Segmentation of Arabic letters signal using Multiscale Principal Component analysis and Zero-Crossing Rate based on Malay speakers

摘要: In this paper, an investigation of segmentation method for Arabic letters signals spoken by Malay speakers, which is the main step further speech processing purpose identifying proper pronunciation performed will be discussed. Recording any corpus requires suitable environment in order to reduce noise but our application mobility most vital point recording. Hence, study, Multiscale Principal Component applied de-noise signal as a pre-step before employing Zero-Crossing Rate function that utilized segment actual voice signal. The outcome proposed first phase Speech Recognition under and uncontrolled conditions.