We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train the attention and decoder networks. In this paper we address this shortcoming by pretraining our network parameters using only text-based data and transcribed speech from other languages. We analyze the relative contributions of both sources of data. Across 3 test languages, our text-based approach resulted in a 20% average relative improvement over a text-based augmentation technique without pretraining. Using transcribed speech from nearby languages gives a further 20-30% relative reduction in character error rate.
@article{arxiv.1812.03919,
title = {Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings},
author = {Matthew Wiesner and Adithya Renduchintala and Shinji Watanabe and Chunxi Liu and Najim Dehak and Sanjeev Khudanpur},
journal= {arXiv preprint arXiv:1812.03919},
year = {2019}
}