Boltzmann machine neural network for Arabic speech recognition

Other Title(s)

الشبكة العصبية المسماة ماكنة Boltzmann لتمييز الكلام العربي

Author

Muhammad, Hind Rustum

Source

Ibn al-Haitham Journal for Pure and Applied Science

Issue

Vol. 19, Issue 4 (31 Dec. 2006), pp.125-133, 9 p.

Publisher

University of Baghdad College of Education for Pure Science / Ibn al-Haitham

Publication Date

2006-12-31

Country of Publication

Iraq

No. of Pages

9

Main Subjects

Natural & Life Sciences (Multidisciplinary)

Abstract AR

استخدمت خوارزمية فورير السريعة (fft) لاستخلاص طاقة الترددات التي تحتويها الإشارة الصوتية تم تقليص حجم البيانات بعد ذلك بسلسلة من العمليات بغية الوصول إلى مجموعة مناسبة للشبكة العصبية التي استخدمت كمميز للأصوات العربية.

استخدم هذا البحث شبكة ماكنة boltznmann كمميز للأصوات حيث دربت مجموعة تدريب تحتوي على عدد من تمثيلات الأصوات العربية التي تم الحصول عليها من مرحلة التمثيل.

استطاعت هزة الشبكة من خلال التدريب إن الأصوات العربية حيث كانت مشجعة جدا بعد تدريب الشبكة العصبية ماكنة Boltzmann.

Abstract EN

Boltzmann machine neural network has been used to recognizc the Arabic specch.

Fast Fourier transformation algorithm has been used to extract spectral features from an a coustic signal.

The spectral feature size is reduced by scries of operations in order to make it salable as input for a neural network which is used as a recogni/.er by Boltzmann Machine Neural network which has been used as a recognizer for phonemes .

٨ training set consist ofa number of ،Arabic phoneme repesentations, is used to train the neural network.

The neural network rccognized Arabic.

After Boltzmann Machine Neural network training the system with few selected Arabic phonemes, the results came out to be very encouraging .

American Psychological Association (APA)

Muhammad, Hind Rustum. 2006. Boltzmann machine neural network for Arabic speech recognition. Ibn al-Haitham Journal for Pure and Applied Science،Vol. 19, no. 4, pp.125-133.
https://search.emarefa.net/detail/BIM-356011

Modern Language Association (MLA)

Muhammad, Hind Rustum. Boltzmann machine neural network for Arabic speech recognition. Ibn al-Haitham Journal for Pure and Applied Science Vol. 19, no. 4 (2006), pp.125-133.
https://search.emarefa.net/detail/BIM-356011

American Medical Association (AMA)

Muhammad, Hind Rustum. Boltzmann machine neural network for Arabic speech recognition. Ibn al-Haitham Journal for Pure and Applied Science. 2006. Vol. 19, no. 4, pp.125-133.
https://search.emarefa.net/detail/BIM-356011

Data Type

Journal Articles

Language

English

Notes

Includes appendix : p. 131-132

Record ID

BIM-356011