تحتوي هذه الورقة على وصف لتقديم معهد Karlsruhe للتكنولوجيا (KIT) لمهمة ترجمة TEDX متعددة اللغات في حملة تقييم IWSLT 2021.نهجنا الرئيسي هو تطوير كل من النظم المتتالية ونظم نهاية إلى نهاية وتجمع بينها في نهاية المطاف لتحقيق أفضل النتائج الممكنة لهذا الإعداد المنخفض للغاية الموارد.يؤكد التقرير أيضا تحسين بعض التحسن المعماري المتسق إضافته إلى بنية المحولات، لجميع المهام: ترجمة الترجمة والنسخ والنطق.
This paper contains the description for the submission of Karlsruhe Institute of Technology (KIT) for the multilingual TEDx translation task in the IWSLT 2021 evaluation campaign. Our main approach is to develop both cascade and end-to-end systems and eventually combine them together to achieve the best possible results for this extremely low-resource setting. The report also confirms certain consistent architectural improvement added to the Transformer architecture, for all tasks: translation, transcription and speech translation.
References used
https://aclanthology.org/
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
In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities
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
Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length prevents its
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