Pre-training on high-resource speech recognition improves low-resource speech-to-text translation

Pre-training on high-resource speech recognition improves low-resource speech-to-text translation Sameer Bansal author Herman Kamper author Karen Livescu author Adam Lopez author Sharon Goldwater author 2019-06 text Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) Jill Burstein editor Christy Doran editor Thamar Solorio editor Association for Computational Linguistics Minneapolis, Minnesota conference publication bansal-etal-2019-pre 10.18653/v1/N19-1006 https://aclanthology.org/N19-1006/ 2019-06 58 68