Davis Liang; Amazon AI

Zhiheng Huang; Amazon AI

Zachary Lipton; Carnegie Mellon University

10: AN EXPLORATION OF DIRECTLY USING WORD AS ACOUSTIC MODELING UNIT FOR SPEECH RECOGNITION

Chunlei Zhang; The University of Texas at Dallas

Chengzhu Yu; Tencent AI Lab

Chao Weng; Tencent AI Lab

Jia Cui; Tencent AI Lab

Dong Yu; Tencent AI Lab

11: IMPROVED TRAINING OF NEURAL TRANS-DIMENSIONAL RANDOM FIELD LANGUAGE MODELS WITH DYNAMIC NOISE-CONTRASTIVE ESTIMATION

Bin Wang; Tsinghua University

Zhijian Ou; Tsinghua University

12: IMPROVING VERY DEEP TIME-DELAY NEURAL NETWORK WITH VERTICAL-ATTENTION FOR EFFECTIVELY TRAINING CTC-BASED ASR SYSTEMS

Sheng Li; National Institute of Information and Communications Technology

Xugang Lu; National Institute of Information and Communications Technology

Ryoichi Takashima; National Institute of Information and Communications Technology

Peng Shen; National Institute of Information and Communications Technology

Tatsuya Kawahara; National Institute of Information and Communications Technology (NICT) / Kyoto University

Hisashi Kawai; National Institute of Information and Communications Technology