COMPARATIVE STUDY OF CLASSIFICATION METHODS USED FOR IDENTIFYING VIETNAMESE – ENGLISH – FRENCH

Le Trung Hieu; Pham Quoc Hung; Nguyen Vinh Quy; Chu Ba Thanh

Le Trung Hieu Hung Yen University of Technology and Education
Pham Quoc Hung Hung Yen University of Technology and Education
Nguyen Vinh Quy Hung Yen University of Technology and Education
Chu Ba Thanh Hung Yen University of Technology and Education

Keywords: Language Identification; Vietnamese; English; French; SVM; SMO; Weka.

Abstract

There are many different methods and models which researched and applied for identification of languages such as GMM, HMM, SVM, ANN models, etc. The article presents test results identify three languages Vietnamese, English, French which use SMO (Sequential Minimal Optimization), iBK, Multilayer Perceptron classifier of Weka with features was extracted by OpenSMILE, the number of features are 384 coefficient. The test results with SMO classifiers show out the highest Vietnamese recognition rate was 98.75%, the highest French recognition was 93,5% when used Multilayer Perceptron classifier and SMO classifier and the highest English recognition was 94,75% with Multilayer Perceptron classifier.

References

William M. Campbell, Joseph P. Campbell, Douglas A. Reynolds, and Pedro Torres-Carrasquillo, “Support Vector Machines for Speaker and Language Recognition,” Computer Speech & Language, vol. 20, no. 2, pp. 210-229, Apr. 2006.

Shigeo Abe, Support Vector Machines for Pattern Classification, 2nd ed. London: Springer, 2010.

Shady Y. EL-Mashed, Mohammed I. Sharway, and Hala H. Zayed, “Speaker Independent Arabic Speech Recognition using Support Vector Machine,” in Department of Electrical Engineering, Shoubra Faculty of Engineering, Benha University, Cairo, Egypt, 2009.

Jue Hou, Yi Liu, Thomas Fang Zheng, Jesper Olsen, and Jilei Tian, “Multi-layered Features with SVM for Chinese Accent Identification,” in Audio Language and Image Processing, 2010, pp. 25-30. [5]. Fred Richardson and William M. Campbell, “Discriminative Keyword Selection using Support Vector Machines,” in Advances in Neural Information Processing Systems 20, 2007, pp. 209-216. [6]. K. Sreenivasa Rao, V. Ramu Reddy, and Sudhamay Maity, Language Identification Using Spectral and Prosodic Features, Springer International Publishing, 2015, ch. 1, pp. 2-7.

Peter F. Brown, Peter V. deSouza, Robert L. Mercer, Vincent J. Della Pietra, and Jenifer C. Lai, “Class-Based n-gram Models of Natural,” Computational Linguistics, vol. 18, no. 4, pp. 467-479, Dec. 1992.

Haizhou Li, Bin Ma, and Chin Hui Lee, “A Vector Space Modeling Approach to Spoken Language Identification,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 1, pp. 271-284, Jan. 2007.

Khe Chai Sim and Haizhou Li, “On Acoustic Diversification Front-End for Spoken Language Identification,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 5, pp. 1029 - 1037, July 2008.

Rong Tong, Bin Ma, Haizhou Li, and Eng Siong Chng, “Target-Oriented Phone Selection from Universal Phone Set for Spoken Language Recognition,” in Interspeech , 2008.

Jia Li You, Yi Ning Chen, Min Chu, Frank K. Soong, and Jin Lin Wang, “Identifying Language Origin of Named Entity with Multiple Information Sources,” in IEEE Transactions on Audio, Speech, and Language Processing, 2008, pp. 1077 - 1086.

Gerrit Reinier Botha and Etienne Barnard, “Factors that Affect the Accuracy of Text-based Language Identification,” Computer Speech & Language, vol. 26, no. 5, pp. 307-320, Oct. 2012. [13]. Marc Picard, An Introduction to the Comparative Phonetics, John Benjamins Publishing Company, Amsterdam/Philadelphia, 1987.

Nguyễn Hữu Quỳnh, Tiếng Việt hiện đại (Ngữ âm, ngữ pháp, phong cách), Trung tâm biên soạn từ điển bách khoa Việt Nam, Hà Nội, 1994.

Zissman, “Automatic Language Identification using Gaussian Mixture and Hidden Markov Models,” in Acoustics, Speech, and Signal Processing, 1993. ICASSP-93 1993 IEEE International Conference on, 1993, pp. 399-402.

Muthusamy, Yeshwant K , Ronald A , Cole, and Beatrice T. Oshika, “The OGI Multi-language Telephone Speech Corpus,” ICSLP, vol. 92, pp. 895-898, Oct. 1992.

Manchala, V. Kamakshi Prasad, and V. Janaki, “GMM based Language Identification System using Robust Features,” International Journal of Speech Technology, vol. 17, no. 2, pp. 99–105, June 2014. [18]. Martin , Alvin F, and Craig S. Greenberg, “The 2009 NIST Language Recognition Evaluation,” in Odyssey, 2010.

Luciana Ferrer, Yun Lei, Mitchell McLaren, and Nicolas Scheffer, “Study of Senone-Based Deep Neural Network Approaches for Spoken Language Recognition,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 1, pp. 105 - 116, Jan. 2016.

Ana Montalvo, Yandre M. G. Costa, and José Ramón Calvo, “Language Identification Using Spectrogram Texture,” in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications.: Springer International Publishing, 2015, pp. 543-550.

Hà Hải Nam, Trịnh Văn Loan, “Một hướng tiếp cận dựa trên tần số cơ bản để định danh tự động ngôn ngữ có thanh điệu và không có thanh điệu,” Kỷ yếu Hội thảo khoa học Quốc gia lần thứ hai về nghiên cứu, phát triển và ứng dụng Công nghệ Thông tin và truyền thông ICT.rda, Hà Nội, 2004, pp. 211-215.

Lan H.Witten, Eibe Frank, and Mark A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, Korean : Morgan Kaufmann, 2011.

Schuller , Björn , Stefan Steidl, and Anton Batliner, “The InterSpeech 2009 Emotion Challenge,” in INTERSPEECH, 2009, pp. 312-315.

John Platt, “Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines,” technical report msr-tr-98-14, Microsoft Research, vol. 112, Apr. 1998.