# RNN Approaches to Text Normalization: A Challenge

arXiv: https://arxiv.org/abs/1611.00068 · HTML: https://mlsanity.com/paper/1611.00068/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2016.

## Built on by (most cited first, 30 of 30)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [Automata-based constraints for language model decoding](https://mlsanity.com/paper/2407.08103/) (2024)
- [Neural Inverse Text Normalization](https://mlsanity.com/paper/2102.06380/) (2021)
- [Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems](https://mlsanity.com/paper/2104.07777/) (2021)
- [A Unified Transformer-based Framework for Duplex Text Normalization](https://mlsanity.com/paper/2108.09889/) (2021)
- [Transformer-based Models of Text Normalization for Speech Applications](https://mlsanity.com/paper/2202.00153/) (2022)
- [Thutmose Tagger: Single-pass neural model for Inverse Text Normalization](https://mlsanity.com/paper/2208.00064/) (2022)
- [Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition](https://mlsanity.com/paper/2210.15063/) (2022)
- [Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition](https://mlsanity.com/paper/2211.03721/) (2022)
- [A unified front-end framework for English text-to-speech synthesis](https://mlsanity.com/paper/2305.10666/) (2023)
- [Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech](https://mlsanity.com/paper/2209.02971/) (2022)
- [PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech](https://mlsanity.com/paper/2511.03080/) (2025)
- [An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer](https://mlsanity.com/paper/2203.16954/) (2022)
- [A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2206.04922/) (2022)
- [Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities](https://mlsanity.com/paper/2305.16407/) (2023)
- [Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text](https://mlsanity.com/paper/2208.10248/) (2022)
- [Multi-Task Learning for Front-End Text Processing in TTS](https://mlsanity.com/paper/2401.06321/) (2024)
- [FormalASR: End-to-End Spoken Chinese to Formal Text](https://mlsanity.com/paper/2605.19266/) (2026)
- [Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs](https://mlsanity.com/paper/2606.29534/) (2026)
- [Building Metadata Inference Using a Transducer Based Language Model](https://mlsanity.com/paper/2212.01964/) (2022)
- [Normalization of Lithuanian Text Using Regular Expressions](https://mlsanity.com/paper/2312.17660/) (2023)
- [Two Approaches to Diachronic Normalization of Polish Texts](https://mlsanity.com/paper/2402.01300/) (2024)
- [Positional Description for Numerical Normalization](https://mlsanity.com/paper/2408.12430/) (2024)
- [VietNormalizer: An Open-Source, Dependency-Free Python Library for Vietnamese Text Normalization in TTS and NLP Applications](https://mlsanity.com/paper/2603.04145/) (2026)
- [KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs](https://mlsanity.com/paper/2605.27984/) (2026)
- [CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation](https://mlsanity.com/paper/2606.24714/) (2026)
- [The Hidden Cost of Digits: Number Normalization and WER in ASR Systems](https://mlsanity.com/paper/2609.21084/) (2026)
- [THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer](https://mlsanity.com/paper/2609.30984/) (2026)

## Abstract (arXiv)

This paper presents a challenge to the community: given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function. We present a data set of general text where the normalizations were generated using an existing text normalization component of a text-to-speech system. This data set will be released open-source in the near future. We also present our own experiments with this data set with a variety of different RNN architectures. While some of the architectures do in fact produce very good results when measured in terms of overall accuracy, the errors that are produced are problematic, since they would convey completely the wrong message if such a system were deployed in a speech application. On the other hand, we show that a simple FST-based filter can mitigate those errors, and achieve a level of accuracy not achievable by the RNN alone. Though our conclusions are largely negative on this point, we are actually not arguing that the text normalization problem is intractable using an pure RNN approach, merely that it is not going to be something that can be solved merely by having huge amounts of annotated text data and feeding that to a general RNN model. And when we open-source our data, we will be providing a novel data set for sequence-to-sequence modeling in the hopes that the the community can find better solutions. The data used in this work have been released and are available at: https://github.com/rwsproat/text-normalization-data