Technical Program
SP-P7: Multilingual Recognition and Identification |
| Session Type: Poster |
| Time: Wednesday, May 29, 08:00 - 10:00 |
| Location: Poster Area D |
| Session Chair: Dong Yu, Microsoft |
| SP-P7.1: CROSS-LANGUAGE KNOWLEDGE TRANSFER USING MULTILINGUAL DEEP NEURAL NETWORK WITH SHARED HIDDEN LAYERS |
| Jui-Ting Huang; Microsoft Corporation |
| Jinyu Li; Microsoft Corporation |
| Dong Yu; Microsoft Research |
| Li Deng; Microsoft Research |
| Yifan Gong; Microsoft Corporation |
| SP-P7.2: RAPID DEVELOPMENT OF A LATVIAN SPEECH-TO-TEXT SYSTEM |
| Ilya Oparin; LNE |
| Lori Lamel; LIMSI CNRS |
| Jean-Luc Gauvain; LIMSI CNRS |
| SP-P7.3: LANGUAGE DIARIZATION FOR CODE-SWITCH CONVERSATIONAL SPEECH |
| Dau-Cheng Lyu; Nanyang Technological University |
| Eng-Siong Chng; Nanyang Technological University |
| Haizhou Li; Nanyang Technological University |
| SP-P7.4: MULTILINGUAL TRAINING OF DEEP NEURAL NETWORKS |
| Arnab Ghoshal; University of Edinburgh |
| Pawel Swietojanski; University of Edinburgh |
| Steve Renals; University of Edinburgh |
| SP-P7.5: MANUAL AND SEMI-AUTOMATIC APPROACHES TO BUILDING A MULTILINGUAL PHONEME SET |
| Ekaterina Egorova; Brno University of Technology |
| Karel Vesely; Brno University of Technology |
| Martin Karafiat; Brno University of Technology |
| Milos Janda; Brno University of Technology |
| Jan Cernocky; Brno University of Technology |
| SP-P7.6: RAPID BOOTSTRAPPING OF A UKRAINIAN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION SYSTEM |
| Tim Schlippe; Karlsruhe Institute of Technology (KIT) |
| Mykola Volovyk; Karlsruhe Institute of Technology (KIT) |
| Kateryna Yurchenko; Karlsruhe Institute of Technology (KIT) |
| Tanja Schultz; Karlsruhe Institute of Technology (KIT) |
| SP-P7.7: GRAPHEME AND MULTILINGUAL POSTERIOR FEATURES FOR UNDER-RESOURCED SPEECH RECOGNITION: A STUDY ON SCOTTISH GAELIC |
| Ramya Rasipuram; Idiap Research Institute, École polytechnique fédérale de Lausanne |
| Peter Bell; Centre for Speech Technology Research, University of Edinburgh |
| Mathew Magimai Doss; Idiap Research Institute |
| SP-P7.8: SUBSPACE MIXTURE MODEL FOR LOW-RESOURCE SPEECH RECOGNITION IN CROSS-LINGUAL SETTINGS |
| Yajie Miao; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |
| Alex Waibel; Carnegie Mellon University |
| SP-P7.9: ACCENT RECOGNITION USING I-VECTOR, GAUSSIAN MEAN SUPERVECTOR AND GAUSSIAN POSTERIOR PROBABILITY SUPERVECTOR FOR SPONTANEOUS TELEPHONE SPEECH |
| Mohamad Hasan Bahari; Katholieke Universiteit Leuven |
| Rahim Saeidi; Radboud University Nijmegen |
| Hugo Van hamme; Katholieke Universiteit Leuven |
| David Van Leeuwen; Radboud University Nijmegen |
| SP-P7.10: INVESTIGATION ON CROSS- AND MULTILINGUAL MLP FEATURES UNDER MATCHED AND MISMATCHED ACOUSTICAL CONDITIONS |
| Zoltán Tüske; RWTH Aachen University |
| Joel Pinto; Nuance Communications Deutschland GmbH |
| Daniel Willett; Nuance Communications Deutschland GmbH |
| Ralf Schlüter; RWTH Aachen University |
| SP-P7.11: EXEMPLAR BASED LANGUAGE RECOGNITION METHOD FOR SHORT-DURATION SPEECH SEGMENTS |
| Meng-Ge Wang; University of Science and Technology of China |
| Yan Song; University of Science and Technology of China |
| Bing Jiang; University of Science and Technology of China |
| Li-Rong Dai; University of Science and Technology of China |
| Ian McLoulghlin; University of Science and Technology of China |
| SP-P7.12: AUTOMATIC LOCALIZATION OF A LANGUAGE-INDEPENDENT SUB-NETWORK ON DEEP NEURAL NETWORKS TRAINED BY MULTI-LINGUAL SPEECH |
| Shigeki Matsuda; National Institute of Information and Communications Technology |
| Xugang Lu; National Institute of Information and Communications Technology |
| Hideki Kashioka; National Institute of Information and Communications Technology |
| SP-P7.13: SUPERVECTOR PRE-PROCESSING FOR PRSVM-BASED CHINESE AND ARABIC DIALECT IDENTIFICATION |
| Qian Zhang; The University of Texas at Dallas |
| Hynek Boril; The University of Texas at Dallas |
| John H.L. Hansen; The University of Texas at Dallas |
| SP-P7.14: IMPROVED MIXED LANGUAGE SPEECH RECOGNITION USING ASYMMETRIC ACOUSTIC MODEL AND LANGUAGE MODEL WITH CODE-SWITCH INVERSION CONSTRAINTS |
| Ying Li; The Hong Kong University of Science and Technology |
| Pascale Fung; The Hong Kong University of Science and Technology |