2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

HLT-7: Speech Translation 1: Models

Session Type: Poster
Time: Wednesday, 9 June, 14:00 - 14:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Bhuvana Ramabhadran, Google, Inc.
 
 HLT-7.1: ORTHROS: NON-AUTOREGRESSIVE END-TO-END SPEECH TRANSLATION WITH DUAL-DECODER
         Hirofumi Inaguma; Kyoto University
         Yosuke Higuchi; Waseda University
         Kevin Duh; Johns Hopkins University
         Tatsuya Kawahara; Kyoto University
         Shinji Watanabe; Johns Hopkins University
 
 HLT-7.2: CASCADED MODELS WITH CYCLIC FEEDBACK FOR DIRECT SPEECH TRANSLATION
         Tsz Kin Lam; Heidelberg University
         Shigehiko Schamoni; Heidelberg University
         Stefan Riezler; Heidelberg University
 
 HLT-7.3: JOINTLY TRAINED TRANSFORMERS MODELS FOR SPOKEN LANGUAGE TRANSLATION
         Hari Krishna Vydana; BUT
         Martin Karafiat; Brno University of Technology
         Katerina Zmolikova; Brno University of Technology
         Lukáš Burget; Brno University of Technology
         Jan "Honza" Cernocky; Brno University of Technology
 
 HLT-7.4: EFFICIENT USE OF END-TO-END DATA IN SPOKEN LANGUAGE PROCESSING
         Yiting Lu; University of Cambridge
         Yu Wang; Shanghai Jiao Tong University
         Mark J. F. Gales; Cambridge University
 
 HLT-7.5: STREAMING SIMULTANEOUS SPEECH TRANSLATION WITH AUGMENTED MEMORY TRANSFORMER
         Xutai Ma; Johns Hopkins University
         Yongqiang Wang; Facebook
         Mohammad Dousti; Facebook
         Philipp Koehn; Johns Hopkins University
         Juan Pino; Facebook
 
 HLT-7.6: AN EMPIRICAL STUDY OF END-TO-END SIMULTANEOUS SPEECH TRANSLATION DECODING STRATEGIES
         Ha Nguyen; Université Grenoble Alpes
         Yannick Estève; Avignon Université
         Laurent Besacier; Université Grenoble Alpes