Login Paper Search My Schedule Paper Index Help

My ICASSP 2020 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)
Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2020 Open Preview.

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.

WE2.I: Robust Speech Recognition

Session Type: Poster
Time: Wednesday, 6 May, 11:30 - 13:30
Location: On-Demand
Session Chairs: Ozlem Kalinli, Apple and Ebru Arisoy-Saraclar, MEF University
 
   WE2.I.1: IMPROVING REVERBERANT SPEECH TRAINING USING DIFFUSE ACOUSTIC SIMULATION
         Zhenyu Tang; University of Maryland
         Lianwu Chen; Tencent AI Lab
         Bo Wu; Tencent AI Lab
         Dong Yu; Tencent AI Lab
         Dinesh Manocha; University of Maryland
 
   WE2.I.2: LOW-FREQUENCY COMPENSATED SYNTHETIC IMPULSE RESPONSES FOR IMPROVED FAR-FIELD SPEECH RECOGNITION
         Zhenyu Tang; University of Maryland
         Hsien-Yu Meng; University of Maryland
         Dinesh Manocha; University of Maryland
 
   WE2.I.3: AIPNET: GENERATIVE ADVERSARIAL PRE-TRAINING OF ACCENT-INVARIANT NETWORKS FOR END-TO-END SPEECH RECOGNITION
         Yi-Chen Chen; National Taiwan University
         Zhaojun Yang; Facebook
         Ching-Feng Yeh; Facebook
         Mahaveer Jain; Facebook
         Michael L. Seltzer; Facebook
 
   WE2.I.4: AUDIO-VISUAL RECOGNITION OF OVERLAPPED SPEECH FOR THE LRS2 DATASET
         Jianwei Yu; Chinese University of Hong Kong
         Shi-Xiong Zhang; Tencent AI Lab
         Jian Wu; Tencent
         Shahram Ghorbani; University of Texas at Dallas
         Bo Wu; Tencent
         Shiyin Kang; Tencent
         Shansong Liu; Chinese University of Hong Kong
         Xunying Liu; Chinese University of Hong Kong
         Helen Meng; Chinese University of Hong Kong
         Dong Yu; Tencent
 
   WE2.I.5: MULTI-TASK SELF-SUPERVISED LEARNING FOR ROBUST SPEECH RECOGNITION
         Mirco Ravanelli; Université de Montréal
         Jianyuan Zhong; University of Rochester
         Santiago Pascual; Universitat Politecnica de Catalunya
         Pawel Swietojanski; University of New South Wales
         Joao Monteiro; Institut National de la Recherche Scientifique/Computer Research Institute of Montréal
         Jan Trmal; Johns Hopkins University
         Yoshua Bengio; Université de Montréal
 
   WE2.I.6: END-TO-END MULTI-PERSON AUDIO/VISUAL AUTOMATIC SPEECH RECOGNITION
         Otavio Braga; Google
         Takaki Makino; Google
         Olivier Siohan; Google
         Hank Liao; Google
 
   WE2.I.7: END-TO-END AUTOMATIC SPEECH RECOGNITION INTEGRATED WITH CTC-BASED VOICE ACTIVITY DETECTION
         Takenori Yoshimura; Nagoya University
         Tomoki Hayashi; Nagoya University
         Kazuya Takeda; Nagoya University
         Shinji Watanabe; Johns Hopkins University
 
   WE2.I.8: END-TO-END TRAINING OF TIME DOMAIN AUDIO SEPARATION AND RECOGNITION
         Thilo von Neumann; Paderborn University
         Keisuke Kinoshita; NTT
         Lukas Drude; Paderborn University
         Christoph Boeddeker; Paderborn University
         Marc Delcroix; NTT
         Tomohiro Nakatani; NTT
         Reinhold Haeb-Umbach; Paderborn University
 
   WE2.I.9: IMPROVING NOISE ROBUST AUTOMATIC SPEECH RECOGNITIONWITH SINGLE-CHANNEL TIME-DOMAIN ENHANCEMENT NETWORK
         Keisuke Kinoshita; NTT
         Tsubasa Ochiai; NTT
         Marc Delcroix; NTT
         Tomohiro Nakatani; NTT
 
   WE2.I.10: A PRACTICAL TWO-STAGE TRAINING STRATEGY FOR MULTI-STREAM END-TO-END SPEECH RECOGNITION
         Ruizhi Li; Johns Hopkins University
         Gregory Sell; Johns Hopkins University
         Xiaofei Wang; Microsoft
         Shinji Watanabe; Johns Hopkins University
         Hynek Hermansky; Johns Hopkins University
 
   WE2.I.11: MULTI-SCALE OCTAVE CONVOLUTIONS FOR ROBUST SPEECH RECOGNITION
         Joanna Rownicka; University of Edinburgh
         Peter Bell; University of Edinburgh
         Steve Renals; University of Edinburgh
 
   WE2.I.12: LEARNING NOISE INVARIANT FEATURES THROUGH TRANSFER LEARNING FOR ROBUST END-TO-END SPEECH RECOGNITION
         Shucong Zhang; University of Edinburgh
         Cong-Thanh Do; Toshiba Research Europe Limited Company
         Rama Doddipatla; Toshiba Research Europe Limited Company
         Steve Renals; University of Edinburgh