Publication
Massively multilingual neural grapheme-to-phoneme conversion
Ben Peters; Jon Dehdari; Josef van Genabith
In: Proceedings of Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing (EMNLP-2017), September 1-11, Copenhagen, Denmark, 2017.
Abstract
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic
speech recognition systems. Most g2p systems are monolingual: they require language-
specific data or handcrafting of rules. Such systems are difficult to extend to low resource
languages, for which data and handcrafted rules are not available. As an alternative, we
present a neural sequence-to-sequence approach to g2p which is trained on spelling–
pronunciation pairs in hundreds of languages. The system shares a single encoder and
decoder across all languages, allowing it to utilize the intrinsic similarities between different
writing systems. We show an 11% improvement in phoneme error rate over an approach
based on adapting high-resource monolingual g2p models to low-resource languages. Our
model is also much more compact relative to previous approaches.