Probabilistic classification based on Gaussian copula for speech recognition: Application to Spoken Arabic digits
作者： Mouldi Bedda , Nadir Farah , Nacereddine Hammami
DOI:
关键词:
摘要: Language modeling for an inflected language such as Arabic poses new challenges automatic speech recognition and related topic due to its rich morphology. A technique is presented in this paper. This employs a full measure of statistical dependence among random variables that known copulas. novel probabilistic classifier combines finite Gaussian mixture marginal distribution function copula developed. Using benchmark data base, the accuracy developed with Mixtures GCGMM validated compared simple empirical GCEM. The result demonstrates improvement shows excellent performance.
参考文章(21)
Marwan Al-Zabibi, An acoustic-phonetic approach in automatic arabic speech recognition Loughborough University. ,(1990)
K. Daqrouq, K.Y. Al Azzawi, Arabic vowels recognition based on wavelet average framing linear prediction coding and neural network Speech Communication. ,vol. 55, pp. 641- 652 ,(2013) , 10.1016/J.SPECOM.2013.01.002
N. Hammami, M. Bedda, F. Nadir, Probabilistic classification based on copula for speech recognitation: an overview international conference on computer applications technology. pp. 1- 3 ,(2013) , 10.1109/ICCAT.2013.6522036
N. Hammami, M. Bedda, N. Farah, Spoken Arabic Digits recognition using MFCC based on GMM 2012 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (STUDENT). pp. 160- 163 ,(2012) , 10.1109/STUDENT.2012.6408392
Yun Lei, John H. L. Hansen, Dialect Classification via Text-Independent Training and Testing for Arabic, Spanish, and Chinese IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 19, pp. 85- 96 ,(2011) , 10.1109/TASL.2010.2045184
Aurelie Voisin, Vladimir A. Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia, Classification of Very High Resolution SAR Images of Urban Areas Using Copulas and Texture in a Hierarchical Markov Random Field Model IEEE Geoscience and Remote Sensing Letters. ,vol. 10, pp. 96- 100 ,(2013) , 10.1109/LGRS.2012.2193869
Nacereddine Hammami, Mouldi Bedda, Nadir Farah, Tree distributions approximation model for robust discrete speech recognition International Journal of Speech Technology. ,vol. 15, pp. 455- 462 ,(2012) , 10.1007/S10772-012-9141-9
Hai-Son Le, I. Oparin, A. Allauzen, J. Gauvain, F. Yvon, Structured Output Layer Neural Network Language Models for Speech Recognition IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 21, pp. 197- 206 ,(2013) , 10.1109/TASL.2012.2215599
Nacereddine Hammami, Mouldi Bedda, Farah Nadir, The second-order derivatives of MFCC for improving spoken Arabic digits recognition using Tree distributions approximation model and HMMs international conference on communications. pp. 1- 5 ,(2012) , 10.1109/ICCITECHNOL.2012.6285769
Vladimir A. Krylov, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia, Supervised High-Resolution Dual-Polarization SAR Image Classification by Finite Mixtures and Copulas IEEE Journal of Selected Topics in Signal Processing. ,vol. 5, pp. 554- 566 ,(2011) , 10.1109/JSTSP.2010.2103925