Speaker recognition based on Arabic phonemes

Abstract In this paper, we investigate the effect of Arabic phonemes on the performance of speaker recognition systems. The investigation reveals that some Arabic phonemes have a strong effect on the recognition rate of such systems. The performance of speaker recognition systems can be improved and their execution time can be reduced by utilizing this finding. Additionally, this finding can be used by segmenting the most effective phonemes for speaker recognition from the utterance, using only the segmented part of the speech for speaker recognition. It can also be used in designing the text to be used in high-performance speaker recognition systems. From our investigation, we find that the recognition rates of Arabic vowels were all above 80%, whereas the recognition rates for the consonants varied from very low (14%) to very high (94%), with the latter achieved by a pharyngeal consonant followed by the two nasal phonemes, which achieved recognition rates above 80%. Four more consonants had recognition rates between 70% and 80%. We show that by utilizing these findings and by designing the text carefully, we can build a high-performance speaker recognition system.

[1]  Shingo Kuroiwa,et al.  Speaker Recognition for Wire/Wireless Communication Systems , 2006, Int. Arab J. Inf. Technol..

[2]  M. Alsulaiman,et al.  Multidirectional Local Feature for Speaker Recognition , 2012, 2012 Third International Conference on Intelligent Systems Modelling and Simulation.

[3]  Vijay K. Madisetti,et al.  The Digital Signal Processing Handbook , 1997 .

[4]  Mansour Al-Ghamdi,et al.  Speaker verification based on Saudi accented Arabic database , 2007, 2007 9th International Symposium on Signal Processing and Its Applications.

[5]  H. Bessalah,et al.  Forensic Identification Reporting Using A GMM Based Speaker Recognition System Dedicated to Algerian Arabic Dialect Speakers , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[6]  Y.A. Alotaibi,et al.  A Word-Dependent Automatic Arabic Speaker Identification System , 2008, 2008 IEEE International Symposium on Signal Processing and Information Technology.

[7]  Oumayma Al Dakkak,et al.  Automatic, Text-Independent, Speaker Identification and Verification System Using Mel Cepstrum and GMM , 2008 .

[8]  S. J. Hussain,et al.  Optimizing network parameters for Arabic speakers recognition , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[9]  Aaron D. Lawson,et al.  Survey and evaluation of acoustic features for speaker recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Muhammad Ghulam,et al.  A technique to overcome the problem of small size database for automatic speaker recognition , 2010, 2010 Fifth International Conference on Digital Information Management (ICDIM).

[11]  Yousif A. El-Imam.  An unrestricted vocabulary Arabic speech synthesis system , 1989, IEEE Trans. Acoust. Speech Signal Process..

[12]  Abdennaceur Kachouri,et al.  Contribution to the Vocal Print Recognition in Arabic Language , 2007 .

[13]  M.M. El-Henawy,et al.  A modified group vector quantization algorithm for speaker identification , 2003, 2003 46th Midwest Symposium on Circuits and Systems.

[14]  Haizhou Li,et al.  An overview of text-independent speaker recognition: From features to supervectors , 2010, Speech Commun..

[15]  M.F. Abu El-Yazeed,et al.  Dimensionality reduction for text-independent speaker identification using Gaussian mixture model , 2003, 2003 46th Midwest Symposium on Circuits and Systems.

[16]  Margit Antal.  PHONETIC SPEAKER RECOGNITION , 2008 .

[17]  M. Alsulaiman,et al.  AUTOMATIC ENLARGEMENT OF SPEECH CORPUS BY USING DIFFERENT TECHNIQUES , 2014 .

[18]  Vijay K. Madisetti.  The Digital Signal Processing Handbook - 3 Volume Set , 2018 .

[19]  Muhammad Ghulam,et al.  KSU Speech Database: Text Selection, Recording and Verification , 2013, 2013 European Modelling Symposium.

[20]  Andreas Stolcke,et al.  Recognizing Arabic speakers with English phones , 2008, Odyssey.

[21]  A. Kachouri,et al.  A new method for speech denoising and speaker verification using subband architecture , 2004, First International Symposium on Control, Communications and Signal Processing, 2004..

[22]  Khalid Saeed,et al.  A Speech-and-Speaker Identification System: Feature Extraction, Description, and Classification of Speech-Signal Image , 2007, IEEE Transactions on Industrial Electronics.

[23]  Hesham Tolba.  A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach , 2011 .

[24]  Lalit R. Bahl,et al.  Speech recognition with continuous-parameter hidden Markov models , 1987 .

[25]  Douglas A. Reynolds,et al.  An overview of automatic speaker recognition technology , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  Halim Sayoud,et al.  Application of the MLVQ1 in speaker identification , 2003, NOLISP.

[27]  Muhammad Ghulam,et al.  Study on pharyngeal and uvular consonants in foreign accented Arabic for ASR , 2010, Comput. Speech Lang..

[28]  Ghulam Muhammad,et al.  Building a Speaker Recognition System with one Sample , 2009 .

[29]  Y.A. Alotaibi.  Recognizing and Investigating Spoken Arabic Alphabet , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[30]  M. Nofal,et al.  Arabic/English automatic spoken language identification , 1999, 1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM 1999). Conference Proceedings (Cat. No.99CH36368).

[31]  Bin Ma,et al.  Text-dependent speaker verification: Classifiers, databases and RSR2015 , 2014, Speech Commun..

[32]  Ghulam Muhammad,et al.  Automatic Speaker Recognition Using Multi-Directional Local Features (MDLF) , 2014 .

[33]  Matthieu Hébert,et al.  Text-Dependent Speaker Recognition , 2008 .

[34]  T. Mohamadi,et al.  QSDAS: NEW QURANIC SPEECH DATABASE FOR ARABIC SPEAKER RECOGNITION , 2010 .

[35]  Muhammad Ghulam,et al.  Noise Effect on Arabic Alphadigits in Automatic Speech Recognition , 2009, IPCV.

[36]  Joaquin Gonzalez-Rodriguez,et al.  Evaluating Automatic Speaker Recognition systems: An overview of the NIST Speaker Recognition Evaluations (1996-2014) , 2014 .

[37]  M. Savic,et al.  Phoneme based speaker verification , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[38]  F.A. Elmisery,et al.  An FPGA Based VQ for Speaker Identification , 2005, 2005 International Conference on Microelectronics.

[39]  Ghulam Muhammad,et al.  MDLF-Mavg: A new speech feature with a voice print , 2013, 2013 7th IEEE GCC Conference and Exhibition (GCC).

[40]  Mansour Alsulaiman,et al.  KSU rich Arabic speech database , 2013 .

[41]  K. Daqrouq,et al.  Speaker Identification Wavelet Transform based method , 2008, 2008 5th International Multi-Conference on Systems, Signals and Devices.

[42]  R. A. Khan,et al.  Applications of Speaker Recognition , 2012 .

[43]  AbdulMalik S. Al-Salman,et al.  Arabic Text-Dependent Speaker Verification for Mobile Devices Using Artificial Neural Networks , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[44]  Oscar Saz-Torralba,et al.  Capturing Local Variability for Speaker Normalization in Speech Recognition , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[45]  Douglas A. Reynolds,et al.  A Tutorial on Text-Independent Speaker Verification , 2004, EURASIP J. Adv. Signal Process..

[46]  Joaquín González-Rodríguez,et al.  Automatic language identification using deep neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).