End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning
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 Translation (ST) system. Our meta-learning approach tackles the data scarcity of the ST task by leveraging the data available from Automatic Speech Recognition (ASR) and Machine Translation (MT) tasks. The meta-learning approach combined with synthetic data augmentation techniques improves the model performance significantly and achieves BLEU scores of 24.58, 27.51, and 27.61 on IWSLT test 2015, MuST-C test, and Europarl-ST test sets respectively.
PDF Abstract
Datasets
MuST-C
Results from the Paper
Ranked #3 on
Speech-to-Text Translation
on MuST-C EN->DE
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Speech-to-Text Translation | MuST-C EN->DE | Transformer + Meta Learning(ASR/MT) + Data Augmentation | Case-sensitive sacreBLEU | 27.51 | # 3 |
