HLT-P5: Multilingual Processing of Language |
Session Type: Poster |
Time: Friday, 8 May, 11:45 - 13:45 |
Location: On-Demand |
Virtual Session: View on Virtual Platform |
Session Chairs: Lori Lamel, LIMSI and Begoña Díaz, Universitat Internacional de Catalunya
|
|
HLT-P5.1: EUROPARL-ST: A MULTILINGUAL CORPUS FOR SPEECH TRANSLATION OF PARLIAMENTARY DEBATES |
Javier Iranzo-Sánchez; Universitat Politècnica de València |
Joan Albert Silvestre-Cerdà; Universitat Politècnica de València |
Javier Jorge; Universitat Politècnica de València |
Nahuel Roselló; Universitat Politècnica de València |
Adrià Giménez; Universitat Politècnica de València |
Albert Sanchis; Universitat Politècnica de València |
Jorge Civera; Universitat Politècnica de València |
Alfons Juan; Universitat Politècnica de València |
|
HLT-P5.2: MULTILINGUAL GRAPHEME-TO-PHONEME CONVERSION WITH BYTE REPRESENTATION |
Mingzhi Yu; University of Pittsburgh |
Hieu Nguyen; Amazon, Inc. |
Alex Sokolov; Amazon, Inc. |
Jack Lepird; Amazon, Inc. |
Kanthashree Sathyendra; Amazon, Inc. |
Samridhi Choudhary; Amazon, Inc. |
Athanasios Mouchtaris; Amazon, Inc. |
Siegfried Kunzmann; Amazon, Inc. |
|
HLT-P5.3: LANGUAGE-AGNOSTIC MULTILINGUAL MODELING |
Arindrima Datta; Google LLC |
Bhuvana Ramabhadran; Google LLC |
Jesse Emond; Google LLC |
Anjuli Kannan; Google LLC |
Brian Roark; Google LLC |
|
HLT-P5.4: ADI17: A FINE-GRAINED ARABIC DIALECT IDENTIFICATION DATASET |
Suwon Shon; ASAPP Inc |
Ahmed Ali; Qatar Computing Research Institute |
Younes Samih; Qatar Computing Research Institute |
Hamdy Mubarak; Qatar Computing Research Institute |
James Glass; Massachusetts Institute of Technology |
|
HLT-P5.5: UNIVERSAL PHONE RECOGNITION WITH A MULTILINGUAL ALLOPHONE SYSTEM |
Xinjian Li; Carnegie Mellon University |
Siddharth Dalmia; Carnegie Mellon University |
Juncheng Li; Carnegie Mellon University |
Patrick Littell; National Research Council of Canada |
Matthew Lee; SIL International |
Jiali Yao; ByteDance AI Lab |
Antonios Anastasopoulos; Carnegie Mellon University |
David Mortensen; Carnegie Mellon University |
Graham Neubig; Carnegie Mellon University |
Alan Black; Carnegie Mellon University |
Florian Metze; Carnegie Mellon University |
|
HLT-P5.6: COUPLED TRAINING OF SEQUENCE-TO-SEQUENCE MODELS FOR ACCENTED SPEECH RECOGNITION |
Vinit Unni; Indian Institute of Technology Bombay |
Nitish Joshi; Indian Institute of Technology Bombay |
Preethi Jyothi; Indian Institute of Technology Bombay |
|
HLT-P5.7: ADDRESSING ACCENT MISMATCH IN MANDARIN-ENGLISH CODE-SWITCHING SPEECH RECOGNITION |
Zhili Tan; Microsoft |
Xinghua Fan; Microsoft |
Hui Zhu; Microsoft |
Ed Lin; Microsoft |
|
HLT-P5.8: DETECTING MISMATCH BETWEEN TEXT SCRIPT AND VOICE-OVER USING UTTERANCE VERIFICATION BASED ON PHONEME RECOGNITION RANKING |
Yoonjae Jeong; NCSOFT |
Hoon-Young Cho; NCSOFT |
|
HLT-P5.9: DNN-BASED SPEECH RECOGNITION FOR GLOBALPHONE LANGUAGES |
Martha Yifiru Tachbelie; University of Bremen |
Ayimunishagu Abulimiti; University of Bremen |
Solomon Teferra Abate; University of Bremen |
Tanja Schultz; University of Bremen |
|
HLT-P5.10: DEEP NEURAL NETWORKS BASED AUTOMATIC SPEECH RECOGNITION FOR FOUR ETHIOPIAN LANGUAGES |
Solomon Teferra Abate; University of Bremen |
Martha Yifiru Tachbelie; University of Bremen |
Tanja Schultz; University of Bremen |
|
HLT-P5.11: IMPROVING THE PERFORMANCE OF TRANSFORMER BASED LOW RESOURCE SPEECH RECOGNITION FOR INDIAN LANGUAGES |
Vishwas M. Shetty; Indian Institute of Technology Madras |
Metilda Sagaya Mary N J; Indian Institute of Technology Madras |
Srinivasan Umesh; Indian Institute of Technology Madras |
|
HLT-P5.12: IMPROVING LANGUAGE IDENTIFICATION FOR MULTILINGUAL SPEAKERS |
Andrew Titus; Apple |
Jan Silovsky; Apple |
Nanxin Chen; Apple and Johns Hopkins University |
Roger Hsiao; Apple |
Mary Young; Apple |
Arnab Ghoshal; Apple |
|