NEW.1: New Applications of ASR |
| Session Type: Poster |
| Poster Time: Wednesday, December 20, 11:00 - 12:30 |
| Location: Poster Area |
| Session Chair: Marc Delcroix, NTT Corporation |
| NEW.1.10: SEEING AND HEARING TOO: AUDIO REPRESENTATION FOR VIDEO CAPTIONING |
| Shun Po Chuang; National Taiwan University, Taiwan |
| Chia-Hung Wan; National Taiwan University, Taiwan |
| Pang-Chi Huang; National Taiwan University, Taiwan |
| Chi-Yu Yang; National Taiwan University, Taiwan |
| Hung-Yi Lee; National Taiwan University, Taiwan |
| NEW.1.11: MULTITASK TRAINING WITH UNLABELED DATA FOR END-TO-END SIGN LANGUAGE FINGERSPELLING RECOGNITION |
| Bowen Shi; Toyota Technological Institute at Chicago, United States |
| Karen Livescu; Toyota Technological Institute at Chicago, United States |
| NEW.1.12: A HIERARCHICAL ATTENTION BASED MODEL FOR OFF-TOPIC SPONTANEOUS SPOKEN RESPONSE DETECTION |
| Andrey Malinin; University of Cambridge, United Kingdom |
| Kate Knill; University of Cambridge, United Kingdom |
| Mark J. F. Gales; University of Cambridge, United Kingdom |
| NEW.1.13: A CONTEXT-AWARE SPEECH RECOGNITION AND UNDERSTANDING SYSTEM FOR AIR TRAFFIC CONTROL DOMAIN |
| Youssef Oualil; Saarland University, Germany |
| Dietrich Klakow; Saarland University, Germany |
| György Szaszák; Saarland University, Germany |
| Ajay Srinivasamurthy; Idiap Research Institute, Switzerland |
| Hartmut Helmke; German Aerospace Center, Germany |
| Petr Motlicek; Idiap Research Institute, Switzerland |
| NEW.1.14: SPOKEN LANGUAGE BIOMARKERS FOR DETECTING COGNITIVE IMPAIRMENT |
| Tuka Alhanai; Massachusetts Institute of Technology, United States |
| Rhoda Au; Boston University School of Medicine and Public Health, United States |
| James Glass; Massachusetts Institute of Technology, United States |
| NEW.1.15: DBLSTM BASED MULTILINGUAL ARTICULATORY FEATURE EXTRACTION FOR LANGUAGE DOCUMENTATION |
| Markus Müller; Karlsruhe Institute of Technology, Germany |
| Sebastian Stüker; Karlsruhe Institute of Technology, Germany |
| Alex Waibel; Karlsruhe Institute of Technology, Germany |
| NEW.1.16: LEARNING MODALITY-INVARIANT REPRESENTATIONS FOR SPEECH AND IMAGES |
| Kenneth Leidal; Massachusetts Institute of Technology, United States |
| David Harwath; Massachusetts Institute of Technology, United States |
| James Glass; Massachusetts Institute of Technology, United States |
| NEW.1.17: EARLY AND LATE INTEGRATION OF AUDIO FEATURES FOR AUTOMATIC VIDEO DESCRIPTION |
| Chiori Hori; Mitsubishi Electric Research Laboratories, United States |
| Takaaki Hori; Mitsubishi Electric Research Laboratories, United States |
| Tim Marks; Mitsubishi Electric Research Laboratories, United States |
| John Hershey; Mitsubishi Electric Research Laboratories, United States |
| NEW.1.18: CRACKING THE COCKTAIL PARTY PROBLEM BY MULTI-BEAM DEEP ATTRACTOR NETWORK |
| Zhuo Chen; Microsoft Corporation, United States |
| Jinyu Li; Microsoft Corporation, United States |
| Xiong Xiao; Microsoft Corporation, United States |
| Takuya Yoshioka; Microsoft Corporation, United States |
| Huaming Wang; Microsoft Corporation, United States |
| Zhenghao Wang; Microsoft Corporation, United States |
| Yifan Gong; Microsoft Corporation, United States |
| NEW.1.19: GROUND TRUTH ESTIMATION OF SPOKEN ENGLISH FLUENCY SCORE USING DECORRELATION PENALIZED LOW-RANK MATRIX FACTORIZATION |
| Hoon Chung; Electronics and Telecommunications Research Institute, Korea (South) |
| Yun Kyung Lee; Electronics and Telecommunications Research Institute, Korea (South) |
| Jeon Gue Park; Electronics and Telecommunications Research Institute, Korea (South) |
