Collaborative Research: Landmark-based Robust Speech Recognition using Prosody-guided Models of Speech Variability
协作研究:使用韵律引导的语音变异模型进行基于地标的鲁棒语音识别
基本信息
- 批准号:0703805
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2007
- 资助国家:美国
- 起止时间:2007-06-01 至 2011-05-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Proposal ID 0703859 Date 04/11/2007 Despite great strides in the development of automatic speech recognition technology, we do not yet have a system with performance comparable to humans in automatically transcribing unrestricted conversational speech, representing many speakers and dialects, and embedded in adverse acoustic environments. This approach applies new high-dimensional machine learning techniques, constrained by empirical and theoretical studies of speech production and perception, to learn from data the information structures that human listeners extract from speech. To do this, we will develop large-vocabulary psychologically realistic models of speech acoustics, pronunciation variability, prosody, and syntax by deriving knowledge representations that reflect those proposed for human speech production and speech perception, using machine learning techniques to adjust the parameters of all knowledge representations simultaneously in order to minimize the structural risk of the recognizer. The team will develop nonlinear acoustic landmark detectors and pattern classifiers that integrate auditory-based signal processing and acoustic phonetic processing, are invariant to noise, change in speaker characteristics and reverberation, and can be learned in a semi-supervised fashion from labeled and unlabeled data. In addition, they will use variable frame rate analysis, which will allow for multi-resolution analysis, as well as implement lexical access based on gesture, using a variety of training data. The work will improve communication and collaboration between people and machines and also improve understanding of how human produce and perceive speech. The work brings together a team of experts in speech processing, acoustic phonetics, prosody, gestural phonology, statistical pattern matching, language modeling, and speech perception, with faculty across engineering, computer science and linguistics. Support and engagement of students and postdoctoral fellows are part of the project, engaging in speech modeling and algorithm development. Finally, the proposed work will result in a set of databases and tools that will be disseminated to serve the research and education community at large.
提案ID 0703859日期04/11/2007尽管自动语音识别技术的发展取得了长足的进步,但我们还没有一个系统在自动转录不受限制的对话语音方面具有与人类相当的性能,代表许多说话者和方言,并嵌入在恶劣的声学环境中。这种方法应用新的高维机器学习技术,受语音产生和感知的经验和理论研究的约束,从数据中学习人类听众从语音中提取的信息结构。要做到这一点,我们将开发大词汇量的语音声学,发音变化,韵律和语法的心理现实模型,通过推导知识表示,反映那些建议人类的语音生产和语音感知,使用机器学习技术来调整所有知识表示的参数,同时为了最大限度地减少识别器的结构风险。该团队将开发非线性声学地标检测器和模式分类器,这些检测器和模式分类器集成了基于语音的信号处理和声学语音处理,对噪声、说话者特征和混响的变化具有不变性,并且可以以半监督的方式从标记和未标记的数据中学习。此外,他们将使用可变帧速率分析,这将允许多分辨率分析,以及使用各种训练数据实现基于手势的词汇访问。这项工作将改善人与机器之间的沟通和协作,并提高对人类如何产生和感知语音的理解。这项工作汇集了语音处理,声学语音学,韵律学,手势音位学,统计模式匹配,语言建模和语音感知方面的专家团队,以及工程,计算机科学和语言学方面的教师。学生和博士后研究员的支持和参与是该项目的一部分,从事语音建模和算法开发。最后,拟议的工作将产生一套数据库和工具,将分发给广大研究和教育界。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Abeer Alwan其他文献
Modeling auditory perception to improve robust speech recognition
建立听觉感知模型以提高稳健的语音识别能力
- DOI:
- 发表时间:
1997 - 期刊:
- 影响因子:0
- 作者:
B. Strope;Abeer Alwan - 通讯作者:
Abeer Alwan
Unraveling the associations between voice pitch and major depressive disorder: a multisite genetic study
揭示声音音调与重度抑郁症之间的关联:一项多站点遗传研究
- DOI:
10.1038/s41380-024-02877-y - 发表时间:
2024-12-31 - 期刊:
- 影响因子:10.100
- 作者:
Yazheng Di;Elior Rahmani;Joel Mefford;Jinhan Wang;Vijay Ravi;Aditya Gorla;Abeer Alwan;Kenneth S. Kendler;Tingshao Zhu;Jonathan Flint - 通讯作者:
Jonathan Flint
Optical Phonetics and Visual Percep Stress in Eng
英语中的光学语音和视觉感知压力
- DOI:
- 发表时间:
2003 - 期刊:
- 影响因子:0
- 作者:
P. Keating;Marco Baroni;Sven Matty;E. T. Auer;Rebecca Scarborough;Abeer Alwan;E. Bernstein - 通讯作者:
E. Bernstein
Towards Automatically Assessing Children’s Picture Description Tasks
自动评估儿童图片描述任务
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Hariram Veeramani;Natarajan Balaji Shankar;Alexander Johnson;Abeer Alwan - 通讯作者:
Abeer Alwan
An Analysis of Large Language Models for African American English Speaking Children’s Oral Language Assessment
非裔美国英语儿童口语评估大语言模型分析
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Alexander Johnson;Christina Chance;Kaycee Stiemke;Hariram Veeramani;Natarajan Balaji Shankar;Abeer Alwan - 通讯作者:
Abeer Alwan
Abeer Alwan的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Abeer Alwan', 18)}}的其他基金
Collaborative Research: Improving speech technology for better learning outcomes: the case of AAE child speakers
协作研究:改进语音技术以获得更好的学习成果:AAE 儿童扬声器的案例
- 批准号:
2202585 - 财政年份:2022
- 资助金额:
-- - 项目类别:
Standard Grant
Collaborative Research: RI: Small: From Ultrasound and MRI to articulatory and acoustic models of child speech development
合作研究:RI:小型:从超声和 MRI 到儿童言语发展的发音和声学模型
- 批准号:
2006979 - 财政年份:2020
- 资助金额:
-- - 项目类别:
Standard Grant
Workshop for Undergraduate and MS Female Students in Speech Science and Technology
语音科学与技术本科生和女硕士讲习班
- 批准号:
1745166 - 财政年份:2017
- 资助金额:
-- - 项目类别:
Standard Grant
NRI: INT: COLLAB: Development, Deployment and Evaluation of Personalized Learning Companion Robots for Early Literacy and Language Learning
NRI:INT:COLLAB:用于早期识字和语言学习的个性化学习伴侣机器人的开发、部署和评估
- 批准号:
1734380 - 财政年份:2017
- 资助金额:
-- - 项目类别:
Standard Grant
RI: Medium: Collaborative Research: Variance and Invariance in Voice Quality: Implications for Machine and Human Speaker Identification
RI:媒介:协作研究:语音质量的方差和不变性:对机器和人类说话人识别的影响
- 批准号:
1704167 - 财政年份:2017
- 资助金额:
-- - 项目类别:
Continuing Grant
A Workshop for Junior Female Researchers in Speech Science and Technology
语音科学与技术青年女性研究员研讨会
- 批准号:
1637240 - 财政年份:2016
- 资助金额:
-- - 项目类别:
Standard Grant
The Role of Speech Science in Developing Robust Speech Technology Applications
语音科学在开发强大的语音技术应用中的作用
- 批准号:
1543522 - 财政年份:2015
- 资助金额:
-- - 项目类别:
Standard Grant
EAGER: Collaborative Research: Models of Child Speech
EAGER:合作研究:儿童言语模型
- 批准号:
1551113 - 财政年份:2015
- 资助金额:
-- - 项目类别:
Standard Grant
EAGER: Variance and Invariance in Voice Quality
EAGER:语音质量的方差和不变性
- 批准号:
1450992 - 财政年份:2014
- 资助金额:
-- - 项目类别:
Standard Grant
EAGER: Collaborative Research: Towards Modeling Human Speech Confusions in Noise
EAGER:协作研究:对噪声中的人类语音混乱进行建模
- 批准号:
1247809 - 财政年份:2012
- 资助金额:
-- - 项目类别:
Standard Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: REU Site: Earth and Planetary Science and Astrophysics REU at the American Museum of Natural History in Collaboration with the City University of New York
合作研究:REU 地点:地球与行星科学和天体物理学 REU 与纽约市立大学合作,位于美国自然历史博物馆
- 批准号:
2348998 - 财政年份:2025
- 资助金额:
-- - 项目类别:
Standard Grant
Collaborative Research: REU Site: Earth and Planetary Science and Astrophysics REU at the American Museum of Natural History in Collaboration with the City University of New York
合作研究:REU 地点:地球与行星科学和天体物理学 REU 与纽约市立大学合作,位于美国自然历史博物馆
- 批准号:
2348999 - 财政年份:2025
- 资助金额:
-- - 项目类别:
Standard Grant
"Small performances": investigating the typographic punches of John Baskerville (1707-75) through heritage science and practice-based research
“小型表演”:通过遗产科学和基于实践的研究调查约翰·巴斯克维尔(1707-75)的印刷拳头
- 批准号:
AH/X011747/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
Democratizing HIV science beyond community-based research
将艾滋病毒科学民主化,超越社区研究
- 批准号:
502555 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Translational Design: Product Development for Research Commercialisation
转化设计:研究商业化的产品开发
- 批准号:
DE240100161 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Discovery Early Career Researcher Award
Understanding the experiences of UK-based peer/community-based researchers navigating co-production within academically-led health research.
了解英国同行/社区研究人员在学术主导的健康研究中进行联合生产的经验。
- 批准号:
2902365 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Studentship
XMaS: The National Material Science Beamline Research Facility at the ESRF
XMaS:ESRF 的国家材料科学光束线研究设施
- 批准号:
EP/Y031962/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
FCEO-UKRI Senior Research Fellowship - conflict
FCEO-UKRI 高级研究奖学金 - 冲突
- 批准号:
EP/Y033124/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
UKRI FCDO Senior Research Fellowships (Non-ODA): Critical minerals and supply chains
UKRI FCDO 高级研究奖学金(非官方发展援助):关键矿产和供应链
- 批准号:
EP/Y033183/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
TARGET Mineral Resources - Training And Research Group for Energy Transition Mineral Resources
TARGET 矿产资源 - 能源转型矿产资源培训与研究小组
- 批准号:
NE/Y005457/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Training Grant