INTEGRATING APPLIED LINGUISTICS WITH ARTIFICIAL INTELLIGENCE-ENABLED ARABIC TEXT-TO-SPEECH SYNTHESIZER
Abstract
Currently, Text-to-Speech (TTS) or speech synthesis, the ability of the complex system to generate a human-like sounding voice from the written text, is becoming increasingly popular in speech processing in various complex systems. TTS is the artificial generation of human speech. A classical TTS system translates a language text into a waveform. Several English TTS systems produce human-like, mature, and natural speech synthesizers. On the other hand, other languages, such as Arabic, have just been considered. The present Arabic speech synthesis solution is of low quality and slow, and the naturalness of synthesized speech is lower than that of English synthesizers. Also, they lack crucial primary speech factors, including rhythm, intonation, and stress. Several studies have been proposed to resolve these problems, integrating using concatenative techniques like parametric or unit selection methods. This paper proposes an Applied Linguistics with Artificial Intelligence-Enabled Arabic Text-to-Speech Synthesizer (ALAI-ATTS) model. This ALAI-ATTS technique includes three essential components: data preprocessing through phonetization and diacritization, Extreme Learning Machine (ELM)-based speech synthesis, and Grey Wolf Fractals Optimization (GWO)-based parameter tuning. Initially, the data preprocessing step includes diacritization, where diacritics are restored to unvoweled text to ensure correct pronunciation, followed by phonetization, translating the text into its phonetic representation. Then, the ELM-based speech synthesis model uses the processed dataset for speech generation. ELMs, well known for their excellent generalization performance and fast learning speed, are especially suitable for real-time TTS applications, balancing high-quality speech output and computational efficiency. Lastly, the GWO methodology is employed to tune the parameters of the ELM. The simulation outcomes validate that the ALAI-ATTS technique considerably enhances the intelligibility and naturalness of Arabic synthesized speech compared to existing approaches. The experimental results of the ALAI-ATTS technique portrayed a lesser value of 3.48, 0.15 and 1.37, 0.25 under WER and DER.
