Arabic Speech Recognition System Based on CMUSphinx

Author(s):  
H. Satori ◽  
M. Harti ◽  
N. Chenfour
2021 ◽  
Vol 8 (1) ◽  
pp. 164-170
Author(s):  
Mohammad Husam Alhumsi ◽  
Saleh Belhassen

Phonetic dictionaries are regarded as pivotal components of speech recognition systems. The function of speech recognition research is to generate a machine which will accurately identify and distinguish the normal human speech from any other speaker. Literature affirmed that Arabic phonetics is one of the major problems in Arabic speech recognition. Therefore, this paper reviews previous studies tackling the challenges faced by initiating an Arabic phonetic dictionary with respect to Arabic speech recognition. It has been found that the system of speech recognition investigated areas of differences concerning Arabic phonetics. In addition, an Arabic phonetic dictionary should be initiated where the Arabic vowels’ phonemes should be considered as a component of the consonants’ phonemes. Thus, the incorporation of developed machine translation systems may enhance the quality of the system. The current paper concludes with the existing challenges faced by Arabic phonetic dictionary.


2017 ◽  
Vol 20 (4) ◽  
pp. 937-949 ◽  
Author(s):  
Mohamed O. M. Khelifa ◽  
Yahya Mohamed Elhadj ◽  
Yousfi Abdellah ◽  
Mostafa Belkasmi

2009 ◽  
Vol 2 (4) ◽  
pp. 67-80 ◽  
Author(s):  
Mohamed Ali ◽  
Moustafa Elshafei ◽  
Mansour Al-Ghamdi ◽  
Husni Al-Muhtaseb

Phonetic dictionaries are essential components of large-vocabulary speaker-independent speech recognition systems. This paper presents a rule-based technique to generate phonetic dictionaries for a large vocabulary Arabic speech recognition system. The system used conventional Arabic pronunciation rules, common pronunciation rules of Modern Standard Arabic, as well as some common dialectal cases. The paper gives in detail an explanation of these rules as well as their formal mathematical presentation. The rules were used to generate a dictionary for a 5.4 hour corpus of broadcast news. The rules and the phone set were tested and evaluated on an Arabic speech recognition system. The system was trained on 4.3 hours of the 5.4 hours of Arabic broadcast news corpus and tested on the remaining 1.1 hours. The phonetic dictionary contains 23,841 definitions corresponding to about 14232 words. The language model contains both bi-grams and tri-grams. The Word Error Rate (WER) came to 9.0%.


Sign in / Sign up

Export Citation Format

Share Document