Technical Program

PM2: Topics in Spoken Language Processing

Session Type: Poster
Poster Time: Monday, December 8, 10:00 - 11:30
Location: Emerald 1-3
Session Chair: Agustin Gravano, University of Buenos Aires
 
PM2.201: OPEN-DOMAIN UTTERANCE GENERATION USING PHRASE PAIRS BASED ON DEPENDENCY RELATIONS
         Hiroaki Sugiyama; NTT, Japan
         Toyomi Meguro; NTT, Japan
         Ryuichiro Higashinaka; NTT, Japan
         Yasuhiro Minami; NTT, Japan
 
PM2.202: BILINGUAL RECURRENT NEURAL NETWORKS FOR IMPROVED STATISTICAL MACHINE TRANSLATION
         Bing Zhao; LinkedIn Inc., United States
         Yik-Cheung Tam; SRI International, United States
 
PM2.203: INCREMENTAL TRANSLATION USING HIERARCHICAL PHRASE-BASED TRANSLATION SYSTEM
         Maryam Siahbani; Simon Fraser University, Canada
         Ramtin Mehdizadeh Seraj; Simon Fraser University, Canada
         Baskaran Sankaran; Simon Fraser University, Canada
         Anoop Sarkar; Simon Fraser University, Canada
 
PM2.204: DOMAIN INVARIANT SPEECH FEATURES USING A NEW DIVERGENCE MEASURE
         Alan Wisler; Arizona State University, United States
         Visar Berisha; Arizona State University, United States
         Julie Liss; Arizona State University, United States
         Andreas Spanias; Arizona State University, United States
 
PM2.205: LABEL CORRELATION MIXTURE MODEL FOR MULTI-LABEL TEXT CATEGORIZATION
         Zhiyang He; Tsinghua University, China
         Ji Wu; Tsinghua University, China
         Ping Lv; Tsinghua University, China
 
PM2.206: UTTERANCE COPY FOR KLATT'S SPEECH SYNTHESIZER USING GENETIC ALGORITHM
         José Sousa; Federal University of Pará, Brazil
         Fabíola Araújo; Federal University of Pará, Brazil
         Aldebaro Klautau; Federal University of Pará, Brazil
 
PM2.207: A METHODOLOGY FOR USING CROWDSOURCED DATA TO MEASURE UNCERTAINTY IN NATURAL SPEECH
         Lara Martin; Carnegie Mellon University, United States
         Matthew Stone; Rutgers University, United States
         Florian Metze; Carnegie Mellon University, United States
         Jack Mostow; Carnegie Mellon University, United States
 
PM2.208: UNSUPERVISED LEXICAL CLUSTERING OF SPEECH SEGMENTS USING FIXED-DIMENSIONAL ACOUSTIC EMBEDDINGS
         Herman Kamper; University of Edinburgh, United Kingdom
         Aren Jansen; Johns Hopkins University, United States
         Simon King; University of Edinburgh, United Kingdom
         Sharon Goldwater; University of Edinburgh, United Kingdom
 
PM2.209: PHONETICS EMBEDDING LEARNING WITH SIDE INFORMATION
         Gabriel Synnaeve; ENS/EHESS, France
         Thomas Schatz; ENS/EHESS/CNRS / INRIA, France
         Emmanuel Dupoux; ENS/EHESS/CNRS, France
 
PM2.210: TRAINING A STATISTICAL SURFACE REALISER FROM AUTOMATIC SLOT LABELLING
         Heriberto Cuayahuitl; Heriot-Watt University, United Kingdom
         Nina Dethlefs; Heriot-Watt University, United Kingdom
         Helen Hastie; Heriot-Watt University, United Kingdom
         Xingkun Liu; Heriot-Watt University, United Kingdom
 
PM2.211: BACKGROUND-TRACKING ACOUSTIC FEATURES FOR GENRE IDENTIFICATION OF BROADCAST SHOWS
         Oscar Saz; University of Sheffield, United Kingdom
         Mortaza Doulaty; University of Sheffield, United Kingdom
         Thomas Hain; University of Sheffield, United Kingdom