# Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices

arXiv: https://arxiv.org/abs/2409.16469 · HTML: https://mlsanity.com/paper/2409.16469/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- [Class LM and word mapping for contextual biasing in End-to-End ASR](https://mlsanity.com/paper/2007.05609/) (2020)
- [End-to-end contextual speech recognition using class language models and a token passing decoder](https://mlsanity.com/paper/1812.02142/) (2018)
- [Improving Performance of End-to-End ASR on Numeric Sequences](https://mlsanity.com/paper/1907.01372/) (2019)
- [Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems](https://mlsanity.com/paper/2203.00888/) (2022)
- [Feedback-Based Self-Learning in Large-Scale Conversational AI Agents](https://mlsanity.com/paper/1911.02557/) (2019)
- [Improving Rare Word Recognition with LM-aware MWER Training](https://mlsanity.com/paper/2204.07553/) (2022)
- [G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR](https://mlsanity.com/paper/1910.12612/) (2019)
- [A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems](https://mlsanity.com/paper/2108.07493/) (2021)
- [Mondegreen: A Post-Processing Solution to Speech Recognition Error Correction for Voice Search Queries](https://mlsanity.com/paper/2105.09930/) (2021)
- [SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings](https://mlsanity.com/paper/2306.02317/) (2023)

## Built on by (most cited first, 1 of 1)

- [SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models](https://mlsanity.com/paper/2507.19361/) (2025)

## Abstract (arXiv)

For end-to-end Automatic Speech Recognition (ASR) models, recognizing personal or rare phrases can be hard. A promising way to improve accuracy is through spelling correction (or rewriting) of the ASR lattice, where potentially misrecognized phrases are replaced with acoustically similar and contextually relevant alternatives. However, rewriting is challenging for ASR models trained with connectionist temporal classification (CTC) due to noisy hypotheses produced by a non-autoregressive, context-independent beam search. We present a finite-state transducer (FST) technique for rewriting wordpiece lattices generated by Transformer-based CTC models. Our algorithm performs grapheme-to-phoneme (G2P) conversion directly from wordpieces into phonemes, avoiding explicit word representations and exploiting the richness of the CTC lattice. Our approach requires no retraining or modification of the ASR model. We achieved up to a 15.2% relative reduction in sentence error rate (SER) on a test set with contextually relevant entities.