paper-with-me

Papers

Amazon Alexa AI’s System for IWSLT 2022 Offline Speech Translation Shared Task

2022-05-01 · IWSLT (ACL) 2022 5 · Akshaya Shanbhogue, Ran Xue, Ching-Yun Chang, Sarah Campbell

This paper describes Amazon Alexa AI’s submission to the IWSLT 2022 Offline Speech Translation Task. Our system is an end-to-end speech translation model that leverages pretrained models and cross modality transfer learning. We detail two improvements to the knowledge transfer schema. First, we implemented a new loss function that reduces knowledge gap between audio and text modalities in translation task effectively. Second, we investigate multiple finetuning strategies including sampling loss, language grouping and domain adaption. These strategies aims to bridge the gaps between speech and text translation tasks. We also implement a multi-stage segmentation and merging strategy that yields improvements on the unsegmented development datasets. Results show that the proposed loss function consistently improves BLEU scores on the development datasets for both English-German and multilingual models. Additionally, certain language pairs see BLEU score improvements with specific finetuning strategies.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationTransfer LearningTranslation

Similar Papers 제목 키워드 기반

CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022

2022-04-12 · IWSLT (ACL) 2022 5 · Peter Polák, Ngoc-Quan Ngoc, Tuan-Nam Nguyen, Danni Liu 외

In this paper, we describe our submission to the Simultaneous Speech Translation at IWSLT 2022. We explore strategies to utilize an offline model in a simultaneous setting without the need to modify the original model. I…

Translation

End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning

2020-07-01 · WS 2020 7 · Nikhil Kumar Lakumarapu, Beomseok Lee, Sathish Reddy Indurthi, Hou Jeung Han 외

In this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task. We adopt the Transformer architecture coupled with the meta-learning approach to build our end-to-end Speech-to-Text Tran…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationMachine Translation+6

ELITR Non-Native Speech Translation at IWSLT 2020

2020-06-05 · WS 2020 7 · Dominik Macháček, Jonáš Kratochvíl, Sangeet Sagar, Matúš Žilinec 외

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…

Translation

The Volctrans Neural Speech Translation System for IWSLT 2021

2021-05-16 · ACL (IWSLT) 2021 8 · Chengqi Zhao, Zhicheng Liu, Jian Tong, Tao Wang 외

This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best …

Translation

DiDi Labs' End-to-end System for the IWSLT 2020 Offline Speech TranslationTask

2020-07-01 · WS 2020 7 · Arkady Arkhangorodsky, Yiqi Huang, Amittai Axelrod

This paper describes the system that was submitted by DiDi Labs to the offline speech translation task for IWSLT 2020. We trained an end-to-end system that translates audio from English TED talks to German text, without …

Translation