Arabic speech recognition using recurrent neural networks

Author

El Choubassi, M.M. ; El Khoury, H.E. ; Alagha, C. E Jabra ; Skaf, J.A. ; Al-Alaoui, M.A.

Author_Institution

Dept. of Electr. & Comput. Eng., American Univ. of Beirut, Lebanon

fYear

2003

fDate

14-17 Dec. 2003

Firstpage

543

Lastpage

547

Abstract

In this paper, a novel approach for implementing Arabic isolated speech recognition is described. While most of the literature on speech recognition (SR) is based on hidden Markov models (HMM), the present system is implemented by modular recurrent Elman neural networks (MRENN). The promising results obtained through this design show that this new neural networks approach can compete with the traditional HMM-based speech recognition approaches.

Keywords

hidden Markov models; natural languages; recurrent neural nets; speech recognition; Arabic speech recognition; HMM; hidden Markov model; modular recurrent Elman neural network; Automatic speech recognition; Cepstral analysis; Feature extraction; Hidden Markov models; Neural networks; Recurrent neural networks; Speech recognition; Strontium; Vector quantization; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on

Print_ISBN

0-7803-8292-7

Type

conf

DOI

10.1109/ISSPIT.2003.1341178

Filename

1341178

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3523273