# Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2505.00028 · HTML: https://mlsanity.com/paper/2505.00028/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension](https://mlsanity.com/paper/2411.13093/) (2024)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT](https://mlsanity.com/paper/2310.04673/) (2023)
- [SLM: Bridge the thin gap between speech and text foundation models](https://mlsanity.com/paper/2310.00230/) (2023)
- [Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model](https://mlsanity.com/paper/2501.07246/) (2025)
- [SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training](https://mlsanity.com/paper/2412.15649/) (2024)
- [Retrieval Augmented End-to-End Spoken Dialog Models](https://mlsanity.com/paper/2402.01828/) (2024)
- [WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models](https://mlsanity.com/paper/2502.14727/) (2025)
- [iRAG: Advancing RAG for Videos with an Incremental Approach](https://mlsanity.com/paper/2404.12309/) (2024)
- [Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications](https://mlsanity.com/paper/2501.02460/) (2025)

## Built on by (most cited first, 5 of 5)

- [Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency](https://mlsanity.com/paper/2604.04847/) (2026)
- [Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage](https://mlsanity.com/paper/2510.02044/) (2025)
- [MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.12928/) (2026)
- [From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding](https://mlsanity.com/paper/2606.16472/) (2026)
- [A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers](https://mlsanity.com/paper/2608.26194/) (2026)

## Abstract (arXiv)

End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such as emotion and speaker identity. However, these systems face key challenges, particularly in incorporating external knowledge, a capability commonly addressed by Retrieval-Augmented Generation (RAG) in text-based large language models (LLMs). The core difficulty lies in the modality gap between input speech and retrieved textual knowledge, which hinders effective integration of information. To address this issue, we propose a novel end-to-end RAG framework that directly retrieves relevant textual knowledge from speech queries. Experimental results demonstrate that our method significantly improves the performance of end-to-end S2S dialogue systems while achieving higher retrieval efficiency. Although the overall performance still lags behind the SOTA cascaded models, our framework offers a promising direction for enhancing knowledge integration in end-to-end S2S systems. Our code and dataset are released.