In spoken language processing, text-to-speech synthesis refers to the process of converting written text into spoken words and sentences. This technology is used in various applications such as voice assistants, audiobooks, and automated customer service systems. The [[traditional TTS pipeline approach]] involves several steps including text analysis, linguistic processing, acoustic modeling, and the generation of the speech waveform. With recent advancements in deep learning techniques, text-to-speech synthesis has become more accurate and natural-sounding than ever before. Advances in deep learning and neural network architectures have led to the recent development and increasing popularity of end-to-end models for text-to-speech (TTS) synthesis, which streamline the process of generating the speech waveform directly from text, by integrating all necessary steps.