# FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2105.03842 · HTML: https://mlsanity.com/paper/2105.03842/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow](https://mlsanity.com/paper/1909.02480/) (2019)
- [Aligned Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2004.01655/) (2020)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior](https://mlsanity.com/paper/1908.07181/) (2019)
- [Felix: Flexible Text Editing Through Tagging and Insertion](https://mlsanity.com/paper/2003.10687/) (2020)
- [Deliberation Model Based Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/2003.07962/) (2020)
- [Semi-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1808.08583/) (2018)
- [ASR Error Correction and Domain Adaptation Using Machine Translation](https://mlsanity.com/paper/2003.07692/) (2020)
- [Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1911.09320/) (2019)
- [On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification](https://mlsanity.com/paper/2004.12617/) (2020)
- [Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input](https://mlsanity.com/paper/1812.09664/) (2018)
- [Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1911.08717/) (2019)
- [A Study of Non-autoregressive Model for Sequence Generation](https://mlsanity.com/paper/2004.10454/) (2020)
- [Transformer Based Deliberation for Two-Pass Speech Recognition](https://mlsanity.com/paper/2101.11577/) (2021)
- [Hint-Based Training for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/1909.06708/) (2019)
- [Improving Readability for Automatic Speech Recognition Transcription](https://mlsanity.com/paper/2004.04438/) (2020)

## Built on by (most cited first, 30 of 43)

- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition](https://mlsanity.com/paper/2109.14420/) (2021)
- [GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators](https://mlsanity.com/paper/2402.06894/) (2024)
- [Resilience of Large Language Models for Noisy Instructions](https://mlsanity.com/paper/2404.09754/) (2024)
- [Error Correction in ASR using Sequence-to-Sequence Models](https://mlsanity.com/paper/2202.01157/) (2022)
- [Non-autoregressive Generative Models for Reranking Recommendation](https://mlsanity.com/paper/2402.06871/) (2024)
- [Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems](https://mlsanity.com/paper/2203.00888/) (2022)
- [Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction](https://mlsanity.com/paper/2211.13252/) (2022)
- [SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition](https://mlsanity.com/paper/2212.01039/) (2022)
- [RED-ACE: Robust Error Detection for ASR using Confidence Embeddings](https://mlsanity.com/paper/2203.07172/) (2022)
- [Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling](https://mlsanity.com/paper/2205.12986/) (2022)
- [Improving Seq2Seq Grammatical Error Correction via Decoding Interventions](https://mlsanity.com/paper/2310.14534/) (2023)
- [MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction](https://mlsanity.com/paper/2401.13260/) (2024)
- [A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models](https://mlsanity.com/paper/2410.04027/) (2024)
- [Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction](https://mlsanity.com/paper/2505.24347/) (2025)
- [Decoupling recognition and transcription in Mandarin ASR](https://mlsanity.com/paper/2108.01129/) (2021)
- [Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejection](https://mlsanity.com/paper/2201.03313/) (2022)
- [ASR Error Correction with Constrained Decoding on Operation Prediction](https://mlsanity.com/paper/2208.04641/) (2022)
- [Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM](https://mlsanity.com/paper/2209.04062/) (2022)
- [SAPIEN: Affective Virtual Agents Powered by Large Language Models](https://mlsanity.com/paper/2308.03022/) (2023)
- [Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline](https://mlsanity.com/paper/2401.14625/) (2024)
- [DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition](https://mlsanity.com/paper/2403.17645/) (2024)
- [PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction](https://mlsanity.com/paper/2302.05040/) (2023)
- [DiaCorrect: Error Correction Back-end For Speaker Diarization](https://mlsanity.com/paper/2309.08377/) (2023)
- [Robust ASR Error Correction with Conservative Data Filtering](https://mlsanity.com/paper/2407.13300/) (2024)
- [Masked Audio Text Encoders are Effective Multi-Modal Rescorers](https://mlsanity.com/paper/2305.07677/) (2023)
- [UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction](https://mlsanity.com/paper/2401.05689/) (2024)
- [Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition](https://mlsanity.com/paper/2407.12817/) (2024)
- [Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition](https://mlsanity.com/paper/2510.19471/) (2025)

## Abstract (arXiv)

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR outputs. Previous works usually use a sequence-to-sequence model to correct an ASR output sentence autoregressively, which causes large latency and cannot be deployed in online ASR services. A straightforward solution to reduce latency, inspired by non-autoregressive (NAR) neural machine translation, is to use an NAR sequence generation model for ASR error correction, which, however, comes at the cost of significantly increased ASR error rate. In this paper, observing distinctive error patterns and correction operations (i.e., insertion, deletion, and substitution) in ASR, we propose FastCorrect, a novel NAR error correction model based on edit alignment. In training, FastCorrect aligns each source token from an ASR output sentence to the target tokens from the corresponding ground-truth sentence based on the edit distance between the source and target sentences, and extracts the number of target tokens corresponding to each source token during edition/correction, which is then used to train a length predictor and to adjust the source tokens to match the length of the target sentence for parallel generation. In inference, the token number predicted by the length predictor is used to adjust the source tokens for target sequence generation. Experiments on the public AISHELL-1 dataset and an internal industrial-scale ASR dataset show the effectiveness of FastCorrect for ASR error correction: 1) it speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model; and 2) it outperforms the popular NAR models adopted in neural machine translation and text edition by a large margin.