International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 71 - Number 24 |
Year of Publication: 2013 |
Authors: Muhammad Akbar Ali Khan, Sahibzada Abdur Rehman Abid, Fatima Tuz Zuhra, Nasir Ahmad |
10.5120/12695-9478 |
Muhammad Akbar Ali Khan, Sahibzada Abdur Rehman Abid, Fatima Tuz Zuhra, Nasir Ahmad . The Development of Pashto Speech Synthesis System. International Journal of Computer Applications. 71, 24 ( June 2013), 49-53. DOI=10.5120/12695-9478
This paper presents a novel Pashto text-to-speech (TTS) synthesis system based on data driven techniques such as Classification and Regression Tree (CART), Bigrams, and Non Uniform Units (NUUs). A modular concatenative TTS system has been developed for the Pashto language. Speech synthesis is carried out through a series of steps with the intention to provide a gradually more absolute transcription of the text, from which the final speech signal is then generated. The steps can be divided into two modules; a Natural Language Processing (NLP) module and a Digital Signal Processing (DSP) module. These steps incrementally enhance the information derived from the input and put it on a generally accessible internal data structure. The goal is to obtain enough information on the internal data structure so as to be capable to obtain an intelligible and natural speech.