# Full-text Error Correction for Chinese Speech Recognition with Large Language Model

arXiv: https://arxiv.org/abs/2409.07790 · HTML: https://mlsanity.com/paper/2409.07790/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 12 Sep 2024.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Deliberation Model Based Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/2003.07962/) (2020)
- [N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space](https://mlsanity.com/paper/2303.00456/) (2023)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [Deep-FSMN for Large Vocabulary Continuous Speech Recognition](https://mlsanity.com/paper/1803.05030/) (2018)
- [FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition](https://mlsanity.com/paper/2109.14420/) (2021)
- [Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection](https://mlsanity.com/paper/2003.01309/) (2020)
- [Multi-task Language Modeling for Improving Speech Recognition of Rare Words](https://mlsanity.com/paper/2011.11715/) (2020)
- [Improving Deliberation by Text-Only and Semi-Supervised Training](https://mlsanity.com/paper/2206.14716/) (2022)
- [Generative error correction for code-switching speech recognition using large language models](https://mlsanity.com/paper/2310.13013/) (2023)
- [Scaling Up Deliberation for Multilingual ASR](https://mlsanity.com/paper/2210.05785/) (2022)

## Built on by (most cited first, 3 of 3)

- [CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese](https://mlsanity.com/paper/2511.04139/) (2025)
- [Chain of Correction for Full-text Speech Recognition with Large Language Models](https://mlsanity.com/paper/2504.01519/) (2025)
- [Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing](https://mlsanity.com/paper/2509.14263/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from short-duration speech recordings, which are the predominant form of speech data for supervised ASR training. This paper investigates the effectiveness of LLMs for error correction in full-text generated by ASR systems from longer speech recordings, such as transcripts from podcasts, news broadcasts, and meetings. First, we develop a Chinese dataset for full-text error correction, named ChFT, utilizing a pipeline that involves text-to-speech synthesis, ASR, and error-correction pair extractor. This dataset enables us to correct errors across contexts, including both full-text and segment, and to address a broader range of error types, such as punctuation restoration and inverse text normalization, thus making the correction process comprehensive. Second, we fine-tune a pre-trained LLM on the constructed dataset using a diverse set of prompts and target formats, and evaluate its performance on full-text error correction. Specifically, we design prompts based on full-text and segment, considering various output formats, such as directly corrected text and JSON-based error-correction pairs. Through various test settings, including homogeneous, up-to-date, and hard test sets, we find that the fine-tuned LLMs perform well in the full-text setting with different prompts, each presenting its own strengths and weaknesses. This establishes a promising baseline for further research. The dataset is available on the website.