Towards a high quality arabic speech synthesis system based on neural networks and residual excited vocal tract model

DOI10.1007/S11760-007-0038-ZMaRDI QIDQ2480194zbMATH OpenOpenAlexFDO

Authors Fatima Chouireb, Mhania Guerti

Publication date 31 March 2008

Published in Signal, Image and Video Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11760-007-0038-z

zbMATH Keywords

natural language processingneural networksphonetic and acoustic segmentationprosodic databaseprosodic-information synthesizerresidual excitationtext-to-speech synthesis

Mathematics Subject Classification ID

Natural language processing (68T50) Approximation methods and heuristics in mathematical programming (90C59) Linguistics (91F20)

Recommendations

• Techniques for high quality Arabic speech synthesis
• Advances in Artificial Intelligence
• Text-to-speech conversion of standard malay
• Basic research and implementation decisions for a text-to-speech synthesis system in Romanian
• scientific article; zbMATH DE number 941399

Cites work

• A comparison of spectral smoothing methods for segment concatenation based speech synthesis
• scientific article; zbMATH DE number 4070373 (Why is no real title available?)

Cited in

(6)

• Techniques for high quality Arabic speech synthesis
• Text-to-speech conversion of standard malay
• Synthesis of the intonation of neutrally spoken modern standard Arabic speech
• Speech synthesis using neural networks trained by an evolutionary algorithm
• Advances in Artificial Intelligence
• A stochastic knowledge-based Thai text-to-speech system

Describes a project that uses

Uses Software

• TTSBOX

This page was built for publication: Towards a high quality arabic speech synthesis system based on neural networks and residual excited vocal tract model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2480194)