SYSTEM FOR CONVERTING SPEECH INTO SYNTHESIS PARAMETERS
SYSTEM FOR CONVERTING SPEECH INTO SYNTHESIS PARAMETERS
批准号:
3494747
负责人:
RICHARD S GOLDHOR
金额:
$5.0万
依托单位:
依托单位国家:
美国
项目类别:
财政年份:
1991
资助国家:
美国
项目状态:
已结题
起止时间:
1991-01-10 至 1992-01-09
中文摘要
我们建议开发一个系统,用于表示语音使用时变
用于语音合成的源滤波器模型的控制参数。我们
在已知的语音环境中使用声学分析技术,
从语音波形中提取KLSYN88合成器参数。 这样的
基于合成的编码将强调有意义的声学语音
语音的特性,使其有可能选择性地修改特定的
生产相关的属性,并允许立即重新合成
原始或修改的波形。
第一阶段有两个目标。 首先,为了确定KLSYN88参数可以在多大程度上
代表特定的自然话语。 第二,确定是否
合适的参数值可以使用
在已知语音上下文中操作的声学算法。
如果成功的话,这种技术将被用作演讲,
用于有语言障碍的正常听力受试者的训练辅助设备,
他们听到自己的话语的更正版本。 也是
集成到商业支持的KLSYN88版本中,因此
显著减少产生控制所需的时间量,
参数
英文摘要
We propose to develop a system for representing speech using time-varying
control parameters for a source-filter model of speech synthesis. We would
employ techniques of acoustic analysis in a known phonetic context to
extract KLSYN88 synthesizer parameters from speech waveforms. Such a
synthesis-based encoding would emphasize meaningful acoustic-phonetic
properties of speech, making it possible to selectively modify specific
production-related attributes, and allowing immediate resynthesis of the
original or modified waveforms.
Phase I has two goals. First, to determine how well KLSYN88 parameters can
represent specific natural utterances. Second, to determine whether
suitable parameter values can be extracted from natural speech using
acoustic algorithms operating in known phonetic contexts.
If successful the resulting technology would be employed as a speech
training aid for normal-hearing subjects with speech impairments, allowing
them to hear corrected versions of their own utterances. It would also be
integrated into a commercially-supported version of KLSYN88, thus
substantially reducing the amount of time required to generate control
parameters.
期刊论文(1)
专著(0)
科研奖励(0)
会议论文
Terrorism Preparedness Training for Occupational Health Professionals
职业健康专业人员的恐怖主义防范培训
DOI:
10.1097/01.jom.0000147267.75156.a1
发表时间:
2004
期刊:
Journal of Occupational and Environmental Medicine
影响因子:
3.2
作者:
[R. Gershon, D. Gemson, K. Qureshi, M. McCollum]
通讯作者:
M. McCollum
Hear What I Want: an Acoustically Smart Personalized Common Room
-
批准号:10484661
-
项目类别:
-
资助金额:$25.96万
-
财政年份:2022
-
负责人:RICHARD S GOLDHOR
-
依托单位:
Clarity in Motion: A Motion-Tolerant Aid for Selectively Hearing Acoustic Sources
-
批准号:10603657
-
项目类别:
-
资助金额:$27.54万
-
财政年份:2022
-
负责人:RICHARD S GOLDHOR
-
依托单位:
SIRCE: A Sensor Image Based Room-Centered Equalization System for Hearing Aids
-
批准号:9255961
-
项目类别:
-
资助金额:$19.83万
-
财政年份:2016
-
负责人:RICHARD S GOLDHOR
-
依托单位:
ACES: A Product to Suppress or Enhance Critical Components in Acoustic Signals
-
批准号:8200823
-
项目类别:
-
资助金额:$29.87万
-
财政年份:2011
-
负责人:RICHARD S GOLDHOR
-
依托单位:
DMX: Enabling Blind Source Separation for Hearing Health Care
-
批准号:8648615
-
项目类别:
-
资助金额:$51.23万
-
财政年份:2010
-
负责人:RICHARD S GOLDHOR
-
依托单位:
DMX: Enabling Blind Source Separation for Hearing Health Care
-
批准号:9061938
-
项目类别:
-
资助金额:$1.6万
-
财政年份:2010
-
负责人:RICHARD S GOLDHOR
-
依托单位:
System For Separating Multiple Acoustic Sources
-
批准号:6693482
-
项目类别:
-
资助金额:$12.55万
-
财政年份:2003
-
负责人:RICHARD S GOLDHOR
-
依托单位:
ENVIRONMENTAL SOUND RECOGNITION
-
批准号:2125978
-
项目类别:
-
资助金额:$21.46万
-
财政年份:1992
-
负责人:RICHARD S GOLDHOR
-
依托单位:
ENVIRONMENTAL SOUND RECOGNITION
-
批准号:3507165
-
项目类别:
-
资助金额:$28.54万
-
财政年份:1992
-
负责人:RICHARD S GOLDHOR
-
依托单位:
ENVIRONMENTAL SOUND RECOGNITION
-
批准号:3494674
-
项目类别:
-
资助金额:$5.0万
-
财政年份:1989
-
负责人:RICHARD S GOLDHOR
-
依托单位: