RI: Small: Creating Text-to-Speech Synthesis for Low Resource Languages

最近语音技术的进步导致了语音对话系统(SDS)的广泛使用，如Siri(IPhone)和Google Assistant(Android)。这些系统支持英语、法语、普通话、日语和西班牙语等高级资源语言(HRL)的语音信息访问方面的重大改进。对于这些语言，研究人员已经构建了词典、解析器、词性标记器、语言模型、搜索引擎和机器翻译引擎来支持语音技术。然而，世界上有大约6500种语言，包括他加洛语、泰米尔语、斯瓦希里语、越南语和普什图语，其中许多语言有数百万人说，但它们并不享受构建SD所需的计算资源。这些被称为低资源语言(LRL)。LRL的发言者不能从HRL的发言者所具有的通信和搜索能力中获益。特别是，很少有研究和资源支持开发文本到语音合成(TTS)系统来为这些语言的SD产生类似Siri的语音。此外，商业和研究TTS系统还需要大量仔细记录的单人语音数据，这对LRL的TTS开发造成了另一个主要(且昂贵的)障碍。这项工作将在LRLS中创建TTS系统，并在此过程中创建并提供工具，供其他人使用“找到的”数据创建他们自己的系统--为其他目的记录的数据或在网络上可用的数据。目前正在开发TTS合成的新范例(参数合成和深度神经网络的使用)，这使得在理论上有可能在不记录大型专用语料库的情况下快速且廉价地建立系统，而是使用为其他目的记录的数据，例如训练语音识别器。这项工作将研究使用这些技术来生产用于LRL的TTS系统。将探讨两个主要问题：1)过滤发现的数据的最佳技术是什么(例如，删除太吵、太吵或不流利的数据)，以获得听起来容易理解和自然的结果？2)能否使用众包和为HRL开发的工具来识别LRL的基本韵律特征，如短语和重音？对英语的初步研究表明，通过使用根据音高变化和发音水平等特征选择的数据子集，可以创造出更自然、更容易理解的声音。这些方法将在土耳其语、阿姆哈拉语和泰卢固语等LRL上进行测试。将自动进行可理解性和自然度方面的评估，并利用以每种语言为母语的众包技术进行评估。这项探索性工作的最终目标将是在广泛的LRL上测试这些技术，这些LRL是为开发语音识别器而收集的。

Recent advances in speech technology have resulted in wide use of Spoken Dialogue Systems (SDS) such as Siri (iPhone) and Google Assistant (Android). These systems support major improvements in information access by voice for High Resource Languages (HRLs) such as English, French, Mandarin, Japanese, and Spanish. For these languages, researchers have built dictionaries, parsers, part-of-speech taggers, language models, search engines, and machine translation engines to support speech technologies. However, there are ~6500 world languages, including Tagalog, Tamil, Swahili, Vietnamese and Pashto, many of which are spoken by millions of people, but which do not enjoy the computational resources necessary to build SDS. These are termed Low Resource Languages (LRLs). Speakers of LRLs do not benefit from the same communication and search capabilities speakers of HRLs do. In particular, there is little research and few resources supporting the development of Text-to-Speech Synthesis (TTS) systems to produce Siri-like speech for SDS in these languages. Furthermore, both commercial and research TTS systems also require large amounts of carefully recorded, single-speaker speech data, creating another major (and expensive) barrier to TTS development for LRLs. This work will create TTS systems in LRLs and, in the process, create and make available tools for others to create their own systems using "found" data - data recorded for other purposes or available on the web.New paradigms for TTS synthesis (parametric synthesis and the use of Deep Neural Nets) are now being developed which make it theoretically possible to build systems quickly and cheaply without recording large, special-purpose speech corpora, instead using data recorded for other purposes such as training speech recognizers. This work will investigate the use these techniques to produce TTS systems for LRL. Two major problems will be explored: 1) What are the best techniques to filter found data (removing data that is too loud, too noisy or disfluent, for example) to obtain intelligible and natural-sounding results? 2) Can basic prosodic features of LRLs such as phrasing and emphasis be identified, using crowdsourcing and tools developed for HRLs? Pilot studies on English have revealed that more natural and intelligible voices can be created by using subsets of the data selected on features such as pitch variation and level of articulation. These methods will be tested on LRLs such as Turkish, Amharic, and Telugu. Evaluations will be made in terms of intelligibility and naturalness both automatically and using crowdsourcing techniques with native speakers of each language. The ultimate goal of this exploratory work will be to test these techniques on a broad variety of LRLs which have been collected for purposes of developing speech recognizers.