ELITR Non-Native Speech Translation at IWSLT 2020

Abstract

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-toend 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.

CUNI Neural ASR with Phoneme-Level Intermediate Step for~Non-Native~SLT at IWSLT 2020

“…Our ASR system produces lowercased, unpunctuated text, but the machine translation works on capitalized, punctuated text, segmented to individual sentences. We use the same biRNN punctuator, truecaser and segmenter as Macháček et al (2020). The punctuator is a bidirectional recurrent neural network by Tilk and Alumäe (2016) trained on the English side of CzEng (Bojar et al, 2016).…”

Proceedings of the 17th International Conference on Spoken Language Translation

“…Our ASR system produces lowercased, unpunctuated text, but the machine translation works on capitalized, punctuated text, segmented to individual sentences. We use the same biRNN punctuator, truecaser and segmenter as Macháček et al (2020). The punctuator is a bidirectional recurrent neural network by trained on the English side of CzEng .…”

“…We use a rule-based Moses Sentence Splitter . More details are in Macháček et al (2020), Section 4.2.…”

“…Our submission to the SLT track relies on the MT systems, which are used also by ELITR project and are described in their submission to this task (Macháček et al, 2020). We do not rely on their validation for this task.…”

“…We submit also all other machine translation systems for Czech and German by ELITR with our "asr" source for contrastive evaluation. See Macháček et al (2020) for more details.…”