Turkish vowel classification based on acoustical and decompositional features optimized by Genetic Algorithm

Abstract In digital speech processing (DSP), vowel classification is one of the important and challenging issue of automatic speech/speaker recognition (ASR) systems where vowels need to be processed in order to identify spoken speech or speaker identity. Because the vowels’ acoustic features such as Formant Frequencies, Energy, Zero Crossing Rate (ZCR) etc. contain patterns revealing speech/speaker characteristics, vowels were used in many studies like speech/speaker recognition, speaker verification, accent/dialect estimation, illness detection via speech etc. In this work, digital speech signals of 8 vowels (/a/, /e/, /i/, /i/, /o/, /o/, /u/ and /u/) in Turkish language were classified using a feature set optimized by Genetic Algorithm. The entire feature vector, which has length of 24, comprises acoustical features (Formant Frequency obtained by Linear Predictive Coding-LPC, Energy, ZCR, Mel-Frequency Cepstral Coefficients-MFCCs) and decompositional features (Wavelet Decomposition Shannon Entropy). All of the 8 isolated vowels were uttered by 10 male speakers (only male to avoid gender effect), and totally 2762 observations were obtained from the vowels signals for classification step. The results inferred that the feature vector optimized by Genetic Algorithm method reached 100% classification success accuracy via the simple 1NN classifier with Manhattan distance. These findings proved success of the proposed model and the Genetic Algorithm’s efficiency on feature selection for the Turkish vowel classification.

[1]  Anil K. Jain,et al.  Dimensionality reduction using genetic algorithms , 2000, IEEE Trans. Evol. Comput..

[2]  Ali Soleimani,et al.  An effective feature selection method for web spam detection , 2019, Knowl. Based Syst..

[3]  Tao Tan,et al.  Retinal artery/vein classification using genetic-search feature selection , 2018, Comput. Methods Programs Biomed..

[4]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[5]  Kandarpa Kumar Sarma,et al.  Segmentation and Classification of Vowel Phonemes of Assamese Speech Using a Hybrid Neural Framework , 2012, Appl. Comput. Intell. Soft Comput..

[6]  Sami Ekici,et al.  Support Vector Machines for classification and locating faults on transmission lines , 2012, Appl. Soft Comput..

[7]  A. Charan Kumari,et al.  Feature Selection Optimization in SPL using Genetic Algorithm , 2018 .

[8]  Frederic Dick,et al.  Neural representation of vowel formants in tonotopic auditory cortex , 2018, NeuroImage.

[9]  Samy Bengio,et al.  Evaluation of formant-like features on an automatic vowel classification task. , 2004, The Journal of the Acoustical Society of America.

[10]  Sazali Yaacob,et al.  Statistical formant descriptors with linear predictive coefficients for accent classification , 2013, 2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA).

[11]  Danyang Yuan,et al.  Genetic algorithm for the optimization of features and neural networks in ECG signals classification , 2017, Scientific Reports.

[12]  Shashidhar G. Koolagudi,et al.  Classification of vocal and non-vocal segments in audio clips using genetic algorithm based feature selection (GAFS) , 2018, Expert Syst. Appl..

[13]  Raymond D. Kent,et al.  Effects of Aging on Vocal Fundamental Frequency and Vowel Formants in Men and Women. , 2017, Journal of voice : official journal of the Voice Foundation.

[14]  Tarek A. Tutunji,et al.  Speaker identification using vowels features through a combined method of formants, wavelets, and neural network classifiers , 2015, Appl. Soft Comput..

[15]  Bin Ghazi,et al.  Arabic Audio News Retrieval System Using Dependent Speaker Mode, Mel Frequency Cepstral Coefficient and Dynamic Time Warping Techniques , 2014 .

[16]  Yunus Korkmaz,et al.  Examining Vowels' Formant Frequency Shifts Caused by Preceding Consonants for Turkish Language , 2018 .

[17]  Jan Nedoma,et al.  Improved method of heuristic classification of vowels from an acoustic signal , 2018 .

[18]  Abdelkader Benyettou,et al.  Speech Recognition Oriented Vowel Classification Using Temporal Radial Basis Functions , 2009, ArXiv.

[19]  Afiahayati,et al.  Suitable CNN Weight Initialization and Activation Function for Javanese Vowels Classification , 2018, INNS Conference on Big Data.

[20]  A. Zourmand,et al.  Vowel Classification of Children's Speech Using Fundamental and Formant Frequencies , 2012, 2012 Fourth International Conference on Computational Intelligence, Modelling and Simulation.