用轻量提示增强模型对生僻词的识别能力
Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems
- 通过提示聚焦机制判断何时关注实体词
- 在小/大实体列表上分别降低30.7%和18.0%的实体错误率
- 无需修改结构，适合部署在资源受限场景
端到端语音识别（ASR）虽有显著进展，但仍难以准确识别罕见及领域特定实体。本文提出一种简单高效的基于提示的上下文增强方法，利用统一多任务学习框架提升识别精度。该方法包含两个核心组件：一个提示偏置模型，用于判断何时应聚焦于提示中的实体；以及一个实体过滤机制，可高效剔除无关实体。在自研领域数据集上，针对小实体列表和大实体列表，相比浅融合基线模型，实体词错误率分别相对降低30.7%和18.0%。该方法优势在于无需改变模型结构，具备轻量化与高效率特点。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。