SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2511.03080 · EMNLP · 2025

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

Haotian He, Michel Wong, Ali Alshehri, Sophia Kao

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

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 productiongrade-based system. To support further research, we release PolyNorm-Benchmark 1 , a multilingual data set covering a diverse range of text normalization phenomena.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2511.03080")
get_code_for_paper("2511.03080")
have("2511.03080")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2511.03080.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2511.03080.svg)](https://syntology.ai/paper/2511.03080)

Connect an agent — have() is free.