Presidential Young Investigator Award (PYI): Computer Research

总统青年研究员奖（PYI）：计算机研究

• 批准号: 8858109
• 负责人: Mary Beckman
• 金额: $ 23.06万
• 依托单位: Ohio State University Research Foundation -DO NOT USE
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1988
• 资助国家: 美国
• 起止时间: 1988-09-01 至 1995-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8858109&HistoricalAwards=false
• 关键词: Presidential; Young; Investigator; Award; PYI

This Presidential Young Investigator Award is for support of Mary Beckman at the Ohio State University. Her research is aimed at understanding and modeling the prosodic patterns which organize speech into coherent units of sound. Earlier work, including most exisitng speech synthesis systems and all speech recognition systems, is based on linguistic theories from the 1960s, which posited only a single type of organizational unit, the phonetic segment, which constituted the informational primitives. More recently, however, linguists have recognized that the prosodic patterns of intonation and stress organize speech into units of various sizes. A computational model based on those theories would take advantage of the way prosodic patterns encode a hierarchy of phonological words and phrases. Such a model would make constructive use of the variation in spectral patterning that accrues from a segment's position in the organizational structure to recover the higher-level informational structure. The significance of this work is that it should yield a computational model for timing patterns that will be implemented in an articulatory synthesis program and ultimately will be incorporated into an automatic speech recognition system, thus bringing a new set of tools to bear on a difficult problem area.

这个总统青年研究员奖是为了支持 玛丽贝克曼在俄亥俄州州立大学。 她的研究旨在 在理解和模拟韵律模式， 把语音组织成连贯的声音单位。 早期的工作，包括大多数语音合成 系统和所有的语音识别系统，是基于 20世纪60年代的语言学理论， 一种组织单位，即语音段， 构成了信息原语。 然而，最近，语言学家已经认识到， 语调和重音的韵律模式将语音组织成 各种尺寸的单位。 一个基于这些的计算模型 理论会利用韵律模式编码的方式 语音单词和短语的等级。 这样的模型 将建设性地利用光谱的变化， 图案，从一个部分的位置， 组织结构，以恢复更高层次的 信息结构 这项工作的意义在于它应该产生一个 将实施的定时模式的计算模型 在发音合成程序中， 结合到自动语音识别系统中，因此 带来一套新的工具来解决一个困难的问题。