Arabic Mispronunciation Recognition System Using LSTM Network
The Arabic language has always been an immense source of attraction to various people from different ethnicities by virtue of the significant linguistic legacy that it possesses. Consequently, a multitude of people from all over the world are yearning to learn it. However, people from different moth...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/7/413 |
| _version_ | 1827732879949430784 |
|---|---|
| author | Abdelfatah Ahmed Mohamed Bader Ismail Shahin Ali Bou Nassif Naoufel Werghi Mohammad Basel |
| author_facet | Abdelfatah Ahmed Mohamed Bader Ismail Shahin Ali Bou Nassif Naoufel Werghi Mohammad Basel |
| author_sort | Abdelfatah Ahmed |
| collection | DOAJ |
| description | The Arabic language has always been an immense source of attraction to various people from different ethnicities by virtue of the significant linguistic legacy that it possesses. Consequently, a multitude of people from all over the world are yearning to learn it. However, people from different mother tongues and cultural backgrounds might experience some hardships regarding articulation due to the absence of some particular letters only available in the Arabic language, which could hinder the learning process. As a result, a speaker-independent and text-dependent efficient system that aims to detect articulation disorders was implemented. In the proposed system, we emphasize the prominence of “speech signal processing” in diagnosing Arabic mispronunciation using the Mel-frequency cepstral coefficients (MFCCs) as the optimum extracted features. In addition, long short-term memory (LSTM) was also utilized for the classification process. Furthermore, the analytical framework was incorporated with a gender recognition model to perform two-level classification. Our results show that the LSTM network significantly enhances mispronunciation detection along with gender recognition. The LSTM models attained an average accuracy of 81.52% in the proposed system, reflecting a high performance compared to previous mispronunciation detection systems. |
| first_indexed | 2024-03-11T00:59:14Z |
| format | Article |
| id | doaj.art-f61f333bf6694ce995ad86984c6faafa |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T00:59:14Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-f61f333bf6694ce995ad86984c6faafa2023-11-18T19:47:18ZengMDPI AGInformation2078-24892023-07-0114741310.3390/info14070413Arabic Mispronunciation Recognition System Using LSTM NetworkAbdelfatah Ahmed0Mohamed Bader1Ismail Shahin2Ali Bou Nassif3Naoufel Werghi4Mohammad Basel5Department of Electrical and Computer Engineering, Khalifa University of Science Technology and Research, Abu Dhabi 127788, United Arab EmiratesDepartment of Electrical Engineering, University of Sharjah, Sharjah 27272, United Arab EmiratesDepartment of Electrical Engineering, University of Sharjah, Sharjah 27272, United Arab EmiratesDepartment of Computer Engineering, University of Sharjah, Sharjah 27272, United Arab EmiratesDepartment of Electrical and Computer Engineering, Khalifa University of Science Technology and Research, Abu Dhabi 127788, United Arab EmiratesDepartment of Computer Engineering, University of Sharjah, Sharjah 27272, United Arab EmiratesThe Arabic language has always been an immense source of attraction to various people from different ethnicities by virtue of the significant linguistic legacy that it possesses. Consequently, a multitude of people from all over the world are yearning to learn it. However, people from different mother tongues and cultural backgrounds might experience some hardships regarding articulation due to the absence of some particular letters only available in the Arabic language, which could hinder the learning process. As a result, a speaker-independent and text-dependent efficient system that aims to detect articulation disorders was implemented. In the proposed system, we emphasize the prominence of “speech signal processing” in diagnosing Arabic mispronunciation using the Mel-frequency cepstral coefficients (MFCCs) as the optimum extracted features. In addition, long short-term memory (LSTM) was also utilized for the classification process. Furthermore, the analytical framework was incorporated with a gender recognition model to perform two-level classification. Our results show that the LSTM network significantly enhances mispronunciation detection along with gender recognition. The LSTM models attained an average accuracy of 81.52% in the proposed system, reflecting a high performance compared to previous mispronunciation detection systems.https://www.mdpi.com/2078-2489/14/7/413artificial intelligencedeep learninglong short-term memoryMel-frequency cepstral coefficientspronunciation errorrecurrent neural network |
| spellingShingle | Abdelfatah Ahmed Mohamed Bader Ismail Shahin Ali Bou Nassif Naoufel Werghi Mohammad Basel Arabic Mispronunciation Recognition System Using LSTM Network Information artificial intelligence deep learning long short-term memory Mel-frequency cepstral coefficients pronunciation error recurrent neural network |
| title | Arabic Mispronunciation Recognition System Using LSTM Network |
| title_full | Arabic Mispronunciation Recognition System Using LSTM Network |
| title_fullStr | Arabic Mispronunciation Recognition System Using LSTM Network |
| title_full_unstemmed | Arabic Mispronunciation Recognition System Using LSTM Network |
| title_short | Arabic Mispronunciation Recognition System Using LSTM Network |
| title_sort | arabic mispronunciation recognition system using lstm network |
| topic | artificial intelligence deep learning long short-term memory Mel-frequency cepstral coefficients pronunciation error recurrent neural network |
| url | https://www.mdpi.com/2078-2489/14/7/413 |
| work_keys_str_mv | AT abdelfatahahmed arabicmispronunciationrecognitionsystemusinglstmnetwork AT mohamedbader arabicmispronunciationrecognitionsystemusinglstmnetwork AT ismailshahin arabicmispronunciationrecognitionsystemusinglstmnetwork AT alibounassif arabicmispronunciationrecognitionsystemusinglstmnetwork AT naoufelwerghi arabicmispronunciationrecognitionsystemusinglstmnetwork AT mohammadbasel arabicmispronunciationrecognitionsystemusinglstmnetwork |