Skip to content
Research Article Open access CC BY 3.0

Wavelet LPC with Neural Network for Spoken Arabic Digits Recognition System

K. Daqrouq, M. Alfaouri, A. Alkhateeb, E. Khalaf, A. Morfeq

Current Journal of Applied Science and Technology · pp. 1238–1255 · Published 18 Jan 2014

10.9734/BJAST/2014/6034

Abstract

The crucial problem of Arabic recognition systems is the availability of several dialects in Arabic language, particularly those with sound variations. Therefore, low recognition rate is encountered as a result of such an environment. In this research paper the authors presented dialect-independent via an enormously effectual wavelet transform (WT) based Arabic digits classier. The proposed system may be divided into two main blocks the features extraction method by combining wavelet transform with the linear prediction coding (LPC) and the classification by probabilistic neural network (PNN). The proposed classier provided a high recognition rate reaching up to 100%, in some cases, and an average rate of about 93% based on speaker-independent system. 450 Arabic spoken digit tested signals were used. The performance of the system in the noisy environment was investigated. The obtained results are very promising; however, the larger testing database may provide more credible results.

Arabic digits wavelet transform speech recognition LPC neural network

References (31)

  1. 1 A theory for multiresolution signal decomposition: the wavelet representation [DOI]
  2. 2 Enhancement of speech corrupted by acoustic noise [DOI]
  3. 3 Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task
  4. 4 A robust algorithm for word boundary detection in the presence of noise [DOI]
  5. 5 Interacting with computers by voice: automatic speech recognition and synthesis [DOI]
  6. 6 Feature extraction using discrete wavelet transform for speech recognition [DOI]
  7. 7 Recognition of speech in additive and convolutional noise based on RASTA spectral processing [DOI]
  8. 8 Optimal selection of wavelet-packet-based features using genetic algorithm in pathological assessment of patients’ speech signal with unilateral vocal fold paralysis [DOI]
  9. 9 An expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System for digital modulation recognition [DOI]
  10. 10 Speaker identification using discrete wavelet packet transform technique with irregular decomposition [DOI]
  11. 11 Towards improving speech detection robustness for speech recognition in adverse conditions [DOI]
  12. 12 A new optimum feature extraction and classification method for speaker recognition: GWPNN [DOI]
  13. 13 Arabic diacritic restoration approach based on maximum entropy models [DOI]
  14. 14 Wavelet entropy and neural network for text-independent speaker identification [DOI]
  15. 15 Average framing linear prediction coding with wavelet transform for text-independent speaker identification system [DOI]
  16. 16 High resolution speech feature parametrization for monophone-based stressed speech recognition [DOI]
  17. 17 Investigating spoken Arabic digits in speech recognition setting [DOI]
  18. 18 An investigation of speech enhancement using wavelet filtering method [DOI]
  19. 19 Connectionist Probability Estimators in HMM Arabic Speech Recognition Using Fuzzy Logic [DOI]
  20. 20 Spectrum Analysis Based onWindows with Variable Widths for Online Signature Verification [DOI]
  21. 21 New Hybrid System (Supervised Classifier/HMM) for Isolated Arabic Speech Recognition [DOI]
  22. 22 Neural network speaker dependent isolated Malay speech recognition system: handcrafted vs genetic algorithm [DOI]
  23. 23 A speaker identification system using a model of artificial neural networks for an elevator application [DOI]
  24. 24 New Approach for Language Identification Based on DNA Computing.
  25. 25 Heart rate variability analysis using wavelet transform [DOI]
  26. 26 Speaker identification through use of features selectedusing genetic algorithm [DOI]
  27. 27 Arabic isolated word recognition using general regression neural network [DOI]
  28. 28 A NEW VECTOR QUANTIZATION APPROACH FOR DISCRETE HMM SPEECH RECOGNITION SYSTEM [DOI]
  29. 29 Application of concurrent generalized regression neural networks for arabic speech recognition.
  30. 30 Hybrid architectures for complex phonetic features classification: a unified approach [DOI]
  31. 31 Blind equalization using adaptive filtering for improving speech recognition over telephone [DOI]

Cited by 13

Bi-directional recurrent end-to-end neural network classifier for spoken Arab digit recognition

Naima Zerari, Samir Abdelhamid, Hassen Bouzgou · 2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP) · 2018

Spoken Utterance Classification Task of Arabic Numerals and Selected Isolated Words

Karim dabbabi, Abdelkarim Mars · Arabian Journal for Science and Engineering · 2022

Spoken Arabic Digits Recognition System Using Convolutional Neural Network

Mona A. Azim, Wedad Hussein, Nagwa L. Badr · Advances in Intelligent Systems and Computing · 2021

Speaker Identification and Verification System for Arabic and Berber Language

Ferhat Roumiassa, Fatma-Zohra Chelali · 020 1st International Conference on Communications, Control Systems and Signal Processing (CCSSP) · 2020

Performance Based Comparision of MFCC and LPC Techniques for Gujarati Numbers Detection

Hiral B. Chauhan, B. A. Tanawala · Emerging Research in Computing, Information, Communication and Applications · 2016

Bidirectional deep architecture for Arabic speech recognition

Naima Zerari, Samir Abdelhamid, Hassen Bouzgou · Open Computer Science · 2019

Showing 6 of 13 known citations — external sources report more than can currently be individually listed.

Article metrics

Real usage data collected on this platform.

34

Page views

0

PDF downloads

3

Outbound clicks

13

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.