These articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.
Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.
Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.
International Journal of Creative Computing (1 paper in press)
A Creative Application of Wavelet Transform and Kalman Filter for Children Proof-reading and Continuous Speech Tracking in Online Stories and TV Programs by Wasiq Khan, Ping Jiang, Pauline Chan, Muhammad Bilal Abstract: Time warped speech; silence removal and background noise are considered
as the most challenging issues in speech pattern recognition. Literature in this field of study contains a variety of novel techniques for speech signal pattern recognition. Among them, the dynamic speed of input speech is challenging and important since the time duration of the recordings and the length of the same speech contents may vary which result in the failure of similarity measurement techniques to find the best match for continuous speech. This paper amalgamates the use of different techniques which include wavelet transform and Kalman filter for position estimation on the basis of posterior probability measure and a dynamic state model. The main objective of the system is to propose a proof-reading and continuous speech matching and tracking system. The proposed system is capable of tracking the position of continuous input speech signal with respect to the template speech with the progression of time. The system is applied to a scenario where a child orally reads the text of an online story and system performs a recursively adaptive sliding window based matching between the input and template speech. Whenever, the child makes a pronunciation error, the system identifies it and stores the matching result and position of the mistake. Keywords: Speech Tracking; Proof Reading; Kalman Filter; Adaptive Window; Wavelet Transform; Pattern Matching.