期刊名称:International Journal of Hybrid Information Technology
印刷版ISSN:1738-9968
出版年度:2011
卷号:4
期号:4
出版社:SERSC
摘要:The paper presents successful experiments on combining twospeaker recognition methods into a hybrid system. The first branch ofrecognition is an innovative approach based on discrete wavelet-Fouriertransform. The second one is classic, based on HTK and classificationinto voice and unvoice segments. The hybrid solution outp erforms bothon a small test set. Further tests of this soultion will be conducted andreported