Improving children s speech recognition under mismatched condition using artificial band width extension

Abstract

Children 8482 s speech production system distinguishes itself from the adults 8482 by shorter vocal tract length and higher pitch value Due to shorter vocal tract length formant frequency values shift to higherband 3400 8000 Hz region The higher pitch value results in relatively more fluctuations in the spectrum compared to adults Narrowband NB 300 3400 Hz automatic speech recognition ASR performance of children 8482 s speech degrades significantly due to loss of information in higher band T