ارسل ملاحظاتك

ارسل ملاحظاتك لنا







الرئيسية > Arabic Speech Recognition Syst...>الوصف

Arabic Speech Recognition System Trough VQLBG Algorithm Using Matlab

المصدر: مجلة الجامعة الوطنية
الناشر: الجامعة الوطنية
المؤلف الرئيسي: Al Baraq, Mowaffak O. A. (Author)
المجلد/العدد: ع11
محكمة: نعم
الدولة: اليمن
التاريخ الميلادي: 2020
الشهر: فبراير
الصفحات: 1 - 20
DOI: 10.46514/1971-000-011-007
ISSN: 2519-6022
رقم MD: 1045171
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: EduSearch, HumanIndex
مواضيع:
الكلمة العربية | اللغة العربية | اللغات
كلمات المؤلف المفتاحية:
A Rectangular Window | ASR System | Feature Extraction | Arabic Word | NLP | DTW | FFT | Mel Frequency Scale | Mel Power Spectrum | MFCC | CodeBook | VQLBG and Euclidean Distances Algorithm
رابط المحتوى:
PDF (صورة)     
صورة الغلاف QR قانون

عدد مرات التحميل

5

حفظ في:
المستخلص: rectangular window techniques has been used for segmentation of the Arabic Speech uttered words to atomic or sub atomic samples. Real time Arabic Speech Recognition system has been developed for introducing recognition of the uttered Arabic words instantly after the utterance. This paper introduces a unique technique making interaction of human with a computer for natural language processing which is basically a speech recognition system. In this paper 100 Arabic voice samples were recorded through a microphone and the system was trained according to the recoded voice samples. MFCC features of speech sample were calculated, Vector Quantization for mapping large feature vectors to finite cluster codewords, build trained codebook model for each word and Euclidean Distances used for recognition word according to distortions associated with each features. This system provides a high accuracy in case of Arabic speech words.
ISSN: 2519-6022

عناصر مشابهة


© 2024 المنظومة. جميع الحقوق محفوظة.