A SPEECH RECOGNITION SYSTEM WITH ADAPTATION TO SPEECH RATE AND VOLUME,

被引：0

作者：

HINRICHS O

GONSCHOREK J

机构：

来源：

| 1971年 / 24卷 / 04期

关键词：

NO-TERMS;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Adaptation to the speech rate is made by segmentation of the speech signal in '%'voiced'%' and '%'unvoiced'%' periods, while adaptation to the speech volume is made by using a variable threshold for quantizing the spectrum of the signal. The vocabulary used for recognition consists of the 10 German numerals and the instructions '%'plus'%', '%'minus'%', '%'start'%' and '%'Loeschen'%'. For testing the speech recognition system the vocabulary was spoken by 50 male and 50 female speakers. The results of the experiments are presented.

引用

页码：177 / 182