# Improving Performance of End-to-End ASR on Numeric Sequences

arXiv: https://arxiv.org/abs/1907.01372 · HTML: https://mlsanity.com/paper/1907.01372/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 17 of 17)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Transformer Based Deliberation for Two-Pass Speech Recognition](https://mlsanity.com/paper/2101.11577/) (2021)
- [Neural Inverse Text Normalization](https://mlsanity.com/paper/2102.06380/) (2021)
- [On Addressing Practical Challenges for RNN-Transducer](https://mlsanity.com/paper/2105.00858/) (2021)
- [Modular Hybrid Autoregressive Transducer](https://mlsanity.com/paper/2210.17049/) (2022)
- [Speech collage: code-switched audio generation by collaging monolingual corpora](https://mlsanity.com/paper/2309.15674/) (2023)
- [Language model fusion for streaming end to end speech recognition](https://mlsanity.com/paper/2104.04487/) (2021)
- [A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data](https://mlsanity.com/paper/2206.13240/) (2022)
- [Thutmose Tagger: Single-pass neural model for Inverse Text Normalization](https://mlsanity.com/paper/2208.00064/) (2022)
- [Text Generation with Speech Synthesis for ASR Data Augmentation](https://mlsanity.com/paper/2305.16333/) (2023)
- [An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR](https://mlsanity.com/paper/2503.08954/) (2025)
- [Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Model](https://mlsanity.com/paper/2202.08171/) (2022)
- [Decoupled Structure for Improved Adaptability of End-to-End Models](https://mlsanity.com/paper/2308.13345/) (2023)
- [Position-Invariant Truecasing with a Word-and-Character Hierarchical Recurrent Neural Network](https://mlsanity.com/paper/2108.11943/) (2021)
- [A Deliberation-based Joint Acoustic and Text Decoder](https://mlsanity.com/paper/2303.15293/) (2023)
- [End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data](https://mlsanity.com/paper/2311.17741/) (2023)
- [Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices](https://mlsanity.com/paper/2409.16469/) (2024)

## Abstract (arXiv)

Recognizing written domain numeric utterances (e.g. I need 1.25.) can be challenging for ASR systems, particularly when numeric sequences are not seen during training. This out-of-vocabulary (OOV) issue is addressed in conventional ASR systems by training part of the model on spoken domain utterances (e.g. I need one dollar and twenty five cents.), for which numeric sequences are composed of in-vocabulary numbers, and then using an FST verbalizer to denormalize the result. Unfortunately, conventional ASR models are not suitable for the low memory setting of on-device speech recognition. E2E models such as RNN-T are attractive for on-device ASR, as they fold the AM, PM and LM of a conventional model into one neural network. However, in the on-device setting the large memory footprint of an FST denormer makes spoken domain training more difficult. In this paper, we investigate techniques to improve E2E model performance on numeric data. We find that using a text-to-speech system to generate additional numeric training data, as well as using a small-footprint neural network to perform spoken-to-written domain denorming, yields improvement in several numeric classes. In the case of the longest numeric sequences, we see reduction of WER by up to a factor of 8.