Usage of the HMM-Based Speech Synthesis for intelligent Arabic voice

Loading...
Thumbnail Image

Date

2008

Journal Title

Journal ISSN

Volume Title

Type

Book chapter

Publisher

AMER INST PHYSICS

Series Info

1st Mediterranean Conference on Intelligent Systems and Automation (CISA 2008);AIP Conference Proceedings Volume: 1019 Pages: 93-+

Doi

Scientific Journal Rankings

Abstract

The HMM as a suitable model for time sequence modeling is used for estimation of speech synthesis parameters, A speech parameter sequence is generated from HMMs themselves whose observation vectors consists of spectral parameter vector and its dynamic feature vectors. HMMs generate cepstral coefficients and pitch parameter which are then fed to speech synthesis filter named Mel Log Spectral Approximation (MLSA), this paper explains how this approach can be applied to the Arabic language to produce intelligent Arabic speech synthesis using the HMM- Based Speech Synthesis and the influence of using of the dynamic features and the increasing of the number of mixture components on the quality enhancement of the Arabic speech synthesized.

Description

Accession Number: WOS:000257193900015

Keywords

Citation

Cited References in Web of Science Core Collection: 22