# ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction

arXiv: https://arxiv.org/abs/2412.03075 · HTML: https://mlsanity.com/paper/2412.03075/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model](https://mlsanity.com/paper/1910.10697/) (2019)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space](https://mlsanity.com/paper/2303.00456/) (2023)
- [BART based semantic correction for Mandarin automatic speech recognition system](https://mlsanity.com/paper/2104.05507/) (2021)
- [Chinese Spelling Correction as Rephrasing Language Model](https://mlsanity.com/paper/2308.08796/) (2023)
- [Familia: A Configurable Topic Modeling Framework for Industrial Text Engineering](https://mlsanity.com/paper/1808.03733/) (2018)

## Built on by (most cited first, 7 of 7)

- [Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2505.15957/) (2025)
- [Contextualized Token Discrimination for Speech Search Query Correction](https://mlsanity.com/paper/2509.04393/) (2025)
- [Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework](https://mlsanity.com/paper/2602.15377/) (2026)
- [Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition](https://mlsanity.com/paper/2603.04945/) (2026)
- [Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing](https://mlsanity.com/paper/2509.14263/) (2025)
- [From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs](https://mlsanity.com/paper/2512.19161/) (2025)
- [Proactive Dialogue Model with Intent Prediction](https://mlsanity.com/paper/2604.27379/) (2026)

## Abstract (arXiv)

Automatic speech Recognition (ASR) is a fundamental and important task in the field of speech and natural language processing. It is an inherent building block in many applications such as voice assistant, speech translation, etc. Despite the advancement of ASR technologies in recent years, it is still inevitable for modern ASR systems to have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc. Therefore, the error correction in ASR is crucial. Motivated by this, this paper studies ASR error correction in the Chinese language, which is one of the most popular languages and enjoys a large number of users in the world. We first create a benchmark dataset named ASR-EC that contains a wide spectrum of ASR errors generated by industry-grade ASR systems. To the best of our knowledge, it is the first Chinese ASR error correction benchmark. Then, inspired by the recent advances in large language models (LLMs), we investigate how to harness the power of LLMs to correct ASR errors. We apply LLMs to ASR error correction in three paradigms. The first paradigm is prompting, which is further categorized as zero-shot, few-shot, and multi-step. The second paradigm is finetuning, which finetunes LLMs with ASR error correction data. The third paradigm is multi-modal augmentation, which collectively utilizes the audio and ASR transcripts for error correction. Extensive experiments reveal that prompting is not effective for ASR error correction. Finetuning is effective only for a portion of LLMs. Multi-modal augmentation is the most effective method for error correction and achieves state-of-the-art performance.