# Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion

arXiv: https://arxiv.org/abs/2006.14194 · HTML: https://mlsanity.com/paper/2006.14194/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings](https://mlsanity.com/paper/2307.16643/) (2023)
- [Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition](https://mlsanity.com/paper/2105.12708/) (2021)
- [Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech](https://mlsanity.com/paper/2206.02147/) (2022)
- [MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model](https://mlsanity.com/paper/2509.01391/) (2025)

## Abstract (arXiv)

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU"). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1,2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol inventories of Latin-like alphabets and cross-linguistically shared feature representations. Such model is especially useful in the scenarios of low resource languages and code switching/foreign words, where the pronunciations in one language need to be adapted to other locales or accents. We further experiment with word language distribution vector as an additional training target in order to improve system performance by helping the model decouple pronunciations across a variety of languages in the parameter space. We show 7.2% average improvement in phoneme error rate over low resource languages and no degradation over high resource ones compared to monolingual baselines.