2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
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 |