Producing synthetic voice, similar to human-like sound, is an emerging novelty of modern interactive media systems. Text-To-Speech (TTS) systems try to generate synthetic and authentic voices via text input. Besides, well known and familiar dubbing, announcing and narrating voices, as valuable possessions of any media organization, can be kept forever by utilizing TTS and Voice Conversion (VC) algorithms . The emergence of deep learning approaches has made such TTS systems more accurate and accessible. To understand TTS systems better, this paper investigates the key components of such systems including text analysis, acoustic modelling and vocoding. The paper then provides details of important state-of-the-art TTS systems based on deep learning. Finally, a comparison is made between recently released systems in term of backbone architecture, type of input and conversion, vocoder used and subjective assessment (MOS). Accordingly, Tacotron 2, Transformer TTS, WaveNet and FastSpeech 1 are among the most successful TTS systems ever released. In the discussion section, some suggestions are made to develop a TTS system with regard to the intended application.

翻译：生成与人类语音相似的合成声音，已成为现代交互式媒体系统的新颖特性。文本转语音（TTS）系统旨在通过文本输入生成合成且逼真的语音。此外，作为任何媒体组织宝贵资产的知名配音、播报与解说声音，可通过TTS与语音转换（VC）算法永久保存。深度学习方法的出现使此类TTS系统更加精确且易于使用。为深入理解TTS系统，本文研究了其关键组件，包括文本分析、声学建模与声码器。随后，本文详细阐述了基于深度学习的重要前沿TTS系统。最后，针对近期发布的系统，从骨干架构、输入与转换类型、所采用声码器及主观评估（MOS）等方面进行了对比。据此，Tacotron 2、Transformer TTS、WaveNet及FastSpeech 1位列迄今最成功的TTS系统。在讨论部分，本文针对目标应用场景提出了开发TTS系统的若干建议。