Realisation d'un systeme de reconnaissance automatique de la parole arabe base sur CMU Sphinx

TL;DR

This paper details the development of an Arabic automatic speech recognition system based on CMU Sphinx 4, achieving 96% accuracy in continuous speech recognition, extending prior digit recognition work.

Contribution

It introduces a continuous Arabic speech recognition system using CMU Sphinx 4, surpassing previous digit recognition limitations with high accuracy.

Findings

Achieved 96% recognition rate for continuous Arabic speech

Extended previous digit recognition work to continuous speech

Demonstrated the effectiveness of CMU Sphinx 4 for Arabic ASR

Abstract

This paper presents the continuation of the work completed by Satori and all. [SCH07] by the realization of an automatic speech recognition system (ASR) for Arabic language based SPHINX 4 system. The previous work was limited to the recognition of the first ten digits, whereas the present work is a remarkable projection consisting in continuous Arabic speech recognition with a rate of recognition of surroundings 96%.