ESPnet-ST IWSLT 2021 Offline Speech Translation System

Understand

This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track.

• This year we made various efforts on training data, architecture, and audio segmentation.
• On the data side, we investigated sequence-level knowledge distillation (SeqKD) for end-to-end (E2E) speech translation.
• Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext.