# Improving Contextual ASR via Multi-grained Fusion with Large Language Models

arXiv: https://arxiv.org/abs/2507.12252 · HTML: https://mlsanity.com/paper/2507.12252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 16 Jul 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition](https://mlsanity.com/paper/2306.16007/) (2023)
- [Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network](https://mlsanity.com/paper/2305.12493/) (2023)
- [Contextual Speech Recognition with Difficult Negative Training Examples](https://mlsanity.com/paper/1810.12170/) (2018)
- [It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition](https://mlsanity.com/paper/2402.05457/) (2024)
- [Can Contextual Biasing Remain Effective with Whisper and GPT-2?](https://mlsanity.com/paper/2306.01942/) (2023)
- [AISHELL-NER: Named Entity Recognition from Chinese Speech](https://mlsanity.com/paper/2202.08533/) (2022)
- [SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus](https://mlsanity.com/paper/2309.05396/) (2023)
- [Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition](https://mlsanity.com/paper/2305.05271/) (2023)
- [Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition](https://mlsanity.com/paper/2207.00857/) (2022)
- [CopyNE: Better Contextual ASR by Copying Named Entities](https://mlsanity.com/paper/2305.12839/) (2023)
- [Contextualized Automatic Speech Recognition with Dynamic Vocabulary](https://mlsanity.com/paper/2405.13344/) (2024)
- [Retrieve and Copy: Scaling ASR Personalization to Large Catalogs](https://mlsanity.com/paper/2311.08402/) (2023)
- [LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2401.06390/) (2024)

## Built on by (most cited first, 1 of 1)

- [Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults](https://mlsanity.com/paper/2508.08684/) (2025)

## Abstract (arXiv)

While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities. Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of keyword phrases. However, these methods operate at different granularities and have their own limitations. In this paper, we propose a novel multi-grained fusion approach that jointly leverages the strengths of both token-level and phrase-level fusion with Large Language Models (LLMs). Our approach incorporates a late-fusion strategy that elegantly combines ASR's acoustic information with LLM's rich contextual knowledge, balancing fine-grained token precision with holistic phrase-level understanding. Experiments on Chinese and English datasets demonstrate that our approach achieves state-of-the-art performance on keyword-related metrics while preserving high accuracy on non-keyword text. Ablation studies further confirm that the token-level and phrase-level components both contribute significantly to the performance gains, complementing each other in our joint multi-grained framework. The code and models will be publicly available at https://github.com/.