EXPLOITING FREQUENCY-SCALING INVARIANCEPROPERTIES OF THE SCALE TRANSFORM FORAUTOMATIC SPEECH RECOGNITION
作者单位：Indian Institute of Technology Kanpur INDIA AT＆T Labs-Research Florham Park NJ USA AT＆T Labs-Research Florham Park NJ USA
会议名称：《6～(th) International Conference on Spoken Language Processing》
会议日期：2000年
学科分类：0303[法学-社会学] 0501[文学-中国语言文学] 050102[文学-语言学及应用语言学] 03[法学] 030303[法学-人类学] 05[文学]
摘 要：正An experimental study of the application of scale-transform to improve the performance of speaker independent continuous speech recognition, is presented in this paper. Three major results are described. First, a comparison was made between the scale-transform based magnitude cepstrum coefficients （STCC） and mel-scale filter bank cepstrum coefficients （MFCC） on a telephone based connected digit recognition task. It was shown that