Arabic and English speech synthesis system

مقدم أطروحة جامعية

Ibrahim, Ibrahim Muhammad

الجامعة

الجامعة التكنولوجية

الكلية

-

القسم الأكاديمي

قسم علوم الحاسوب

دولة الجامعة

العراق

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

1999

الملخص الإنجليزي

Speech synthesizers for computer voice outputs are most useful when not restricted to a presorted vocabulary.

The simplest approach to unrestricted text-to-speech translation uses a small set of conversion rules, each specifying a pronunciation for one or more letters in some context.

This thesis which is a design of speech synthesis system based on two of speech synthesis methods that have been designed.

A synthesis by rule (Arabic and English text-to-speech) is obtained with its algorithm for synthesizing speech from written text, using stored phonemes for English text-to-speech as a synthesis unit, and new method, which depends on the combinations of consonant-vowel (Of) synthesis unit for Arabic text-to-speech which proved its success for a some stored syllables and nodes that can be developed for all words of Arabic language.

The second method presented in this thesis is the analysis-synthesis method (linear prediction analysis & synthesizer), the new method for synthesizing a reasonable quality speech using mapping method for excitation n gen era ton to speech.

This system was implemented on IBM compatible computer, 486 DX4-100MHz with a sound blaster support using Turbo Pascal 1.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-306358