mlsanityData to 14 Oct 2026

Retrieval Augmented Generation based context discovery for ASR

arXiv 2509.19567 ↗First posted 23 Sep 2025cs.CL eess.AScited by 1

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

Abstract (arXiv)

This work investigates retrieval augmented generation as an efficient strategy for automatic context discovery in context-aware Automatic Speech Recognition (ASR) system, in order to improve transcription accuracy in the presence of rare or out-of-vocabulary terms. However, identifying the right context automatically remains an open challenge. This work proposes an efficient embedding-based retrieval approach for automatic context discovery in ASR. To contextualize its effectiveness, two alternatives based on large language models (LLMs) are also evaluated: (1) large language model (LLM)-based context generation via prompting, and (2) post-recognition transcript correction using LLMs. Experiments on the TED-LIUMv3, Earnings21 and SPGISpeech demonstrate that the proposed approach reduces WER by up to 17% (percentage difference) relative to using no-context, while the oracle context results in a reduction of up to 24.1%.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 23 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

15 of 23 references.

References · 15

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  4. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 226
  5. 2020Contextual RNN-T For Open Domain ASRcited by 85
  6. 2021SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitioncited by 78
  7. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
  8. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  9. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  10. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  11. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  12. 2023Retrieve and Copy: Scaling ASR Personalization to Large Catalogscited by 7
3 more
  1. 2024Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASRcited by 5
  2. 2024Locality enhanced dynamic biasing and sampling strategies for contextual ASRcited by 3
  3. 2024Text Injection for Neural Contextual Biasingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026JSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASRcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems
  2. 2024Speech Retrieval-Augmented Generation without Automatic Speech Recognition
  3. 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
  4. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
  5. 2025Retrieval-Augmented Speech Recognition Approach for Domain Challenges
  6. 2024Context Awareness Gate For Retrieval Augmented Generation
  7. 2024Retrieval Augmented Correction of Named Entity Speech Recognition Errors
  8. 2026Cached LLM Probability Retrieval for Speech Recognition ↗