ELITR Non-Native Speech Translation at IWSLT 2020
This is an incremental improvement for researchers and practitioners in speech translation, focusing on non-native speech.
The paper describes ELITR's system submission for the non-native speech translation task at IWSLT 2020, tackling the problem of translating non-native speech by developing offline and real-time ASR and SLT systems, with results including a new end-to-end general ASR system and a hybrid ASR trained on non-native speech, though concrete numbers are not provided.
This paper is an ELITR system submission for the non-native speech translation task at IWSLT 2020. We describe systems for offline ASR, real-time ASR, and our cascaded approach to offline SLT and real-time SLT. We select our primary candidates from a pool of pre-existing systems, develop a new end-to-end general ASR system, and a hybrid ASR trained on non-native speech. The provided small validation set prevents us from carrying out a complex validation, but we submit all the unselected candidates for contrastive evaluation on the test set.