用极小内存实现海量关键词的快速语音检索
Massive Open-Vocabulary Keyword Spotting
- 采用压缩特征存储技术，内存占用仅为基线1/128
- 支持百万级关键词库，识别准确率接近无损方案
- 无需微调模型，跨语言关键词检索仍有效
自动语音识别系统在处理训练数据中罕见的专业术语时表现不佳。开放词汇关键词检测结合上下文偏置可缓解此问题，但现有系统仅能处理数百个关键词，否则成为性能瓶颈。我们提出一种新系统，将特征存储内存降低至可比基线的1/128，可在不微调语音识别模型的前提下，支持大规模关键词库的开放词汇检索，即使在训练中未见的语言上也能达到与无损方案相当的实体召回率。
原文摘要 · Abstract (English)
Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology. Open-vocabulary keyword spotting, combined with contextual biasing, has been shown to mitigate this issue. However, existing systems can only handle glossaries of a few hundred terms without becoming an infeasible bottleneck. We propose a system that stores features with a memory footprint up to 128 times smaller than a comparable baseline and allows users to process massive databases while remaining open-vocabulary. Without fine-tuning the speech recognition model, our system achieves a comparable entity recall as uncompressed solutions, even in languages not seen during training.
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。