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

点击翻译按钮获取中文摘要

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.