Author: Mohamed Hassan ,Mohamed./ Title: Automatic Speech Annotation Using HMM Based on Wavelet<br>Packets Best Tree Encoding /

Search In this Thesis

العنوان

Automatic Speech Annotation Using HMM Based on Wavelet
Packets Best Tree Encoding /

المؤلف

Mohamed Hassan ,Mohamed.

هيئة الاعداد

باحث / Mohamed Hassan Mohamed

مشرف / Amr Mohamed Refat Gody

مشرف / Rania Ahmed Aboul Seoud

مناقش / Salwa Hussein El Ramly

مناقش / Abdelfatah Ahmed Sheta

الموضوع

electric waves electric wavelet Hidden Markov models. Electrical engineering & applied signal processing.

تاريخ النشر

2013.

عدد الصفحات

177 p. :

اللغة

الإنجليزية

الدرجة

ماجستير

التخصص

الهندسة

تاريخ الإجازة

21/5/2013

مكان الإجازة

جامعة الفيوم - كلية الهندسة - Electronics and Communication Department.

الفهرس

Only 14 pages are availabe for public view

from

177

from

177

Abstract

Manual annotation for tim-aligning a speech waveform against the corresponding phonetic sequence is a time consuming task.THis research aimed to introduce a completely automated arabic isolated phone speakers independent recognition system. based on wavelet packets best tree encoding feature (WPBTE)is used to find phoneme boundaries along speech utterance. comparison to mel-frequency cepstral coefficients (MFCCS) speech feature in solving the same problem is provided. hidden markov model and gaussian mixture are used for building the statistical models through this research .HTK software toolkit is utilized for implementation of the model.