AN EMPIRICAL STUDY OF END-TO-END SIMULTANEOUS SPEECH TRANSLATION DECODING STRATEGIES

Ha Nguyen (1) , Yannick Estève (2) , Laurent Besacier (1)

1 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
2 LIA - Laboratoire Informatique d'Avignon

This paper proposes a decoding strategy for end-to-end simultaneous speech translation. We leverage end-to-end models trained in offline mode and conduct an empirical study for two language pairs (English-to-German and English-to-Portuguese). We also investigate different output token granularities including characters and Byte Pair Encoding (BPE) units. The results show that the proposed decoding approach allows to control BLEU/Average Lagging trade-off along different latency regimes. Our best decoding settings achieve comparable results with a strong cascade model evaluated on the simultaneous translation track of IWSLT 2020 shared task.

Mots clés: Simultaneous speech translation; end-to-end models; low-latency decoding

Domaines: Informatique et langage [cs.CL]

Ha Nguyen, Yannick Estève, Laurent Besacier. AN EMPIRICAL STUDY OF END-TO-END SIMULTANEOUS SPEECH TRANSLATION DECODING STRATEGIES. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021), Jun 2021, Toronto, Canada. ⟨10.1109/ICASSP39728.2021.9414276⟩. ⟨hal-03372480⟩