Abstract
In this paper we explore a very simple neural approach to mapping orthography to phonetic transcription in a low-resource context. The basic idea is to start from a baseline system and focus all efforts on data augmentation. We will see that some techniques work, but others do not.
Cite
CITATION STYLE
APA
Hammond, M. (2021). Data augmentation for low-resource grapheme-to-phoneme mapping. In SIGMORPHON 2021 - 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, Proceedings of the Workshop (pp. 126–130). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.sigmorphon-1.14
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Already have an account? Sign in
Sign up for free