Arabic Unit Selection Emotional Speech Synthesis using Blending Data Approach
Waleed M. Azmy, Sherif Mahdy Abdou, Mahmoud E. Shoman · International Journal of Computer Applications · 2013
This paper introduce the work done to build an Arabic unit selection voice that could carry emotional information.Three emotional sates were covered; normal, sad and questions.An emotional speech classifier was used to enhance the intelligibility of the used recorded speech database.The classification information was employed in the proposed target cost to produce more natural and emotive synthetic speech.The system is evaluated according to the naturalness and emotiveness of the produced speech.The system evaluations show significant increase in the naturalness and emotiveness scores.