课题基金 / 基金详情

SGER: Exploring Universal Acoustic Characterization of Spoken Languages

SGER: Exploring Universal Acoustic Characterization of Spoken Languages
SGER:探索口语的普遍声学特征
批准号:
0639204
负责人:
Chin-Hui Lee
金额:
$0.0万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2006
资助国家:
美国
项目状态:
已结题
起止时间:
2006-08-15 至 2009-01-31

项目摘要

项目成果

Chin-Hui Lee的其他基金

相似基金

相关文献

中文摘要
翻译
探索口语的通用声学特征摘要我们探索了一种新的方法来对所有人类语言进行建模,假设口语的声音特征可以由一组通用的声学单位覆盖,而不是与传统的语音定义直接联系。它们对应的模型被称为声学分段模型(ASM),可以用来将所说的话语解码成这样的单元串。这些单元及其对应于特定语言的训练集中的话语的共现的统计可用于构建特征向量以构建用于自动口语识别(LID)的基于向量的语言分类器。对于口语查询,以类似的方式提取ASM派生的特征向量,然后将其用于区分个别口语。这个ASM集合可以以无人监督的方式自下而上地建立,并将作为声学字母表的模型来构建用于语音识别和语言识别的声学词典。在该项目中,我们研究了与UAC相关的三个基本问题,即:(1)建模口语所需的声学单元的声学覆盖和分辨率;(2)UAC派生的特征用于口语识别的复杂性和区分性;(3)语言线索与UAC单元的关系用于建模口语。这项研究有助于更好地理解人类通过声学和语言线索识别口语,并提供数学建模和计算技术来建立LID系统。我们还打算利用我们在另一项关于自动语音属性转录(ASAT)的NSF拨款中的研究成果,为语言特征及其与听觉感知的相关性建模显著的语音线索。整个可用的语言线索集合,包括电话、音节、单词、韵律和词汇线索,也可以结合到这种协同方法中来进行口语建模和识别。
英文摘要
Exploring Universal Acoustic Characterization of Spoken LanguagesAbstractWe explore a novel approach to modeling all human languages by assuming that the sound characteristics of spoken languages can be covered by a universal set of acoustic units with no direct link to conventional phonetic definitions. Their corresponding models, called acoustic segment models (ASMs), can be used to decode spoken utterances into strings of such units. The statistics of these units and their co-occurrences corresponding to utterances in a training set of a particular language can be used to construct feature vectors to build vector-based language classifiers for automatic spoken language identification (LID). For spoken queries, ASM-derived feature vectors are extracted in a similar manner and then used to discriminate individual spoken languages. This collection of ASMs can be established from bottom up in an unsupervised manner, and will serve as models of acoustic alphabets to construct acoustic lexicons for speech recognition and language identification. In the project we study three fundamental issues related to UAC, namely: (1) acoustic coverage and resolution of acoustic units needed to model spoken languages; (2) complexity and discriminative power of UAC-derived features for spoken language identification; and (3) relationship of language cues with UAC units for modeling spoken languages. This research facilitates a better understanding of human identification of spoken languages through acoustic and linguistic cues, and provides mathematical modeling and computing techniques to build LID systems. We also intend to leverage our research results in another NSF grant on automatic speech attribute transcription (ASAT) to model salient speech cues for language characterization and their relevance to auditory perception. The entire collection of available language cues, including phones, syllables, words, prosody, and lexical cues, can also be incorporated into this synergistic approach to spoken language modeling and identification.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
ITR-(NHS+ASE)-(int+dmc+sim) Automatic Speech Attribute Transcription (ASAT): A Collaborative Speech Research Paradigm and Cyberinfrastructure with Applications to Automatic Speech
  • 批准号:
    0427413
  • 项目类别:
    Standard Grant
  • 资助金额:
    $0.0万
  • 财政年份:
    2004
  • 负责人:
    Chin-Hui Lee
  • 依托单位:
2003 Symposium on Next Generation Automatic Speech Recognition (ASR)
  • 批准号:
    0352730
  • 项目类别:
    Standard Grant
  • 资助金额:
    $4.96万
  • 财政年份:
    2003
  • 负责人:
    Chin-Hui Lee
  • 依托单位:
SGER: Exploring New Auditory Perception Based Approaches to ASR
  • 批准号:
    0350408
  • 项目类别:
    Standard Grant
  • 资助金额:
    $9.95万
  • 财政年份:
    2003
  • 负责人:
    Chin-Hui Lee
  • 依托单位:
国内基金
海外基金
Exploring Changing Fertility Intentions in China
  • 批准号:
    --
  • 项目类别:
    外国学者研究基金
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    MINHEE CHAE
  • 依托单位:
Exploring the Intrinsic Mechanisms of CEO Turnover and Market
  • 批准号:
    --
  • 项目类别:
    外国学者研究基金
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    HAOFEI Z
  • 依托单位:
Exploring the Intrinsic Mechanisms of CEO Turnover and Market Reaction: An Explanation Based on Information Asymmetry
  • 批准号:
    W2433169
  • 项目类别:
    外国学者研究基金项目
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    HAOFEI ZHANG
  • 依托单位: