Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems
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_ | 1866908774681280512 |
|---|---|
| author | Ren, Bo Shi, Yu Li, Jinyu |
| author_facet | Ren, Bo Shi, Yu Li, Jinyu |
| contents | End-to-End Automatic Speech Recognition (ASR) has advanced significantly yet still struggles with rare and domain-specific entities. This paper introduces a simple yet efficient prompt-based biasing technique for contextualized ASR, enhancing recognition accuracy by leverage a unified multitask learning framework. The approach comprises two key components: a prompt biasing model which is trained to determine when to focus on entities in prompt, and a entity filtering mechanism which efficiently filters out irrelevant entities. Our method significantly enhances ASR accuracy on entities, achieving a relative 30.7% and 18.0% reduction in Entity Word Error Rate compared to the baseline model with shallow fusion on in-house domain dataset with small and large entity lists, respectively. The primary advantage of this method lies in its efficiency and simplicity without any structure change, making it lightweight and highly efficient. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems Ren, Bo Shi, Yu Li, Jinyu Audio and Speech Processing Computation and Language End-to-End Automatic Speech Recognition (ASR) has advanced significantly yet still struggles with rare and domain-specific entities. This paper introduces a simple yet efficient prompt-based biasing technique for contextualized ASR, enhancing recognition accuracy by leverage a unified multitask learning framework. The approach comprises two key components: a prompt biasing model which is trained to determine when to focus on entities in prompt, and a entity filtering mechanism which efficiently filters out irrelevant entities. Our method significantly enhances ASR accuracy on entities, achieving a relative 30.7% and 18.0% reduction in Entity Word Error Rate compared to the baseline model with shallow fusion on in-house domain dataset with small and large entity lists, respectively. The primary advantage of this method lies in its efficiency and simplicity without any structure change, making it lightweight and highly efficient. |
| title | Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2506.06252 |