HLT-L1: Spoken Language Translation |
| Session Type: Lecture |
| Time: Thursday, 7 May, 09:00 - 11:00 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Yang Liu, Amazon |
| HLT-L1.1: END-END SPEECH-TO-TEXT TRANSLATION WITH MODALITY AGNOSTIC META-LEARNING |
| Sathish Reddy Indurthi; Samsung Research |
| Houjeung Han; Samsung Research |
| Nikhil Kumar Lakumarapu; Samsung Research |
| Beomseok Lee; Samsung Research |
| Insoo Chung; Samsung Research |
| Sangha Kim; Samsung Research |
| Chanwoo Kim; Samsung Research |
| HLT-L1.2: ANALYZING ASR PRETRAINING FOR LOW-RESOURCE SPEECH-TO-TEXT TRANSLATION |
| Mihaela C. Stoian; University of Edinburgh |
| Sameer Bansal; University of Edinburgh |
| Sharon Goldwater; University of Edinburgh |
| HLT-L1.3: INSTANCE-BASED MODEL ADAPTATION FOR DIRECT SPEECH TRANSLATION |
| Mattia Antonino Di Gangi; Fondazione Bruno Kessler and University of Trento |
| Viet Nhat Nguyen; University of Trento |
| Matteo Negri; Fondazione Bruno Kessler |
| Marco Turchi; Fondazione Bruno Kessler |
| HLT-L1.4: RE-TRANSLATION STRATEGIES FOR LONG FORM, SIMULTANEOUS, SPOKEN LANGUAGE TRANSLATION |
| Naveen Arivazhagan; Google |
| Colin Cherry; Google |
| Te I; Google |
| Wolfgang Macherey; Google |
| Pallavi Baljekar; Google |
| George Foster; Google |
| HLT-L1.5: SKINAUGMENT: AUTO-ENCODING SPEAKER CONVERSIONS FOR AUTOMATIC SPEECH TRANSLATION |
| Arya D. McCarthy; Johns Hopkins University |
| Liezl Puzon; Facebook |
| Juan Pino; Facebook |
| HLT-L1.6: END-TO-END SPEECH TRANSLATION WITH SELF-CONTAINED VOCABULARY MANIPULATION |
| Mei Tu; Samsung Research China-Beijing |
| Fan Zhang; Samsung Research China-Beijing |
| Wei Liu; Samsung Research China-Beijing |