Turkish Journal of Electrical Engineering and Computer Sciences




This paper describes research in the field of the improved methodology of the classification of vowels /a, a:/, /$\varepsilon$, $\varepsilon$:/, /ı, i:/, /o, o:/, and /u, u:/ (vowel symbols according to IPA, i.e. International Phonetic Alphabet). The aim is to develop an improved method enabling the automatic allocation of vowel symbols to the corresponding time segments of acoustic recordings of an undisturbed speech signal. The combined classification method is based on finding frequencies of the first two local maxims (formants) in a smoothed linear predictive amplitude spectrum (LPC, linear predictive coding) and zero-crossing values of each speech active voiced short-term segment of the recording. Based on these monitored values, simple heuristic conditions are arranged for the classification of the respective vowel. Implementation of the algorithm was realized using the MATLAB environment and its Graphical User Interface (GUI) was used for the user interaction. Verification of the success rate of vowel classification was done using recordings of forty speakers (twenty men and twenty women), where each speaker repeated the vowels repeatedly with short successive pauses. The success rate of recognizing vowels is classified and evaluated based on results obtained from our designed method.


Speech recognition, classification, linear prediction, cepstrum, formants, vowels, acoustic signal

First Page


Last Page