# End-to-End Speech Recognition Contextualization with Large Language Models

arXiv: https://arxiv.org/abs/2309.10917 · HTML: https://mlsanity.com/paper/2309.10917/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [Deep Shallow Fusion for RNN-T Personalization](https://mlsanity.com/paper/2011.07754/) (2020)
- [Contextual Adapters for Personalized Speech Recognition in Neural Transducers](https://mlsanity.com/paper/2205.13660/) (2022)
- [Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition](https://mlsanity.com/paper/2305.05271/) (2023)
- [Scaling ASR Improves Zero and Few Shot Learning](https://mlsanity.com/paper/2111.05948/) (2021)
- [Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition](https://mlsanity.com/paper/2306.00804/) (2023)
- [G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR](https://mlsanity.com/paper/1910.12612/) (2019)

## Built on by (most cited first, 22 of 22)

- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning](https://mlsanity.com/paper/2311.02248/) (2023)
- [Chain-of-Thought Prompting for Speech Translation](https://mlsanity.com/paper/2409.11538/) (2024)
- [Efficient Streaming LLM for Speech Recognition](https://mlsanity.com/paper/2410.03752/) (2024)
- [Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation](https://mlsanity.com/paper/2407.10303/) (2024)
- [DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding](https://mlsanity.com/paper/2406.09345/) (2024)
- [Contextualization of ASR with LLM using phonetic retrieval-based augmentation](https://mlsanity.com/paper/2409.15353/) (2024)
- [Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning](https://mlsanity.com/paper/2506.05671/) (2025)
- [LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.08597/) (2024)
- [Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval](https://mlsanity.com/paper/2411.00664/) (2024)
- [WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing](https://mlsanity.com/paper/2506.01263/) (2025)
- [SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation](https://mlsanity.com/paper/2505.03273/) (2025)
- [Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions](https://mlsanity.com/paper/2406.14701/) (2024)
- [Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words](https://mlsanity.com/paper/2408.08027/) (2024)
- [Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing](https://mlsanity.com/paper/2506.02012/) (2025)
- [Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems](https://mlsanity.com/paper/2506.06252/) (2025)
- [PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition](https://mlsanity.com/paper/2509.12647/) (2025)
- [A Neural Model for Contextual Biasing Score Learning and Filtering](https://mlsanity.com/paper/2510.23849/) (2025)
- [How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs](https://mlsanity.com/paper/2608.05759/) (2026)
- [Exploring the Feasibility of End-to-End Large Language Model as a Compiler](https://mlsanity.com/paper/2511.04132/) (2025)
- [Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models](https://mlsanity.com/paper/2606.25436/) (2026)
- [Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?](https://mlsanity.com/paper/2606.25444/) (2026)

## Abstract (arXiv)

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for contextualizing speech recognition models incorporating LLMs. Our approach casts speech recognition as a mixed-modal language modeling task based on a pretrained LLM. We provide audio features, along with optional text tokens for context, to train the system to complete transcriptions in a decoder-only fashion. As a result, the system is implicitly incentivized to learn how to leverage unstructured contextual information during training. Our empirical results demonstrate a significant improvement in performance, with a 6% WER reduction when additional textual context is provided. Moreover, we find that our method performs competitively and improve by 7.5% WER overall and 17% WER on rare words against a baseline contextualized RNN-T system that has been trained on more than twenty five times larger speech dataset. Overall, we demonstrate that by only adding a handful number of trainable parameters via adapters, we can unlock contextualized speech recognition capability for the pretrained LLM while keeping the same text-only input functionality.