Arabic Speech Recognition System Based on CMUSphinx

Satori, Hassan; Harti, Mostafa; Chenfour, Nouredine

doi:10.1109/isciii.2007.367358

Cited by 40 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Arabic is the native language for over 300 million speakers and considered one of the official languages in many countries around the world. It has a unique set of diacritics that can change the meaning [4]. Arabic ASR received little attention compared to other languages, and research was oblivious to the diacritics in most cases.…”

Section: Introductionmentioning

confidence: 99%

Arabic Speech Recognition System Based on MFCC and HMMs

Elharati¹,

Alshaari²,

Këpuska³

2020

JCC

View full text Add to dashboard Cite

Speech recognition allows the machine to turn the speech signal into text through identification and understanding process. Extract the features, predict the maximum likelihood, and generate the models of the input speech signal are considered the most important steps to configure the Automatic Speech Recognition System (ASR). In this paper, an automatic Arabic speech recognition system was established using MATLAB and 24 Arabic words Consonant-Vowel Consonant-Vowel Consonant-Vowel (CVCVCV) was recorded from 19 Arabic native speakers, each speaker uttering the same word 3 times (total 1368 words). In order to test the system, 39-features were extracted by partitioning the speech signal into frames ~ 0.25 sec shifted by 0.10 sec. in back-end, the statistical models were generated by separated the features into number of states between 4 to 10, each state has 8-gaussian distributions. The data has 48 k sample rate and 32-bit depth and saved separately in a wave file format. The system was trained in phonetically rich and balanced Arabic speech words list (10 speakers * 3 times * 24 words, total 720 words) and tested using another word list (24 words * 9 speakers * 3 times *, total 648 words). Using different speakers similar words, the system obtained a very good word recognition accuracy results of 92.92% and a Word Error Rate (WER) of 7.08%.

show abstract

Section: Introductionmentioning

confidence: 99%

Arabic Speech Recognition System Based on MFCC and HMMs

Elharati¹,

Alshaari²,

Këpuska³

2020

JCC

View full text Add to dashboard Cite

show abstract

“…Based on that, it is a necessity to enable disabled students to interact with computers in a simple and effective way. Hence, multiple software solutions were proposed with different levels of efficiency and flexibility to create a near normal interaction real time environment between disabled students and computers . Accordingly, we were motivated in this work to present a speech recognition system that helps armed‐disabled students to communicate with computers for educational applications in a simple yet flexible way and with a high accuracy ratio in implementation.…”

Section: Introductionmentioning

confidence: 99%

“…There are many methodologies, comparable in focus to our proposed work, done to enhance the recognition rate of systems that allow arm‐disable students to interact with computers. In reference , an Arabic speech recognition system was proposed utilizing open source Carnegie Melon University (CMU) Sphinx‐4 and hidden Markov models (HMM). Actually, HMM is considered as an effective statistical model.…”

Section: Introductionmentioning

confidence: 99%

An efficient speech recognition system for arm‐disabled students based on isolated words

Darabkh

Haddad

Sweidan

et al. 2017

Comp Applic In Engineering

View full text Add to dashboard Cite

Over the previous decades, a need has emerged to empower human‐machine communication systems, which are essential to not only perform actions, but also obtain information especially in education applications. Moreover, any communication system has to introduce an efficient and easy way for interaction with a minimum possible error rate. The keyboard, mouse, trackball, touch‐screen, and joystick are all examples of tools which were built to provide mechanical human‐to‐machine interaction. However, a system with the ability to use oral speech, which is the natural form of communication between humans instead of mechanical communication systems, can be more practical for normal students and even a necessity for arm‐disabled students who cannot use their arms to handle traditional education tools like pens and notebooks. In this paper, we present a speech recognition system that allows arm‐disabled students to control computers by voice as a helping tool in the educational process. When a student speaks through a microphone, the speech is divided into isolated words which are compared with a predefined database of huge number of spoken words to find a match. After that, each recognized word is translated into its related tasks which will be performed by the computer like opening a teaching application or renaming a file. The speech recognition process discussed in this paper involves two separate approaches; the first approach is based on double thresholds voice activity detection and improved Mel‐frequency cepstral coefficients (MFCC), while the second approach is based on discrete wavelet transform along with modified MFCC algorithm. Utilizing the best values for all parameters in just mentioned techniques, our proposed system achieved a recognition rate of 98.7% using the first approach, and 98.86% using the second approach of which is better in ratio than the first one but slower in processing which is a critical point for a real time system. Both proposed approaches were compared with other relevant approaches and their recognition rates were noticeably higher.

show abstract

“…Computational linguistics might be considered as a synonym of automatic processing of natural language, since the main task of computational linguistics is just the construction of computer programs to process words and texts in natural language [1]. The main objective of the spell-checker system is to flag words in a text that may not be spelled correctly [5]. This flagging process is done at the word level without considering the text context.…”

Section: Introductionmentioning

confidence: 99%

Towards Arabic Spell-Checker Based on N-Grams Scores

Muaidi¹,

Al-tarawneh²

2012

IJCA

View full text Add to dashboard Cite

The main purpose of this paper is to develop a simple and flexible spell-checker for Arabic language. The proposed spell-checker is based on N-Grams scores. For this purpose, eleven matrices are built to present the combination between the Arabic letters word. Each matrix concerns in the connection between a 2-grams letters. Each cell in the generarated matrix is assigned an integer value 2, 1 or 0. The cell is assigned the value 2 in the corresponding matrix; if the word is ended by these two letter and assigned 1 if there is a connection and the word is not over yet, and is assigned 0 otherwise. On the other side searching process for any word that is by extracting each pair of letters in the word then it examines the value for each pair when the corresponding value is zero then the spell checker will consider the test word as wrong; otherwise it will check if it is assign with 1 that indicates that there is a connection it will be continue until reach to the value of 2 to determine that the word is correct. The overall accuracy for the proposed spell-checker is reached to 98.99%.

show abstract

Arabic Speech Recognition System Based on CMUSphinx

Cited by 40 publications

References 7 publications

Arabic Speech Recognition System Based on MFCC and HMMs

Arabic Speech Recognition System Based on MFCC and HMMs

An efficient speech recognition system for arm‐disabled students based on isolated words

Towards Arabic Spell-Checker Based on N-Grams Scores

Contact Info

Product

Resources

About