One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble
This provides a more accurate G2P solution for speech recognition and synthesis in multiple languages, though it is incremental as it builds on existing Transformer and ensemble methods.
The paper tackled the challenge of grapheme-to-phoneme conversion with limited training data by using multilingual Transformer ensembles and self-training, achieving a word error rate of 14.99 and phoneme error rate of 3.30 across 15 languages, which improved over competitive baselines.
The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P models is challenging. We describe a simple approach of exploiting model ensembles, based on multilingual Transformers and self-training, to develop a highly effective G2P solution for 15 languages. Our models are developed as part of our participation in the SIGMORPHON 2020 Shared Task 1 focused at G2P. Our best models achieve 14.99 word error rate (WER) and 3.30 phoneme error rate (PER), a sizeable improvement over the shared task competitive baselines.