Arabic isolated word recognition system using hybrid feature extraction techniques and neural network

Boussaid, Lotfi; Hassine, Mohamed Ali Ben

doi:10.1007/s10772-017-9480-7

Cited by 21 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1. Evaluation of our proposed model compared to other models Models Accuracy Dataset type [21] 97.8% 10 Isolated Arabic Words [22] 94.39% -94.56% 40 Arabic words [23] Used Error rate 0.68% 11 standard Arabic isolated words [24] 71.75% 3 Arabic isolated words [25] 58.4% -76.7% 29 isolated Arabic Letters Our developed model 97.99% Impairments children Dataset contains 0-9 and 8 Arabic Letters…”

Section: Resultsmentioning

confidence: 99%

“…The system uses a voting mechanism to merge the method outputs. While the mean calculation time is 1.56 seconds and the accuracy of the system increased [23], system was built for 11 common Arabic isolated words with a speech recognition system. During the extraction stage several methods have been employed, including cepstral coefficients for the mel frequency (MLF), linear perceptual prediction, linear perceptual prediction and time derivatives in their initial order.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Towards developing impairments arabic speech dataset using deep learning

Shareef

Al-Irhayim

2022

IJEECS

View full text Add to dashboard Cite

<span>The effective and efficient recognition of speech sounds errors for impaired children is important if a defective phonological process is early detected and corrected. This study deals with the topic of classification of speech sound errors in Arabic impairments children when Arabic letters and numbers are incorrectly pronounced. For 18 standard Arabic isolated numerals and characters, we created an impaired children speech recognition system. We utilized the Mel frequency cepstral coefficients throughout the feature extraction step. then deep long short-term memory network recognition phase. We used the developed model with the developed dataset and the classification accuracy was 97.99% and lose 0.18%, additionally, the results have been compared and yielded extremely intriguing results with previously existing recognition rates models.</span>

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Towards developing impairments arabic speech dataset using deep learning

Shareef

Al-Irhayim

2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…It was then used to programmatically realize speech recognition for specific speech instances, as well as write speech recognition functions into functions that can be called by other modules. Additionally, it was used to implement a speech recognition system foundation, and to cultivate and improve the ability of the system to consult the literature and comprehensively use new knowledge [ 1 ].…”

Section: Methodsmentioning

confidence: 99%

Application of an Isolated Word Speech Recognition System in the Field of Mental Health Consultation: Development and Usability Study

2020

JMIR Med Inform

View full text Add to dashboard Cite

Background Speech recognition is a technology that enables machines to understand human language. Objective In this study, speech recognition of isolated words from a small vocabulary was applied to the field of mental health counseling. Methods A software platform was used to establish a human-machine chat for psychological counselling. The software uses voice recognition technology to decode the user's voice information. The software system analyzes and processes the user's voice information according to many internal related databases, and then gives the user accurate feedback. For users who need psychological treatment, the system provides them with psychological education. Results The speech recognition system included features such as speech extraction, endpoint detection, feature value extraction, training data, and speech recognition. Conclusions The Hidden Markov Model was adopted, based on multithread programming under a VC2005 compilation environment, to realize the parallel operation of the algorithm and improve the efficiency of speech recognition. After the design was completed, simulation debugging was performed in the laboratory. The experimental results showed that the designed program met the basic requirements of a speech recognition system.

show abstract

“…Many new techniques have been proposed to improve MT for example manage the results of rare words, various attention mechanisms [13] and minimize sentence loss. Some tecent works also have especially dealt with domain adaptation for NMT by providing meta-information to the neural network.…”

Section: Introductionmentioning

confidence: 99%

DIA-English-Arabic neural machine translation domain: sulfur industry

Hameed

Faisal

Abbas

et al. 2022

IJEECS

View full text Add to dashboard Cite

The aim of this paper is the design and development a new English-Arabic neural machine translation (NMT) called DIA translation system. The main purpose of the designing system is to study translator limited sulfur industry domain as a stand-alone tool in order to improve the translation quality. Machine translation (MT) are very sensitive to the domains they were trained on and can be integrated with general (English-Arabic) MT systems. The proposed system has mainly four directions: supports chemical symbols, terms, phrase, and text and it is evaluated by using (1,200) various English declarative sentences which written by English Language experts. The obtained results indicate that this system is high effective and has an accuracy of 79.33% in comparison with Google translator which has 38.67% for the same test samples.

show abstract

Arabic isolated word recognition system using hybrid feature extraction techniques and neural network

Cited by 21 publications

References 6 publications

Towards developing impairments arabic speech dataset using deep learning

Towards developing impairments arabic speech dataset using deep learning

Application of an Isolated Word Speech Recognition System in the Field of Mental Health Consultation: Development and Usability Study

DIA-English-Arabic neural machine translation domain: sulfur industry

Contact Info

Product

Resources

About