INTERSPEECH 2006 - ICSLP
Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Improving Arabic HMM Based Speech Synthesis Quality

Ossama Abdel-Hamid, Sherif Mahdy Abdou, Mohsen Rashwan

Cairo University, Egypt

HMM based speech synthesis, where speech parameters are generated directly from HMM models, is a new technique relative to other speech synthesis techniques. In this paper, we propose some modifications to the basic system to improve its quality. We apply a multi-band excitation model. And we use samples extracted from the spectral envelop as spectral parameters. In the synthesis, the voiced and unvoiced speech parts are mixed according to bands voicing parameters. The voiced part is generated based on a harmonic sinusoidal model. Experimental tests performed on Arabic dataset show that the applied modifications improved the quality.

Full Paper

Bibliographic reference.  Abdel-Hamid, Ossama / Abdou, Sherif Mahdy / Rashwan, Mohsen (2006): "Improving Arabic HMM based speech synthesis quality", In INTERSPEECH-2006, paper 1693-Tue3BuP.10.