# SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings

arXiv: https://arxiv.org/abs/2306.02317 · HTML: https://mlsanity.com/paper/2306.02317/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 4 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [Deep Shallow Fusion for RNN-T Personalization](https://mlsanity.com/paper/2011.07754/) (2020)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model](https://mlsanity.com/paper/1910.10697/) (2019)
- [Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities](https://mlsanity.com/paper/1912.09251/) (2019)
- [Personalization Strategies for End-to-End Speech Recognition Systems](https://mlsanity.com/paper/2102.07739/) (2021)
- [Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems](https://mlsanity.com/paper/2203.00888/) (2022)
- [Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model](https://mlsanity.com/paper/2209.01250/) (2022)
- [Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer](https://mlsanity.com/paper/2301.06735/) (2023)
- [A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems](https://mlsanity.com/paper/2108.07493/) (2021)
- [UserLibri: A Dataset for ASR Personalization Using Only Text](https://mlsanity.com/paper/2207.00706/) (2022)
- [A Toolbox for Construction and Analysis of Speech Datasets](https://mlsanity.com/paper/2104.04896/) (2021)

## Built on by (most cited first, 4 of 4)

- [Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR](https://mlsanity.com/paper/2404.10180/) (2024)
- [Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices](https://mlsanity.com/paper/2409.16469/) (2024)
- [Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization](https://mlsanity.com/paper/2309.17267/) (2023)
- [High-precision Voice Search Query Correction via Retrievable Speech-text Embedings](https://mlsanity.com/paper/2401.04235/) (2024)

## Abstract (arXiv)

Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval mechanisms, usually based on minimum edit distance between fragments of ASR hypothesis and user phrases. However, the edit-distance approach is slow, non-trainable, and may have low recall as it relies only on common letters. We propose: 1) a novel algorithm for candidate retrieval, based on misspelled n-gram mappings, which gives up to 90% recall with just the top 10 candidates on Spoken Wikipedia; 2) a non-autoregressive neural model based on BERT architecture, where the initial transcript and ten candidates are combined into one input. The experiments on Spoken Wikipedia show 21.4% word error rate improvement compared to a baseline ASR system.