Indian Journal of Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Arabic Speech Segmentation: Automatic Verses Manual Method and Zero Crossing Measurements


Affiliations
1 Computer Research Institute, KACST, P.O. Box 6080, Riyadh 11442, Saudi Arabia
 

In this paper, a comparison between the automatic and manual approach of speech segmentation for the Arabic speech is conducted. In this approach, the automatic method, using the energy level measurement is compared to the manual segmentation procedure. The traditional zero crossing method commonly used for speech processing is also included in this work. The energy measurement method is based on dividing the uttered tokens into different levels. For instance, the Arabic language phonemes are divided into two energy regions: unvoiced phonemes which can be categorized as low energy include the sounds / س / (/s/) and / ه / (/h/). On the other hand, vowels and semi-vowels such as / َ / ( فتحه ) (/ ‘a /) and / و / (/w/) are labeled as high energy. Voiced fricatives, for instance, the sounds / ز / (/z/) and / /ع (/aa/) are classified as high energy phonemes.

Keywords

Manual Speech Segmentation, Automatic Speech Segmentation, Voiced Phonemes, Voiceless Phonemes
User

  • Alghmadi M (2003) KACST Arabic phonetic database. The 15th Int. Congress of Phonetics Sci. 3109-3112.

  • Cherif A, Bouafif L and Dabbabi T (2001) Pitch detection and formant analysis of Arabic speech processing. Appl. Acoustics. 1129-1140.

  • Demuynck K and Laureys T (2002) A comparison of different approaches to automatic speech segmentation. Lecturer notes in Computer Sci. 2448, 385-406.

  • Essa O (2005) Using prosody in automatic segmentation of speech. Computer Science Dept., University of South Carolina.

  • Hemert V (1991) Automatic segmentation of speech. IEEE Trans. on Signal Processing. 1008-1012.

  • Lee Y, Papineni K, Roukos S, Emam O and Hassan H (2003) Language model based arabic word segmentation. Proc. of the 41st Annual meeting of the Association for Computational Linguistics. 399-406.

  • Tolba M, Nazmy T, Abdelhamid A and Gadallah M (2005) A novel method for Arabic consonant/vowel segmentation using wavelet transform. Proc. of IJICIS. 353-364.


Abstract Views: 486

PDF Views: 119




  • Arabic Speech Segmentation: Automatic Verses Manual Method and Zero Crossing Measurements

Abstract Views: 486  |  PDF Views: 119

Authors

Mohammed A. Al-Manie
Computer Research Institute, KACST, P.O. Box 6080, Riyadh 11442, Saudi Arabia
Mohammed I. Alkanhal
Computer Research Institute, KACST, P.O. Box 6080, Riyadh 11442, Saudi Arabia
Mansour M. Al-Ghamdi
Computer Research Institute, KACST, P.O. Box 6080, Riyadh 11442, Saudi Arabia

Abstract


In this paper, a comparison between the automatic and manual approach of speech segmentation for the Arabic speech is conducted. In this approach, the automatic method, using the energy level measurement is compared to the manual segmentation procedure. The traditional zero crossing method commonly used for speech processing is also included in this work. The energy measurement method is based on dividing the uttered tokens into different levels. For instance, the Arabic language phonemes are divided into two energy regions: unvoiced phonemes which can be categorized as low energy include the sounds / س / (/s/) and / ه / (/h/). On the other hand, vowels and semi-vowels such as / َ / ( فتحه ) (/ ‘a /) and / و / (/w/) are labeled as high energy. Voiced fricatives, for instance, the sounds / ز / (/z/) and / /ع (/aa/) are classified as high energy phonemes.

Keywords


Manual Speech Segmentation, Automatic Speech Segmentation, Voiced Phonemes, Voiceless Phonemes

References





DOI: https://doi.org/10.17485/ijst%2F2010%2Fv3i12%2F29847