# Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion

arXiv: https://arxiv.org/abs/1506.00196 · HTML: https://mlsanity.com/paper/1506.00196/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2015.

## Built on by (most cited first, 19 of 19)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [ByT5 model for massively multilingual grapheme-to-phoneme conversion](https://mlsanity.com/paper/2204.03067/) (2022)
- [Smoothing and Shrinking the Sparse Seq2Seq Search Space](https://mlsanity.com/paper/2103.10291/) (2021)
- [A Survey of Deep Learning Audio Generation Methods](https://mlsanity.com/paper/2406.00146/) (2024)
- [Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech](https://mlsanity.com/paper/2401.10465/) (2024)
- [Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study](https://mlsanity.com/paper/2606.22009/) (2026)
- [Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models](https://mlsanity.com/paper/2411.07563/) (2024)
- [Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown](https://mlsanity.com/paper/2102.10551/) (2021)
- [A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion](https://mlsanity.com/paper/2209.11963/) (2022)
- [Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction](https://mlsanity.com/paper/2308.08442/) (2023)
- [External Knowledge Augmented Polyphone Disambiguation Using Large Language Model](https://mlsanity.com/paper/2312.11920/) (2023)
- [Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning](https://mlsanity.com/paper/2609.09974/) (2026)
- [Neural String Edit Distance](https://mlsanity.com/paper/2104.08388/) (2021)
- [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)
- [Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation](https://mlsanity.com/paper/2210.10200/) (2022)
- [UniGlyph: A Seven-Segment Script for Universal Language Representation](https://mlsanity.com/paper/2410.08974/) (2024)
- [GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor](https://mlsanity.com/paper/2505.19384/) (2025)
- [Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS](https://mlsanity.com/paper/2512.08006/) (2025)

## Abstract (arXiv)

Sequence-to-sequence translation methods based on generation with a side-conditioned language model have recently shown promising results in several tasks. In machine translation, models conditioned on source side words have been used to produce target-language text, and in image captioning, models conditioned images have been used to generate caption text. Past work with this approach has focused on large vocabulary tasks, and measured quality in terms of BLEU. In this paper, we explore the applicability of such models to the qualitatively different grapheme-to-phoneme task. Here, the input and output side vocabularies are small, plain n-gram models do well, and credit is only given when the output is exactly correct. We find that the simple side-conditioned generation approach is able to rival the state-of-the-art, and we are able to significantly advance the stat-of-the-art with bi-directional long short-term memory (LSTM) neural networks that use the same alignment information that is used in conventional approaches.