EVALUATION OF VOWEL NORMALIZATION PROCEDURES
EVALUATION OF VOWEL NORMALIZATION PROCEDURES
复制标题
DOI：
10.1121/1.383734
复制
发表时间：
1980-01-01
影响因子：
2.4
通讯作者：
DISNER, SF
中科院分区：
文献类型：
--
作者：
DISNER, SF
元音标准化过程通常基于它们如何有效地将单个测试数据集的元音分成与该人类语言的语音类别相对应的不同组来评估。这里提出了一种可量化的评估方法，根据从数据中去除了多少总体方差。这种评估方法适用于元音或6个不同的日耳曼语言，根据4个不同的程序进行规范化。1号规范化过程对所有语言都是最有效的。其中一些最成功的规范化将过程性工件引入数据，并改变了不同语言或方言之间元音的相对质量。如果元音系统不同，则将一种语言的规范化元音与另一种语言的（单独）规范化元音进行比较是无效的。这些程序工件的外观的一些原因进行了讨论。
Vowel normalization procedures are commonly evaluated on the basis of how effectively they separate the vowels of a single test data set into distinct groups, corresponding to the phonetic categories of that human language. A quantifiable method of evaluation is proposed here, based on how much of the overall variance is removed from the data. This evaluation method is applied to the vowels or 6 different Germanic languages which were normalized according to 4 different procedures. No 1 normalization procedure is the most effective for all languages. Some of the most successful of these normalizations introduce procedural artifacts into the data, and the relative quality of vowels across languages or dialects is altered. Comparisons of the normalized vowels of 1 language with the (separately) normalized vowels of another language are not valid if the vowel systems are different. Some reasons for the appearance of these procedural artifacts are discussed.