# Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models

arXiv: https://arxiv.org/abs/2411.07563 · HTML: https://mlsanity.com/paper/2411.07563/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [ByT5 model for massively multilingual grapheme-to-phoneme conversion](https://mlsanity.com/paper/2204.03067/) (2022)
- [Transformer based Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/2004.06338/) (2020)
- [Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/1506.00196/) (2015)
- [SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation](https://mlsanity.com/paper/2207.13703/) (2022)
- [Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction](https://mlsanity.com/paper/2307.09744/) (2023)

## Built on by (most cited first, 2 of 2)

- [Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study](https://mlsanity.com/paper/2606.22009/) (2026)
- [SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings](https://mlsanity.com/paper/2607.01238/) (2026)

## Abstract (arXiv)

Grapheme-to-phoneme (G2P) conversion is a crucial step in Text-to-Speech (TTS) systems, responsible for mapping grapheme to corresponding phonetic representations. However, it faces ambiguities problems where the same grapheme can represent multiple phonemes depending on contexts, posing a challenge for G2P conversion. Inspired by the remarkable success of Large Language Models (LLMs) in handling context-aware scenarios, contextual G2P conversion systems with LLMs' in-context knowledge retrieval (ICKR) capabilities are proposed to promote disambiguation capability. The efficacy of incorporating ICKR into G2P conversion systems is demonstrated thoroughly on the Librig2p dataset. In particular, the best contextual G2P conversion system using ICKR outperforms the baseline with weighted average phoneme error rate (PER) reductions of 2.0% absolute (28.9% relative). Using GPT-4 in the ICKR system can increase of 3.5% absolute (3.8% relative) on the Librig2p dataset.