论文部分内容阅读
作者考察了约60项有关语言自动识别器的研究,根据对这些文献全面深入的研究的结果,提出22条颇有见识的专门结论。这些结论对汉语自动识别器的研制同样是很有价值的。原文分三部份:第一部份扼要叙述语言过程的性质,介绍与语言自动识别有关的一些语言学研究领域;第二部份评述已发表的语言自动识别器研究报告,逐一介绍现有语言自动识别器的工作原理和特点;第三部份是结论。这里只就结论部份译出供参考。 1.机器的识别操作必须紧密地和人识别语言的方法相联系。
The author examines about 60 studies of automatic speech recognizers and, based on the results of a comprehensive and in-depth study of these documents, makes 22 very specific and expert conclusions. These conclusions are also valuable for the development of Chinese automatic recognizer. The original text is divided into three parts: The first part briefly describes the nature of the language process, introduces some linguistic research fields related to automatic language recognition; the second part reviews the published research reports on automatic speech recognizers, introducing the existing languages one by one Automatic recognizer works and features; The third part is the conclusion. Here only the conclusion part translated for reference. 1. The identification of machines must be closely linked to the way people recognize the language.