# THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer

arXiv: https://arxiv.org/abs/2609.30984 · HTML: https://mlsanity.com/paper/2609.30984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [RNN Approaches to Text Normalization: A Challenge](https://mlsanity.com/paper/1611.00068/) (2016)
- [NeMo Inverse Text Normalization: From Development To Production](https://mlsanity.com/paper/2104.05055/) (2021)
- [Neural Inverse Text Normalization](https://mlsanity.com/paper/2102.06380/) (2021)
- [Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization](https://mlsanity.com/paper/2203.15917/) (2022)
- [PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech](https://mlsanity.com/paper/2511.03080/) (2025)

## Abstract (arXiv)

Text-to-speech needs written text in spoken form, and speech recognition output needs the reverse. For Khmer, neither direction has a maintained open-source tool, and the script makes both harder: words are not separated by spaces, and number words occur inside ordinary words. We present Tha, a Khmer text normalization and inverse text normalization toolkit built from weighted finite-state transducers. It segments and classifies a whole line in one shortest-path search, and a second transducer rejects token boundaries inside a Khmer syllable. On Google's Khmer test suite, Tha agrees with the reference on all 274 cardinals up to one spelling variant, and on 2,906 real TTS prompts, 153 of the 158 sentences it rewrites are correct. Tha is open source under the Apache 2.0 license.