Identification of Voicing Assimilation From Children’s Speech

Abstract

In this paper, an attempt has been made for the automatic identification of the voicing assimilation or harmony process. In these processes the voiced sounds are replaced by unvoiced sounds and vice versa. The phonological processes appear in the children represent the age wise speech learning ability, where the processes start to disappear as children grow. Speech Language Pathologists (SLPs) analyse these processes to evaluate the learning ability of the children. The pitch is present in voiced speech and absent in unvoiced region of speech. This gives the clear view of the assimilation; hence pitch is explored for the identification of voicing assimilation. Features extracted from the test words (mispronounced words) are compared with the reference/correct words using Dynamic Time Warping (DTW) and region of mispronunciation is identified from the properties of DTW curve. The highest accuracy of identifying voicing assimilation achieved using pitch feature is 88%. © INDIACom-2017.