# PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech

arXiv: https://arxiv.org/abs/2511.03080 · HTML: https://mlsanity.com/paper/2511.03080/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 2 of 2)

- [RNN Approaches to Text Normalization: A Challenge](https://mlsanity.com/paper/1611.00068/) (2016)
- [A Chat About Boring Problems: Studying GPT-based text normalization](https://mlsanity.com/paper/2309.13426/) (2023)

## Built on by (most cited first, 3 of 3)

- [Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation](https://mlsanity.com/paper/2609.01246/) (2026)
- [Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach](https://mlsanity.com/paper/2609.27205/) (2026)
- [THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer](https://mlsanity.com/paper/2609.30984/) (2026)

## Abstract (arXiv)

Text Normalization (TN) is a key preprocessing step in Text-to-Speech (TTS) systems, converting written forms into their canonical spoken equivalents. Traditional TN systems can exhibit high accuracy, but involve substantial engineering effort, are difficult to scale, and pose challenges to language coverage, particularly in low-resource settings. We propose PolyNorm, a prompt-based approach to TN using Large Language Models (LLMs), aiming to reduce the reliance on manually crafted rules and enable broader linguistic applicability with minimal human intervention. Additionally, we present a language-agnostic pipeline for automatic data curation and evaluation, designed to facilitate scalable experimentation across diverse languages. Experiments across eight languages show consistent reductions in the word error rate (WER) compared to a production-grade-based system. To support further research, we release PolyNorm-Benchmark, a multilingual data set covering a diverse range of text normalization phenomena.