Multi-Module G2P Converter for Persian Focusing on Relations between Words

Grapheme-to-phoneme (G2P) is the task of converting a grapheme sequence into its pronunciation sequence. It is an essential component of text-to-speech (TTS) and speech recognition systems for any language lacking consistent pronunciation rules. Persian is a low-resource language with more homograph complexities than languages such as English. In this paper, we investigate the application of integrated and multi-module frameworks for G2P conversion for the Persian language. The results demonstrate that our proposed multi-module G2P system outperforms our integrated systems in terms of accuracy and speed. The system consists of a pronunciation dictionary as our look-up table, along with separate models to handle homographs, OOVs and ezafe in Persian created using GRU and Transformer architectures. The system is sequence-level rather than word-level, which allows it to effectively capture the unwritten relations between words (cross-word information) necessary for homograph disambiguation and ezafe recognition without the need for any pre-processing. After evaluation, our system achieved a 94.48% word-level accuracy, outperforming the previous G2P systems for Persian.