Deep Learning Methods for Arabic Autoencoder Speech Recognition System for Electro-Larynx Device

Abstract

Recent advances in speech recognition have achieved remarkable performance comparable with human transcribers’ abilities. But this significant performance is not the same for all the spoken languages. The Arabic language is one of them. Arabic speech recognition is bounded to the lack of suitable datasets. Artificial intelligence algorithms have shown promising capabilities for Arabic speech recognition. Arabic is the official language of 22 countries, and it has been estimated that 400 million people speak the Arabic language worldwide. Speech disabilities have been one of the expanding problems in the last decades, even in kids. Some devices can be used to generate speech for those people. One of these devices is the Servox Digital Electro-Larynx (EL). In this research, we developed an autoencoder with a combination of long short-term memory (LSTM) and gated recurrent units (GRU) models to recognize recorded signals from Servox Digital EL Electro-Larynx. The proposed framework consisted of three steps: denoising, feature extraction, and Arabic speech recognition. The experimental results show 95.31% accuracy for Arabic speech recognition with the proposed model. In this research, we evaluated different combinations of LSTM and GRU for constructing the best autoencoder. A rigorous evaluation process indicates better performance with the use of GRU in both encoder and decoder structures. The proposed model achieved a 4.69% word error rate (WER). Experimental results confirm that the proposed model can be used for developing a real-time app to recognize common Arabic spoken words.

Arabic Speech Recognition: Advancement and Challenges

“…Recently, Mohammed and Abdulkareem [38] to identify documented signals from the Servox Digital EL Electro-Larynx developed an autoencoder that combines LSTM and GRU models. There were three steps in the proposed framework: denoising, feature extraction, and Arabic speech recognition.…”

Exploring the Impact of Mismatch Conditions, Noisy Backgrounds, and Speaker Health on Convolutional Autoencoder-Based Speaker Recognition System with Limited Dataset

“…The system utilizes MFCCs as input, achieving high accuracy rates with potential applications in security, surveillance, and forensics. The authors recommend modifications to the deep learning model for increased accuracy.In the context of communication aids, [14] presents a deep learning-based Arabic autoencoder speech recognition system for electrolarynx devices. The proposed system addresses challenges of noise and limited data, outperforming other models in terms of accuracy and robustness.…”

DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic

“…The Arabic language, with approximately 400 million speakers across the globe, stands as the fifth most widely spoken language worldwide (Mohammed Ameen et al, 2023). Its vast linguistic diversity, rooted in rich historical and regional variations, necessitates continuous advancements in the field of natural language processing (NLP) (Abdul-Mageed et al, 2020).…”