# Tag and correct: high precision post-editing approach to correction of speech recognition errors

arXiv: https://arxiv.org/abs/2406.07589 · HTML: https://mlsanity.com/paper/2406.07589/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [Spanish Pre-trained BERT Model and Evaluation Data](https://mlsanity.com/paper/2308.02976/) (2023)
- [Achieving Human Parity in Conversational Speech Recognition](https://mlsanity.com/paper/1610.05256/) (2016)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition](https://mlsanity.com/paper/2105.03842/) (2021)
- [Toward domain-invariant speech recognition via large scale training](https://mlsanity.com/paper/1808.05312/) (2018)
- [Open Challenge for Correcting Errors of Speech Recognition Systems](https://mlsanity.com/paper/2001.03041/) (2020)

## Abstract (arXiv)

This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recognition) hypothesis word by word and a corrector module that applies corrections returned by the tagger. The proposed solution is applicable to any ASR system, regardless of its architecture, and provides high-precision control over errors being corrected. This is especially crucial in production environments, where avoiding the introduction of new mistakes by the error correction model may be more important than the net gain in overall results. The results show that the performance of the proposed error correction models is comparable with previous approaches while requiring much smaller resources to train, which makes it suitable for industrial applications, where both inference latency and training times are critical factors that limit the use of other techniques.