# Connecting Speech Encoder and Large Language Model for ASR

arXiv: https://arxiv.org/abs/2309.13963 · HTML: https://mlsanity.com/paper/2309.13963/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 38 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (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)
- [PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation](https://mlsanity.com/paper/2104.12369/) (2021)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning](https://mlsanity.com/paper/2308.11276/) (2023)

## Built on by (most cited first, 30 of 80)

- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix](https://mlsanity.com/paper/2505.13032/) (2025)
- [video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models](https://mlsanity.com/paper/2406.15704/) (2024)
- [An Embarrassingly Simple Approach for LLM with Strong ASR Capacity](https://mlsanity.com/paper/2402.08846/) (2024)
- [LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis](https://mlsanity.com/paper/2505.02625/) (2025)
- [Language Model Can Listen While Speaking](https://mlsanity.com/paper/2408.02622/) (2024)
- [Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model](https://mlsanity.com/paper/2501.07246/) (2025)
- [AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs](https://mlsanity.com/paper/2311.06753/) (2023)
- [VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation](https://mlsanity.com/paper/2502.13508/) (2025)
- [Large Language Models are Strong Audio-Visual Speech Recognition Learners](https://mlsanity.com/paper/2409.12319/) (2024)
- [LLMs Meet Multimodal Generation and Editing: A Survey](https://mlsanity.com/paper/2405.19334/) (2024)
- [COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning](https://mlsanity.com/paper/2311.02248/) (2023)
- [Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?](https://mlsanity.com/paper/2402.12025/) (2024)
- [Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models](https://mlsanity.com/paper/2310.05863/) (2023)
- [Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning](https://mlsanity.com/paper/2409.19510/) (2024)
- [BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5](https://mlsanity.com/paper/2406.19954/) (2024)
- [MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens](https://mlsanity.com/paper/2503.11315/) (2025)
- [CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion](https://mlsanity.com/paper/2402.05889/) (2024)
- [SSR: Alignment-Aware Modality Connector for Speech Language Models](https://mlsanity.com/paper/2410.00168/) (2024)
- [SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning](https://mlsanity.com/paper/2504.09081/) (2025)
- [Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation](https://mlsanity.com/paper/2409.16644/) (2024)
- [Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs](https://mlsanity.com/paper/2503.06362/) (2025)
- [Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition](https://mlsanity.com/paper/2312.03668/) (2023)
- [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)
- [Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach](https://mlsanity.com/paper/2505.14336/) (2025)
- [UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions](https://mlsanity.com/paper/2310.02973/) (2023)
- [Investigating Decoder-only Large Language Models for Speech-to-text Translation](https://mlsanity.com/paper/2407.03169/) (2024)

## Abstract (arXiv)

The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a speech encoder with an LLM. This paper presents a comparative study of three commonly used structures as connectors, including fully connected layers, multi-head cross-attention, and Q-Former. Speech encoders from the Whisper model series as well as LLMs from the Vicuna model series with different model sizes were studied. Experiments were performed on the commonly used LibriSpeech, Common Voice, and GigaSpeech datasets, where the LLMs with Q-Formers demonstrated consistent and considerable word error rate (WER) reductions over LLMs with other connector structures. Q-Former-based LLMs can generalise well to out-of-domain datasets, where 12% relative WER reductions over the Whisper baseline ASR model were achieved on the Eval2000 test set without using any in-domain training data from Switchboard. Moreover, a novel segment-level Q-Former is proposed to enable LLMs to recognise speech segments with a duration exceeding the limitation of the encoders, which results in 17% relative WER reductions over other connector structures on 90-second-long speech data.