SRPOL’s System for the IWSLT 2020 End-to-End Speech Translation Task

Potapczyk, Tomasz; Przybysz, Paweł

doi:10.18653/v1/2020.iwslt-1.9

Public

SRPOL’s System for the IWSLT 2020 End-to-End Speech Translation Task

Published • Jan 1, 2020

Authors:

Tomasz Potapczyk

Paweł Przybysz

Abstract

This paper describes the submission to IWSLT 2020 We took part in the offline End-to-End English to German TED lectures translation task. We based our solution on our last year's submission We used a slightly altered Transformer(Vaswani et al., 2017) architecture with ResNet-like(He et al., 2016) co...

View

Open Access

Subject

Transformer

Computer science

Speech translation

Generate AI Take for this paper

Highlights, strengths & weaknesses, commercial applications, and societal impact — written for this paper on demand.

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!