文本转语音系统与媒体应用概述
An overview of text-to-speech systems and media applications
AI总结：
本文概述了基于深度学习的文本转语音（TTS）系统，分析了其关键组件，对比了多种先进系统，并指出Tacotron 2等是最成功的TTS系统，最后提出了针对预期应用的开发建议。
摘要：
生成类似人类声音的合成语音是现代交互式媒体系统的一项新兴新奇功能。文本转语音（TTS）系统试图通过文本输入生成合成且逼真的声音。此外，通过利用 TTS 和语音转换（VC）算法，任何媒体组织所拥有的知名且熟悉的配音、播音和旁白声音等宝贵资产都可以被永久保存。深度学习方法的出现使得此类 TTS 系统变得更加准确和易于获取。为了更好地理解 TTS 系统，本文研究了此类系统的关键组件，包括文本分析、声学建模和声码器。随后，本文详细介绍了基于深度学习的重要的、最先进的 TTS 系统。最后，对最近发布的系统在主干架构、输入和转换类型、使用的声码器以及主观评估（MOS）方面进行了比较。因此，Tacotron 2、Transformer TTS、WaveNet 和 FastSpeech 1 是有史以来发布的最为成功的 TTS 系统。在讨论部分，提出了一些关于针对预期应用开发 TTS 系统的建议。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
