Note: this article is intended as a broad and high-level overview of the process of creating a custom speech synthesis pipeline. An in-depth tutorial is planned for a foreseeable future. It was a cold October day as I was casually browsing the web. While wasting my time, not sure of what my next project was going to be, I stumbled upon a speech synthesis idea. The last time I tried messing around with such technology was probably in 2013.

Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive TTS, etc. We further summarize resources related to TTS (e.g., datasets, opensource implementations) and discuss future research directions.