Home/International Journal of Intelligent Computing and Information Sciences/Article Record
Peer-Reviewed Article July 18, 2021

Data Augmentation for Arabic Speech Recognition Based on End-to-End Deep Learning

Are you an author of this work?Link to your sovereign AfriScholar profile
Published in: International Journal of Intelligent Computing and Information Sciences
Publisher: Ain Shams University, Faculty of Computer and Information Science • Egypt • 1687-109X • 2535-1710
DOI: https://doi.org/10.21608/ijicis.2021.73581.1086

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%.

Download Full Text PDFView at PublisherCrossref RecordCrossref XML

Verified Citation Velocity

Recorded scholarly citations in African and international peer-reviewed literature

23
Total Citations

Citations are continuously tracked and harvested across continental OJS endpoints and OpenAlex feeds.