Adaptation of acoustic and language model for improving Arabic automatic speech recognition
Other Title(s)
مواءمة النموذج الصوتي و اللغوي لزيادة فاعلية التعرف التلقائي على المنطوق العربي
Dissertant
Thesis advisor
Comitee Members
al-Attar, Ashraf Muhammad
Radi, Muhammad Abd al-Latif
University
Islamic University
Faculty
Faculty of Information Technology
University Country
Palestine (Gaza Strip)
Degree
Master
Degree Date
2016
English Abstract
Automatic Speech Recognition (ASR) is translation of spoken words into text by computer.
ASR technology has been widely integrated into many systems.
However, Arabic speech recognition applications still suffer from high error rate, which is mainly due to a variation in speech.
Variation in speech leads to a mismatch between the Arabic speech and the trained models.
Variation in speech is a major problem in improving the accuracy of Arabic automatic continuous speech recognition applications.
Variability may occur at the phonetic, word, or sentence level.
In this thesis, the researcher proposes an approach to adapt acoustic model and language model under limited resource for Arabic speakers.
A preliminary work on pronunciation model has also been carried out.
Arabic acoustic modeling has been proposed to overcome the variation in speech under limited resource for Arabic speakers.
In our case, if there are several Arabic acoustic models available, we can propose a hybrid approach of interpolation and merging of acoustic model for adapting the target acoustic model.
The proposed approaches have proven to be very effective to handle the variability existing in the Arabic speech.
The Word Error Rate (WER) was measured for both systems.
It was found that the baseline system has the WER equals 13.28% which was significantly decreased to 11.04% in the Enhanced system.
Besides, the researcher proposed interpolation approach for adapting the Arabic language model.
The results showed that the baseline system has the WER equals 12.4% which significantly declined to 8.4% in the Enhanced system.
In addition, the results showed that applying the hybrid of acoustic approach followed by interpolation language approach achieved considerable improvement of 5.32% in the WER.
The baseline system has the WER equals 13.28% which was significantly reduced to 7.96% in the Enhanced system.
However, the proposed phonetic rules in pronunciation model did not lead to a significant improvement.
Main Subjects
Information Technology and Computer Science
No. of Pages
90
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Literature review.
Chapter Three : Related work.
Chapter Four : Methodology.
Chapter Five : Experiments and evaluation.
Chapter Six : Conclusions and future works.
References.
American Psychological Association (APA)
Inshasi, Usamah Sulayman Ali. (2016). Adaptation of acoustic and language model for improving Arabic automatic speech recognition. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-688753
Modern Language Association (MLA)
Inshasi, Usamah Sulayman Ali. Adaptation of acoustic and language model for improving Arabic automatic speech recognition. (Master's theses Theses and Dissertations Master). Islamic University. (2016).
https://search.emarefa.net/detail/BIM-688753
American Medical Association (AMA)
Inshasi, Usamah Sulayman Ali. (2016). Adaptation of acoustic and language model for improving Arabic automatic speech recognition. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-688753
Language
English
Data Type
Arab Theses
Record ID
BIM-688753
