Talker-Recognition Procedure Based on Analysis of Variance

Abstract

This paper describes a talker‐recognition procedure that selects a small subset of features from a much larger body of data and bases recognition on this subset. The subset is chosen as those features having small variation between utterances of a given talker as compared to the variation among utterances of different talkers. This procedure is applied to materials consisting of quantized spectrographic information from a group of 10 talkers uttering 10 different words 7 times each. Features are formed as the average of the speech energy over certain rectangular areas on the spectrograms. Results are computed as a function of the number of features used and as a function of the size of the areas used to form the features. Although this paper treats only talker recognition, the recognition procedure is general and can be applied to other problems where it is desirable to use a simple method to select a few important features from a much larger set that can number several thousands.