English

Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects

Computation and Language 2021-04-12 v1 Machine Learning Sound

Abstract

Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data. We propose a novel use of transformer-based attention model that can adapt to unseen dialects of English language, while using a small dictionary. We show that our method has potential applications for accent transfer for text-to-speech, and for building robust G2P models for dialects with limited pronunciation dictionary size. We experiment with two English dialects: Indian and British. A model trained from scratch using 1000 words from British English dictionary, with 14211 words held out, leads to phoneme error rate (PER) of 26.877%, on a test set generated using the full dictionary. The same model pretrained on CMUDict American English dictionary, and fine-tuned on the same dataset leads to PER of 2.469% on the test set.

Keywords

Cite

@article{arxiv.2104.04091,
  title  = {Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects},
  author = {Eric Engelhart and Mahsa Elyasi and Gaurav Bharaj},
  journal= {arXiv preprint arXiv:2104.04091},
  year   = {2021}
}

Comments

5

R2 v1 2026-06-24T00:59:06.540Z