# Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction

arXiv: https://arxiv.org/abs/2408.16180 · HTML: https://mlsanity.com/paper/2408.16180/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 29 Aug 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/1908.10992/) (2019)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition](https://mlsanity.com/paper/2310.06434/) (2023)
- [Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM](https://mlsanity.com/paper/1706.02737/) (2017)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [Distilling the Knowledge of BERT for Sequence-to-Sequence ASR](https://mlsanity.com/paper/2008.03822/) (2020)

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

- [When Large Language Models Meet Speech: A Survey on Integration Approaches](https://mlsanity.com/paper/2502.19548/) (2025)
- [LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context](https://mlsanity.com/paper/2505.17410/) (2025)
- [LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families](https://mlsanity.com/paper/2603.20042/) (2026)
- [Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models](https://mlsanity.com/paper/2603.25750/) (2026)

## Abstract (arXiv)

With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how LLM-based GER can enhance and expand the capabilities of Japanese language processing, presenting the first GER benchmark for Japanese ASR with 0.9-2.6k text utterances. We also introduce a new multi-pass augmented generative error correction (MPA GER) by integrating multiple system hypotheses on the input side with corrections from multiple LLMs on the output side and then merging them. To the best of our knowledge, this is the first investigation of the use of LLMs for Japanese GER, which involves second-pass language modeling on the output transcriptions generated by the ASR system (e.g., N-best hypotheses). Our experiments demonstrated performance improvement in the proposed methods of ASR quality and generalization both in SPREDS-U1-ja and CSJ data.