Data Augmentation for Arabic Speech Recognition Based on End-to-End Deep Learning | ||
| International Journal of Intelligent Computing and Information Sciences | ||
| Article 4, Volume 21, Issue 2, July 2021, Pages 50-64 PDF (904.89 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/ijicis.2021.73581.1086 | ||
| Authors | ||
| Hamzah Alsayadi* 1; Abdelaziz Abdelhamid2; Islam Hegazy3; Zaki Taha4 | ||
| 1Department of Computer science, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt | ||
| 2Department of Computer science, Faculty of Computer and Information Sciences,Ain Shams University, Cairo, Egypt | ||
| 3Faculty of Computer and Information Sciences | ||
| 4Faculty of Computers and Information Sciences, Ain Shams University | ||
| Abstract | ||
| End-to-end deep learning approach has greatly enhanced the performance of speech recognition systems. With deep learning techniques, the overfitting stills the main problem with a little data. Data augmentation is a suitable solution for the overfitting problem, which is adopted to improve the quantity of training data and enhance robustness of the models. In this paper, we investigate data augmentation method for enhancing Arabic automatic speech recognition (ASR) based on end-to-end deep learning. Data augmentation is applied on original corpus for increasing training data by applying noise adaptation, pitch-shifting, and speed transformation. An CNN-LSTM and attention-based encoder-decoder method are included in building the acoustic model and decoding phase. This method is considered as state-of-art in end-to-end deep learning, and to the best of our knowledge, there is no prior research employed data augmentation for CNN-LSTM and attention-based model in Arabic ASR systems. In addition, the language model is built using RNN-LM and LSTM-LM methods. The Standard Arabic Single Speaker Corpus (SASSC) without diacritics is used as an original corpus. Experimental results show that applying data augmentation improved word error rate (WER) when compared with the same approach without data augmentation. The achieved average reduction in WER is 4.55%. | ||
| Keywords | ||
| Arabic Speech Recognition; Data Augmentation; CNN-LSTM; RNN-LM; Attention-based Model | ||
|
Statistics Article View: 833 PDF Download: 1,634 |
||
