Scale transform in speech analysis

In this paper, we study the scale transform of the spectral-envelope of spe ech utterances by different speakers. This study is motivated by the hypoth esis that the formant frequencies between different speakers are approximat ely related by a scaling constant for a given vowel. The scale transform ha s the fundamental property that the magnitude of the scale-transform of a f unction X(f) and its scaled version root alpha X(alpha f) are same, The met hods presented here are useful in reducing variations in acoustic features. We show that the F-ratio tests indicate better separability of vowels by u sing scale-transform based features than mel-transform based features. The data used in the comparison of the different features consist of 200 uttera nces of four vowels that are extracted from the TIMIT data base.