RI: SMALL: Modeling Voice Source Transformation in Monolingual and Crosslingual Non-parallel Voice Conversion Applications

RI：SMALL：对单语言和跨语言非并行语音转换应用中的语音源转换进行建模

• 批准号: 1116475
• 负责人: Elliot Moore
• 金额: $ 24.46万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-07-15 至 2015-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1116475&HistoricalAwards=false
• 关键词: RI; SMALL; Modeling; Voice; Source

Voice conversion (VC) systems transform segments of speech from a given source speaker so that itcan be identified as spoken by a specified target speaker. Currently, standard VC systems requireparallel training on extensively labeled sets of speech data where the source and target speaker shareequivalent content for building direct mapping models. This project builds on the concepts of nonparallelVC systems reducing the need for labeled and shared speech content between source and targetspeakers as well as allowing for both intra-lingual and cross-lingual conversion scenarios. This projectfocuses on two main areas: (1) Building a framework for non-parallel VC without explicit phonetic,sound, word, or sentence level labels, and (2) Providing effective target speaker mapping to obtainconverted speech with as good as or better quality compared to current VC systems. The VCframework consists of three main components: (1) A speaker independent language model; (2) Analgorithm for model adaptation to target speaker; (3) A speech synthesis block to generate convertedspeech from a target-adapted language model.This project will provide a broad framework for applications such as personalization of assistive textto-speech (TTS) systems, foreign language learning, and as a possible component in speech-to-speechtranslation systems. This project will support graduate student research and provide results forcommunity distribution through conference and journal submission. Additionally, an open-sourcesoftware toolset will be developed and freely distributed. The project will also be used in outreach forunderrepresented groups in Science Technology Engineering and Mathematics (STEM) disciplines.

语音转换（VC）系统转换来自给定源说话者的语音片段，以便可以将其识别为指定目标说话者所说的。目前，标准 VC 系统需要对广泛标记的语音数据集进行并行训练，其中源说话者和目标说话者共享用于构建直接映射模型的等效内容。该项目建立在非并行 VC 系统的概念之上，减少了源说话者和目标说话者之间对标记和共享语音内容的需求，并允许语言内和跨语言转换场景。该项目重点关注两个主要领域：(1) 构建一个非并行 VC 框架，无需明确的语音、声音、单词或句子级别标签，以及 (2) 提供有效的目标说话者映射，以获得质量相同或更好的转换语音与当前的 VC 系统相比。 VC框架由三个主要组件组成：（1）与说话人无关的语言模型； (2)模型适应目标说话人的算法； (3) 语音合成模块，用于从目标适应的语言模型生成转换后的语音。该项目将为辅助文本转语音 (TTS) 系统的个性化、外语学习等应用提供广泛的框架，并作为语音到语音翻译系统。该项目将支持研究生研究，并通过会议和期刊提交提供成果供社区分发。此外，还将开发并免费分发开源软件工具集。该项目还将用于科学技术工程和数学（STEM）学科中代表性不足的群体的外展活动。