徽州文书文本化语音识别技术应用研究

Research on the Textualization of Huizhou Documents Using Auto Speech Recognition

文章旨在探索语音识别技术应用于徽州文书文本化的可行性及其模式:采用实验研究法比较3种文本化方式的优劣,运用功能分析法探讨徽州文书文本化语音识别技术应用的潜在模式。研究发现:语音识别技术适用于徽州文书文本化工作,识别时间为手工录入的六分之一,识别率为80.22%,相较于OCR提升超过25%,并可同步实现语音建档及初步语义标注功能。文章提出应用语音识别技术进行徽州文书文本化的方法,具有一定的可行性且潜在应用模式多样,可为民间历史文献文本化工作提供参考。

This article aims to explore the feasibility of using Auto Speech Recognition to improve the textualization efficiency of Huizhou Documents and its potential application modes. Experiment study is applied to find out the advantages and disadvantages among three textualizing methods,then functional analysis is used for discussing the potential application modes of the textualization of Huizhou Documents using Auto Speech Recognition. Results show that Auto Speech Recognition is suitable for the textualization of Huizhou Documents.The recognition time is only 1/6 of the manual input,and the recognition rate reaches 80.22% which has been improved by more than 25% compared with OCR. Auto Speech Recognition can also realize the voice documentation and preliminary semantic annotation. This study indicates that it is feasible to apply Auto Speech Recognition to textualize Huizhou Documents, and there are various potential application modes, which is expected to constitute a reference for the digitalization of historical documents.