In this paper, we introduce a high-quality and large-scale benchmark dataset for English-Vietnamese speech translation with 508 audio hours, consisting of 331K triplets of (sentence-lengthed audio, English source transcript sentence, Vietnamese target subtitle sentence). We also conduct empirical experiments using strong baselines and find that the traditional "Cascaded" approach still outperforms the modern "End-to-End" approach. To the best of our knowledge, this is the first large-scale English-Vietnamese speech translation study. We hope both our publicly available dataset and study can serve as a starting point for future research and applications on English-Vietnamese speech translation. Our dataset is available at https://github.com/VinAIResearch/PhoST
@article{arxiv.2208.04243,
title = {A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation},
author = {Linh The Nguyen and Nguyen Luong Tran and Long Doan and Manh Luong and Dat Quoc Nguyen},
journal= {arXiv preprint arXiv:2208.04243},
year = {2022}
}
Comments
In Proceedings of INTERSPEECH 2022, to appear. The first three authors contributed equally to this work