论文信息 - Recognizing and Investigating Spoken Arabic Alphabet

Recognizing and Investigating Spoken Arabic Alphabet

Alphabet recognition is needed in many applications for retrieving information associated with the spelling of a name, such as telephone, addresses, etc. In this paper Arabic alphabets were investigated from the speech recognition problem point of view. The system was an isolated whole word speech recognizer. Spoken Arabic alphabet has more than one set, each of which contains members of alphabets that are acoustically very similar. This recognition system achieved 83.34% correct for alphabets. The spoken alphabet "Hamzah" got almost 100% recognition rate, but the worst performance was encountered with alphabet "Baa", "Taa", "Thaa", "H_aa", "Thaal", "Raa", "Seen", "T_aa", "Dhaa", and "Faa".

Y.A. Alotaibi

[1] Biing-Hwang Juang,et al. Hidden Markov Models for Speech Recognition , 1991 .

[2] Andreas Spanias,et al. High-performance alphabet recognition , 1996, IEEE Trans. Speech Audio Process..

[3] Marwan Al-Zabibi. An acoustic-phonetic approach in automatic arabic speech recognition , 1990 .

[4] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[5] Ronald A. Cole,et al. Speaker-independent recognition of spoken English letters , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[6] P. Cosi,et al. High performance telephone bandwidth speaker independent continuous digit recognition , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[7] Stephen A. Zahorian,et al. Signal modeling for high-performance robust isolated word recognition , 2001, IEEE Trans. Speech Audio Process..

[8] John H. L. Hansen,et al. Discrete-Time Processing of Speech Signals , 1993 .