توضح هذه الورقة التقديم إلى المهمة المشتركة لخطوط خطاب IWSLT 2021 من قبل فريق IMS.نستخدم النماذج الحديثة من النماذج المشتركة مع العديد من أساليب تكبير البيانات ومتعدد المهام والنقل مناهج للتعرف على الكلام التلقائي (ASR) وخطوات الترجمة الآلية (MT) لنظامنا المتتالي.علاوة على ذلك، فإننا نستكشف أيضا جدوى نموذج ترجمة خط الكلام (ST) بالكامل في حالة كمية مقيدة للغاية من الحقيقة الأرضية المصنفة.يحقق أفضل نظامنا أفضل أداء بين جميع الأنظمة المقدمة للسواحيلية للإنجليزية والفرنسية مع درجات بلو 7.7 و 13.7 على التوالي، وثاني أفضل نتيجة للسواحيلية السواحلية إلى الإنجليزية مع النتيجة بلو 14.9.
This paper describes the submission to the IWSLT 2021 Low-Resource Speech Translation Shared Task by IMS team. We utilize state-of-the-art models combined with several data augmentation, multi-task and transfer learning approaches for the automatic speech recognition (ASR) and machine translation (MT) steps of our cascaded system. Moreover, we also explore the feasibility of a full end-to-end speech translation (ST) model in the case of very constrained amount of ground truth labeled data. Our best system achieves the best performance among all submitted systems for Congolese Swahili to English and French with BLEU scores 7.7 and 13.7 respectively, and the second best result for Coastal Swahili to English with BLEU score 14.9.
References used
https://aclanthology.org/
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
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
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 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 spe
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