Technical Program

PM1: ASR and Synthesis

Session Type: Poster
Poster Time: Monday, December 8, 10:00 - 11:30
Location: Emerald 4-6
Session Chair: Abhijeet Sangwan, University of Texas at Dallas
 
PM1.101: MARGIN-BASED DISCRIMINATIVE PRONUNCIATION MODELING FOR LARGE VOCABULARY MANDARIN SPEECH RECOGNITION
         Yi Liu; Peking University, China
         Xiangang Li; Peking University, China
         Xihong Wu; Peking University, China
 
PM1.102: SEMANTIC LANGUAGE MODELS FOR AUTOMATIC SPEECH RECOGNITION
         Ali Orkan Bayer; University of Trento, Italy
         Giuseppe Riccardi; University of Trento, Italy
 
PM1.103: CONTEXT-BASED RECOGNITION NETWORK ADAPTATION FOR IMPROVING ON-LINE ASR IN AIR TRAFFIC CONTROL
         Anna Schmidt; Saarland University, Germany
         Youssef Oualil; Saarland University, Germany
         Oliver Ohneiser; German Aerospace Center (DLR), Germany
         Matthias Kleinert; German Aerospace Center (DLR), Germany
         Marc Schulder; Saarland University, Germany
         Arif Khan; Saarland University, Germany
         Hartmut Helmke; German Aerospace Center (DLR), Germany
         Dietrich Klakow; Saarland University, Germany
 
PM1.104: VOICE CONVERSION USING DEEP NEURAL NETWORKS WITH SPEAKER-INDEPENDENT PRE-TRAINING
         Seyed Hamidreza Mohammadi; Oregon Health and Science University, United States
         Alexander Kain; Oregon Health and Science University, United States
 
PM1.105: EFFICIENT MULTI-LINGUAL UNSUPERVISED ACOUSTIC MODEL TRAINING UNDER MISMATCH CONDITIONS
         Masahiro Saiko; NICT, Japan
         Hitoshi Yamamoto; NEC, Japan
         Ryosuke Isotani; NEC, Japan
         Chiori Hori; NICT, Japan
 
PM1.106: ACQUISITION OF ORDINAL WORDS USING WEAKLY SUPERVISED NMF
         Vincent Renkens; KU Leuven, Belgium
         Steven Janssens; KU Leuven, Belgium
         Bart Ons; KU Leuven, Belgium
         Jort Gemmeke; KU Leuven, Belgium
         Hugo Van hamme; KU Leuven, Belgium
 
PM1.107: A DATA-DRIVEN PHONEME MAPPING TECHNIQUE USING INTERPOLATION VECTORS OF PHONE-CLUSTER ADAPTIVE TRAINING
         Basil Abraham; Indian Institute of Technology Madras, India
         Neethu Mariam Joy; Indian Institute of Technology Madras, India
         Navneeth K; Indian Institute of Technology Madras, India
         S Umesh; Indian Institute of Technology Madras, India
 
PM1.108: DOCUMENT-BASED DIRICHLET CLASS LANGUAGE MODEL FOR SPEECH RECOGNITION USING DOCUMENT-BASED N-GRAM EVENTS
         Md. Akmal Haidar; Institut national de la recherche scientifique, University of Quebec, Canada
         Douglas O'Shaughnessy; Institut national de la recherche scientifique, University of Quebec, Canada
 
PM1.109: FURTHER INVESTIGATION INTO MULTILINGUAL TRAINING AND ADAPTATION OF STACKED BOTTLE-NECK NEURAL NETWORK STRUCTURE
         Frantisek Grezl; Brno University of Technology, Czech Republic
         Ekaterina Egorova; Brno University of Technology, Czech Republic
         Martin Karafiat; Brno University of Technology, Czech Republic
 
PM1.110: RECONSTRUCTION OF ARTICULATORY MEASUREMENTS WITH SMOOTHED LOW-RANK MATRIX COMPLETION
         Weiran Wang; Toyota Technological Institute at Chicago, United States
         Raman Arora; Johns Hopkins University, United States
         Karen Livescu; Toyota Technological Institute at Chicago, United States