Spoken Arabic Digits recognition using MFCC based on GMM

Gaussian mixture model (GMM) is a conventional method for speech recognition, known for its effectiveness and scalability in speech modeling. This paper presents automatic recognition of the Spoken Arabic Digits based on (GMM) classifier and the leading approach for speech recognition features extraction Delta-Delta Mel- frequency cepstral coefficients (DDMFCC). The experimental results give the best result with the obtained parameters; they achieve a 99.31% correct digit recognition dataset which is very satisfactory compared to previous work on spoken Arabic digits speech recognition.

[1]  Nadir Farah,et al.  Tree distributions approximation model for robust discrete speech recognition , 2012, Int. J. Speech Technol..

[2]  Nacereddine Hammami,et al.  The second-order derivatives of MFCC for improving spoken Arabic digits recognition using Tree distributions approximation model and HMMs , 2012, 2012 International Conference on Communications and Information Technology (ICCIT).

[3]  Donghui Guo,et al.  Speaker recognition using weighted dynamic MFCC based on GMM , 2010, 2010 International Conference on Anti-Counterfeiting, Security and Identification.

[4]  Othman O. Khalifa,et al.  Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools , 2010, International Conference on Computer and Communication Engineering (ICCCE'10).

[5]  Lyle Campbell,et al.  Ethnologue: Languages of the world (review) , 2008 .

[6]  Xiaohui Hu,et al.  Spoken arabic digits recognition based on wavelet neural networks , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[7]  Brian Kingsbury,et al.  Advances in Arabic Speech Transcription at IBM Under the DARPA GALE Program , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[8]  Xueying Zhang,et al.  A Speech Recognition Method of Isolated Words Based on Modified LPC Cepstrum , 2007 .

[9]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[10]  J. Hansen,et al.  Dialect Classification via Text-Independent Training and Testing for Arabic, Spanish, and Chinese , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Danoush Hosseinzadeh,et al.  Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs , 2007, 2007 IEEE 9th Workshop on Multimedia Signal Processing.

[12]  Nacereddine Hammami,et al.  Improved tree model for arabic speech recognition , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[13]  Zhigang Cao,et al.  Improved MFCC-based feature for robust speaker identification , 2005 .

[14]  Merouane Bouzid.  Robust quantization of LPC parameters for speech communication over noisy channel , 2009, 2009 Second International Conference on the Applications of Digital Information and Web Technologies.

[15]  J.H.L. Hansen,et al.  An efficient scoring algorithm for Gaussian mixture model based speaker identification , 1998, IEEE Signal Processing Letters.

[16]  Yuhua Qian,et al.  MGRS in Incomplete Information Systems , 2007 .

[17]  Raja N. Ainon,et al.  Arabic speech recognition using Hidden Markov Model Toolkit(HTK) , 2010, 2010 International Symposium on Information Technology.

[18]  M. Bedda,et al.  HMM parameters estimation based on cross-validation for Spoken Arabic Digits recognition , 2011, 2011 International Conference on Communications, Computing and Control Applications (CCCA).