mlsanityData to 7 Oct 2026

Retrieval-Augmented Speech Recognition Approach for Domain Challenges

arXiv 2502.15264 ↗First posted 21 Feb 2025cs.CL cs.SD eess.AScited by 2

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

Speech recognition systems often face challenges due to domain mismatch, particularly in real-world applications where domain-specific data is unavailable because of data accessibility and confidentiality constraints. Inspired by Retrieval-Augmented Generation (RAG) techniques for large language models (LLMs), this paper introduces a LLM-based retrieval-augmented speech recognition method that incorporates domain-specific textual data at the inference stage to enhance recognition performance. Rather than relying on domain-specific textual data during the training phase, our model is trained to learn how to utilize textual information provided in prompts for LLM decoder to improve speech recognition performance. Benefiting from the advantages of the RAG retrieval mechanism, our approach efficiently accesses locally available domain-specific documents, ensuring a convenient and effective process for solving domain mismatch problems. Experiments conducted on the CSJ database demonstrate that the proposed method significantly improves speech recognition accuracy and achieves state-of-the-art results on the CSJ dataset, even without relying on the full training data.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 27 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

25 of 27 references.

References · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2023Qwen Technical Reportcited by 3,273
  7. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  10. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  11. 2015Listen, Attend and Spellcited by 542
  12. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
13 more
  1. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  2. 2023AudioPaLM: A Large Language Model That Can Speak and Listencited by 333
  3. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 183
  4. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  5. 2023X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languagescited by 127
  6. 2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
  7. 2020Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capabilitycited by 63
  8. 2024SpeechVerse: A Large-scale Generalizable Audio Language Modelcited by 62
  9. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  10. 2023Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognitioncited by 48
  11. 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognitioncited by 30
  12. 2023Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognitioncited by 10
  13. 2024Improving Domain-Specific ASR with LLM-Generated Contextual Descriptionscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Zero-Shot Context-Aware ASR for Diverse Arabic Varietiescited by 0
  2. 2026From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition
  2. 2024Speech Retrieval-Augmented Generation without Automatic Speech Recognition
  3. 2024Retrieval Augmented Correction of Named Entity Speech Recognition Errors
  4. 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
  5. 2025Multi-task retriever fine-tuning for domain-specific and efficient RAG
  6. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  7. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  8. 2024R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation