Retrieval Augmented Generation based context discovery for ASR
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909913121292288 |
|---|---|
| author | Siskos, Dimitrios Papadopoulos, Stavros Parada, Pablo Peso Zhang, Jisi Saravanan, Karthikeyan Drosou, Anastasios |
| author_facet | Siskos, Dimitrios Papadopoulos, Stavros Parada, Pablo Peso Zhang, Jisi Saravanan, Karthikeyan Drosou, Anastasios |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19567 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval Augmented Generation based context discovery for ASR Siskos, Dimitrios Papadopoulos, Stavros Parada, Pablo Peso Zhang, Jisi Saravanan, Karthikeyan Drosou, Anastasios Computation and Language Audio and Speech Processing 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%. |
| title | Retrieval Augmented Generation based context discovery for ASR |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.19567 |