No Access

Exploitation of Morphological Structures in Large Vocabulary Arabic Speech Recognition

S. DATTA

Department of Electronic and Electrical Engineering, Loughborough University, Loughborough, LE11 3TU, UK

Search for more papers by this author

M. AL-ZABIBI

Scientific Studies and Research Centre, Damascus, P. O. Box. 4470, Syria

Search for more papers by this author

, and

O. FAROOQ

Department of Electronics Engineering, Aligarh Muslim University, Aligarh, India

Search for more papers by this author

https://doi.org/10.1142/S0219427905001353Cited by:2 (Source: Crossref)

Abstract

This paper presents a new approach for large vocabulary Arabic speech recognition based on exploiting the morphological structures of the Arabic language. In this model, word discrimination is achieved by a hybrid analysis scheme, where vowels are described in detail while consonants are classified according to broad phonetic classes. Different phonetic classification strategies are used to describe two large vocabulary lexicons. The results show that about 83% of the 10,000 test Arabic words can be uniquely represented by using 7 broad phonetic classes for consonants and six classes for vowels. In this case, the maximum number of words having the same phonetic labelling is 6. This paper summarises the results of ten different phonetic classification schemes and discusses their implication for a large vocabulary speech recognition system.

Keywords:

References

H. Bahi and M. Sellami, Combination of vector quantization and hidden Markov models for Arabic speech recognition, Proceedings of ACS/IEEE International Conference on Computer Systems and Applications (IEEE Computer Society, 2001) pp. 6–100. Google Scholar
S. H. Alani, Arabic Phonology: An Acoustic and Physiological Investigation, PhD thesis, Indiana University, 1970 . Google Scholar
M. Mrayati , Speech processing application to the Arabic language , Proceedings of the Workshop on Computer Processing of the Arabic Language ( Kuwait Institute of Scientific Research , 1985 ) . Google Scholar
M. Al-Zabibi, An Acoustic Phonetic Approach in Automatic Arabic Speech recognition, PhD thesis, Loughborough University of Technology, 1990 . Google Scholar
Sabah Al-Fadaghi and Fawaz Al-Anzi , A new algorithm to generate Arabic root-pattern forms , Proceedings of 11th National Conference and Exhibition . Google Scholar
H. Tayyan , Y. Alam Meer and M. Mrayati , Database for Arabic roots , Proceedings of the 2nd Conference on Arabic Computational Linguistics ( Kuwait Institute of Scientific Research , 1989 ) . Google Scholar
A. S. Shaheen, Phonetic method for Arabic structure, Alrisalah Establishment, (in Arabic), 1985 . Google Scholar
D. W. Shipman and V. Zue, Properties of large lexicons: Implications for advanced isolated word recognition system, Proceedings of International Conference on Acoustics Speech and Signal Processing ICASSP-82 (1982) pp. 546–549. Google Scholar
L. R. Rabiner and S. E. Levinson, IEEE Transactions on Communications COMM-29, 612 (1981). Google Scholar
L. R. Rabiner, S. E. Levinson and M. M. Sondhi, Bell System Technical Journal 62, 1075 (1983). Crossref, Google Scholar
R. J. Jones, S. Downey and J. S. Mason, Continuous speech recognition using syllables, Proceedings of Eurospeech (1997) pp. 1171–1174. Google Scholar
S. Almajali, A. Sharieh and M. Qutiashat, AMSE Review 44, 1 (2001). Google Scholar
D. A. Abduh, The Common Words in the Arabic Language, publication of Riyadh University, Saudi Arabia (in Arabic), 1979 . Google Scholar
J. Gauvain and L. Lamel, Proceedings of the IEEE 88, 1181 (2000). Crossref, Google Scholar
A. R. E. Ahmed, I. A. Maaly and M. A. H. Abbas, Performance tests on several parametric representations for an Arabic phoneme recognition system using HMMs, Proceedings of 13th International Conference on Applications of Artificial Intelligence in Engineering AIENG XIII (Computational Mechanics Publications, 1998) pp. 45–48. Google Scholar