Helpful Statistics in Recognizing Basic Arabic Phonemes
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 2
Abstract
The recognition of continuous speech is one of the main challenges in the building of automatic speech recognition (ASR) systems, especially when it comes to phonetically complex languages such as Arabic. An ASR system seems to be actually in a blocked alley. Nearly all solutions follow the same general model. The previous research focused on enhancing its performance by incorporating supplementary features. This paper is part of ongoing research efforts aimed at developing a high-performance Arabic speech recognition system for learning and teaching purposes. It investigates a statistical analysis of certain distinctive features of the basic Arabic phonemes which seems helpful in enhancing the performance of a baseline HMM-based ASR system. The statistics are collected using a particular Arabic speech database, which involves ten different male speakers and more than eight hours of speech which covers all Arabic phonemes. In HMM modeling framework, the statistics provided are helpful in establishing the appropriate number of HMM states for each phoneme and they can also be utilized as an initial condition for the EM estimation procedure, which generally, accelerates the estimation process and, thus, improves the performance of the system. The obtained findings are presented and possible applications of automatic speech recognition and speaker identification systems are also suggested.
Authors and Affiliations
Mohamed O. M. Khelifa, Yousfi Abdellah, Yahya O. M. ElHadj, Mostafa Belkasmi
Keywords
Related Articles
- EP ID EP249145
- DOI 10.14569/IJACSA.2017.080231
- Views 128
- Downloads 0
Comprehensive Centralized-Data Warehouse for Managing Malaria Cases
Tanah Bumbu is one of the most endemic areas in Indonesia for patients diagnosed with malaria diseases. Currently, available malaria case data were stored in disparate sources. Hence, it is difficult for the public healt...
Securely Eradicating Cellular Dependency for E-Banking Applications
Numerous applications are available on the Internet for the exchange of personal information and money. All these applications need to authenticate the users to confirm their legitimacy. Currently, the most commonly empl...
E-learning System Which Allows Students’ Confidence Level Evaluation with Their Voice When They Answer to the Questions During Achievement Tests
E-learning system which allows students’ confidence level evaluation with their voice when they answer to the question during achievement tests is proposed. Through experiments of comparison of students’ confidence level...
Defense Mechanisms against Machine Learning Modeling Attacks on Strong Physical Unclonable Functions for IOT Authentication: A Review
Security component in IoT system are very crucial because the devices within the IoT system are exposed to numerous malicious attacks. Typical security components in IoT system performs authentication, authorization, mes...
Efficient Software Testing Technique based on Hybrid Database Approach
In the field of computer science, software testing is referred as a critical process which is executed in order to assess and analyze the performance and risks existing in software applications. There is an emphasis on i...