تصف هذه الورقة Kit'SubImission إلى مهمة ترجمة الكلام IWSLT 2021 دون اتصال بالإنترنت.وصفنا نظاما في كل من الحالة المتتالية وحالة نهاية إلى النهاية.في الحالة المتتالية، حققنا في معماريات مختلفة من نهاية إلى نهاية لوحدة التعرف على الكلام.لوحدة تجزئة النص، قمنا بتدريب نموذج صغير يستند إلى محول على بيانات أحادية الجودة عالية الجودة.لوحدة الترجمة، تم إعادة استخدام نموذج الترجمة العصبي في العام الماضي.في حالة نهاية إلى نهاية، فقد قمنا بتحسين بنية محولات الخطاب النسبية للوصول أو حتى تجاوز نتيجة نظام Cascade.
This paper describes KIT'submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the speech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year's neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system.
References used
https://aclanthology.org/
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 knowl
In this paper, we describe Zhejiang University's submission to the IWSLT2021 Multilingual Speech Translation Task. This task focuses on speech translation (ST) research across many non-English source languages. Participants can decide whether to work
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate transcription. We use the Transformer-based
This paper describes Maastricht University's participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions. Our primary system
The paper describes BUT's English to German offline speech translation (ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on MustC-Common te