Energy bands and spectral cues for Arabic vowels recognition

The present study examines the short and long Arabic vowels (/a/, /a:/, /i/, /i:/, /u/ and /u:/) with a new approach based on three methods: formant frequencies extraction, spectral moments and energy bands. Among Arabic language characteristics compared to other languages are long vowels which can be pronounced with different duration length. The formant frequencies are the most exploited in characterizing vowels in different languages nevertheless using only formants was not very significant for vowels identification especially when production duration augments. Therefore, our approach is to broaden previous studies and present new tools in order to characterize long vowels compared to short ones.

[1]  Yongqiang Feng,et al.  Detecting anticipatory effects in speech articulation by means of spectral coefficient analyses , 2011, Speech Commun..

[2]  Peter Ladefoged.  The phonetic basis for computer speech processing , 1986 .

[3]  K. Stevens,et al.  Development of a Quantitative Description of Vowel Articulation , 1955 .

[4]  Janne Savela,et al.  Role of Selected Spectral Attributes in the Perception of Synthetic Vowels , 2009 .

[5]  Peter Ladefoged,et al.  Elements of Acoustic Phonetics , 1962 .

[6]  Tapio Salakoski,et al.  Role of Different Spectral Attributes in Vowel Categorization: the Case of Udmurt , 2007, NODALIDA.

[7]  藤村 靖,et al.  Gunnar Fant: Acoustic Theory of Speech Production : with Calculations based on X-Ray Studies of Russian Articulations, Mouton & Co, 1960, 's-Gravenhage $ 15 , 1962 .

[8]  F S COOPER,et al.  The interconversion of audible and visible patterns as a basis for research in the perception of speech. , 1951, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Kimiko Tsukada,et al.  An Acoustic Comparison of Vowel Length Contrasts in Standard Arabic, Japanese and Thai , 2009, 2009 International Conference on Asian Language Processing.

[10]  Yousef Ajami Alotaibi,et al.  Speech Recognition System and Formant Based Analysis of Spoken Arabic Vowels , 2009, FGIT.

[11]  B. Dodd,et al.  The perceptual magnet effect in Australian English vowels , 2000, Perception & psychophysics.

[12]  S. Linville,et al.  Vocal tract resonance analysis of aging voice using long-term average spectra. , 2001, Journal of voice : official journal of the Voice Foundation.

[13]  Shahid Masud,et al.  On Vowels Segmentation and Identification Using Formant Transitions in Continuous Recitation of Quranic Arabic , 2008, New Challenges in Applied Intelligence Technologies.

[14]  S. Xue,et al.  Volumetric measurements of vocal tracts for male speakers from different races , 2006, Clinical linguistics & phonetics.

[15]  Yaser S Natour,et al.  Formant frequency characteristics in normal Arabic-speaking Jordanians. , 2011, Journal of voice : official journal of the Voice Foundation.

[16]  G. Fant.  Acoustic theory of speech production : with calculations based on X-ray studies of Russian articulations , 1961 .

[17]  T. Kitama,et al.  Critical spectral regions for vowel identification , 2002, Neuroscience Research.

[18]  Pentti Körkkö.  Spectral moments analysis of /s/ coarticulation development in Finnish-speaking children , 2015, ICPhS.

[19]  J. Hillenbrand,et al.  Acoustic characteristics of American English vowels. , 1994, The Journal of the Acoustical Society of America.