Retrieval Augmented Generation based context discovery for ASR

Siskos Dimitrios, Stavros Papadopoulos, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan, Anastasios Drosou


Abstract
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%.
Anthology ID:
2025.findings-emnlp.768
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14247–14254
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.768/
DOI:
Bibkey:
Cite (ACL):
Siskos Dimitrios, Stavros Papadopoulos, Pablo Peso Parada, Jisi Zhang, Karthikeyan Saravanan, and Anastasios Drosou. 2025. Retrieval Augmented Generation based context discovery for ASR. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 14247–14254, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Retrieval Augmented Generation based context discovery for ASR (Dimitrios et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.768.pdf
Checklist:
 2025.findings-emnlp.768.checklist.pdf