Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 1245 2023-08-03 14:32:06 |
2 layout Meta information modification 1245 2023-08-04 03:02:05 | |
3 layout Meta information modification 1245 2023-09-05 10:50:04 |

Video Upload Options

Do you have a full video?

Confirm

Are you sure to Delete?
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Ahmed, A.; Bader, M.; Shahin, I.; Nassif, A.B.; Werghi, N.; Basel, M. Arabic Mispronunciation Recognition System Using LSTM Network. Encyclopedia. Available online: https://encyclopedia.pub/entry/47622 (accessed on 13 June 2024).
Ahmed A, Bader M, Shahin I, Nassif AB, Werghi N, Basel M. Arabic Mispronunciation Recognition System Using LSTM Network. Encyclopedia. Available at: https://encyclopedia.pub/entry/47622. Accessed June 13, 2024.
Ahmed, Abdelfatah, Mohamed Bader, Ismail Shahin, Ali Bou Nassif, Naoufel Werghi, Mohammad Basel. "Arabic Mispronunciation Recognition System Using LSTM Network" Encyclopedia, https://encyclopedia.pub/entry/47622 (accessed June 13, 2024).
Ahmed, A., Bader, M., Shahin, I., Nassif, A.B., Werghi, N., & Basel, M. (2023, August 03). Arabic Mispronunciation Recognition System Using LSTM Network. In Encyclopedia. https://encyclopedia.pub/entry/47622
Ahmed, Abdelfatah, et al. "Arabic Mispronunciation Recognition System Using LSTM Network." Encyclopedia. Web. 03 August, 2023.
Arabic Mispronunciation Recognition System Using LSTM Network
Edit

The widespread use of CALL (computer-assisted language learning) systems attests to their success in helping people improve their language and speech skills. CALL is predominantly concerned with addressing pronunciation errors in non-native speakers’ speech. Accurate mispronunciation detection, voice recognition, and accurate pronunciation evaluation are all activities that may be accomplished with CALL.

artificial intelligence deep learning long short-term memory Mel-frequency cepstral coefficients

1. Introduction

The widespread use of CALL (computer-assisted language learning) systems attests to their success in helping people improve their language and speech skills. CALL is predominantly concerned with addressing pronunciation errors in non-native speakers’ speech. Accurate mispronunciation detection, voice recognition, and accurate pronunciation evaluation are all activities that may be accomplished with CALL. Similarly, there are a plethora of studies on speech processing that have been implemented in numerous languages with the aim of facilitating language learning. Breakthroughs in AI and other areas of computer science have permitted extensive study of CALL. Due to the inability of their mouth muscles to articulate the intricacies of a particular language, speakers of different languages are prone to committing pronunciation problems while speaking a particular language. For this reason, academics often explore mispronunciation in English, Dutch, and French, while Arabic literary studies are scarce. However, Arabic studies have increased in recent years. Arabic, the most widely spoken language with approximately 290 million native speakers and 132 million non-native speakers, and one of the six official languages of the United Nations (UN), has two major dialects, Classical Arabic (CA) and Modern Standard Arabic (MSA). Classical Arabic is the language of the Quran, whereas Modern Standard Arabic is a modified form of the Quran used in daily conversation. In order to retain the right meaning of the phrases, the rules for pronouncing the Quranic language are quite well-defined.
Table 1 illustrates the most mispronounced Arabic letters in the field of pronunciation. Therefore, the effect of employing long short-term memory as a classifier blended with Mel-frequency cepstral coefficients as the feature extractor is observed. The LSTM network is well suited for speech recognition due to its ability to model the complex temporal relationships in speech signals, adapt to variations in the input data, and handle sequences of variable lengths.
Table 1. Most common disordered Arabic letters.

References

  1. Pengbin Fu; Daxing Liu; Huirong Yang; LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition. Inf. 2022, 13, 250.
  2. Wenxuan Ye; Shaoguang Mao; Frank Soong; Wenshan Wu; Yan Xia; Jonathan Tien; Zhiyong Wu. An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings; Institute of Electrical and Electronics Engineers (IEEE): Piscataway, NJ, United States, 2022; pp. 6827-6831.
  3. Kun Li; Xiaojun Qian; Helen Meng; Mispronunciation Detection and Diagnosis in L2 English Speech Using Multidistribution Deep Neural Networks. IEEE/ACM Trans. Audio, Speech, Lang. Process. 2016, 25, 193-207.
  4. Mostafa Shahin; Beena Ahmed; Anomaly detection based pronunciation verification approach using speech attribute features. Speech Commun. 2019, 111, 29-43.
  5. Moner N. M. Arafa; Reda Elbarougy; A. A. Ewees; G. M. Behery; A Dataset for Speech Recognition to Support Arabic Phoneme Pronunciation. Int. J. Image, Graph. Signal Process. 2018, 10, 31-38.
  6. Sura Ramzi Shareef; Yousra Faisal Muhammad Al-Irhayim; Comparison Between Features Extraction Techniques for Impairments Arabic Speech. AL-Rafdain Eng. J. (AREJ) 2022, 27, 190-197.
More
Information
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register : , , , , ,
View Times: 206
Revisions: 3 times (View History)
Update Date: 05 Sep 2023
1000/1000
Video Production Service