专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20140074468A1 System and Method for Automatic Prediction of Speech Suitability for Statistical Modeling 有权
标题翻译：自动预测统计建模语音适用性的系统与方法
公开(公告)号：US20140074468A1
公开(公告)日：2014-03-13
申请号：US13606618
申请日：2012-09-07
申请人： Alexander Sorin , Slava Shechtman , Vincent Pollet
发明人： Alexander Sorin , Slava Shechtman , Vincent Pollet
IPC分类号： G10L15/00
CPC分类号： G10L25/48 , G10L13/04 , G10L25/18
摘要： An embodiment according to the invention provides a capability of automatically predicting how favorable a given speech signal is for statistical modeling, which is advantageous in a variety of different contexts. In Multi-Form Segment (MFS) synthesis, for example, an embodiment according to the invention uses prediction capability to provide an automatic acoustic driven template versus model decision maker with an output quality that is high, stable and depends gradually on the system footprint. In speaker selection for a statistical Text-to-Speech synthesis (TTS) system build, as another example context, an embodiment according to the invention enables a fast selection of the most appropriate speaker among several available ones for the full voice dataset recording and preparation, based on a small amount of recorded speech material.
摘要翻译：根据本发明的实施例提供了一种自动预测给定语音信号对于统计建模有利的能力，这在各种不同的上下文中是有利的。在多格段（MFS）合成中，例如，根据本发明的实施例使用预测能力来提供具有高，稳定的输出质量的自动声驱动模板与模型决策者，并逐渐依赖于系统占用。在用于统计文本到语音合成（TTS）系统构建的说话者选择中，作为另一示例性上下文，根据本发明的实施例使得能够在完整语音数据集记录和准备中的几个可用的扬声器中快速选择最合适的说话者，基于少量的录音材料。

2. 发明授权

US09484045B2 System and method for automatic prediction of speech suitability for statistical modeling 有权
标题翻译：自动预测语音适用性的统计建模系统和方法
公开(公告)号：US09484045B2
公开(公告)日：2016-11-01
申请号：US13606618
申请日：2012-09-07
申请人： Alexander Sorin , Slava Shechtman , Vincent Pollet
发明人： Alexander Sorin , Slava Shechtman , Vincent Pollet
IPC分类号： G10L13/06 , G10L13/04 , G10L19/00 , G10L25/48 , G10L25/18
CPC分类号： G10L25/48 , G10L13/04 , G10L25/18
摘要： An embodiment according to the invention provides a capability of automatically predicting how favorable a given speech signal is for statistical modeling, which is advantageous in a variety of different contexts. In Multi-Form Segment (MFS) synthesis, for example, an embodiment according to the invention uses prediction capability to provide an automatic acoustic driven template versus model decision maker with an output quality that is high, stable and depends gradually on the system footprint. In speaker selection for a statistical Text-to-Speech synthesis (TTS) system build, as another example context, an embodiment according to the invention enables a fast selection of the most appropriate speaker among several available ones for the full voice dataset recording and preparation, based on a small amount of recorded speech material.
摘要翻译：根据本发明的实施例提供了一种自动预测给定语音信号对于统计建模有利的能力，这在各种不同的上下文中是有利的。在多格段（MFS）合成中，例如，根据本发明的实施例使用预测能力来提供具有高，稳定的输出质量的自动声驱动模板与模型决策者，并逐渐依赖于系统占用。在用于统计文本到语音合成（TTS）系统构建的说话者选择中，作为另一示例性上下文，根据本发明的实施例使得能够在完整语音数据集记录和准备中的几个可用的扬声器中快速选择最合适的说话者，基于少量的录音材料。

3. 发明授权

US08321222B2 Synthesis by generation and concatenation of multi-form segments 有权
标题翻译：通过多代段的生成和连接进行合成
公开(公告)号：US08321222B2
公开(公告)日：2012-11-27
申请号：US11838609
申请日：2007-08-14
申请人： Vincent Pollet , Andrew Breen
发明人： Vincent Pollet , Andrew Breen
IPC分类号： G10L13/08
CPC分类号： G10L13/07 , G10L15/142
摘要： A speech synthesis system and method is described. A speech segment database references speech segments having various different speech representational structures. A speech segment selector selects from the speech segment database a sequence of speech segment candidates corresponding to a target text. A speech segment sequencer generates from the speech segment candidates sequenced speech segments corresponding to the target text. A speech segment synthesizer combines the selected sequenced speech segments to produce a synthesized speech signal output corresponding to the target text.
摘要翻译：描述语音合成系统和方法。语音段数据库引用具有各种不同语音表示结构的语音段。语音段选择器从语音段数据库中选择与目标文本相对应的语音段候选序列。语音段定序器从语音段生成与目标文本相对应的排序的语音段。语音段合成器组合所选择的排序语音段以产生对应于目标文本的合成语音信号输出。

4. 发明授权

US07567896B2 Corpus-based speech synthesis based on segment recombination 有权
标题翻译：基于片段重组的基于语料库的语音合成
公开(公告)号：US07567896B2
公开(公告)日：2009-07-28
申请号：US11037545
申请日：2005-01-18
申请人： Geert Coorman , Vincent Pollet , Stefaan Van Gerven , Mario De Bock , Bert Van Coile , Jan De Moortel
发明人： Geert Coorman , Vincent Pollet , Stefaan Van Gerven , Mario De Bock , Bert Van Coile , Jan De Moortel
IPC分类号： G06F17/21
CPC分类号： G10L13/06 , G10L13/07
摘要： A system and method generate synthesized speech through concatenation of speech segments that are derived from a large prosodically-rich corpus of speech segments including using an additional dictionary of speech segment identifier sequences.
摘要翻译：系统和方法通过从语音段的大的韵律丰富语料库导出的语音段的级联来产生合成语音，包括使用语音段标识符序列的附加字典。

5. 发明申请

US20090048841A1 Synthesis by Generation and Concatenation of Multi-Form Segments 有权
标题翻译：通过多代段的产生和连接进行合成
公开(公告)号：US20090048841A1
公开(公告)日：2009-02-19
申请号：US11838609
申请日：2007-08-14
申请人： Vincent Pollet , Andrew Breen
发明人： Vincent Pollet , Andrew Breen
IPC分类号： G10L13/06
CPC分类号： G10L13/07 , G10L15/142
摘要： A speech synthesis system and method is described. A speech segment database references speech segments having various different speech representational structures. A speech segment selector selects from the speech segment database a sequence of speech segment candidates corresponding to a target text. A speech segment sequencer generates from the speech segment candidates sequenced speech segments corresponding to the target text. A speech segment synthesizer combines the selected sequenced speech segments to produce a synthesized speech signal output corresponding to the target text.
摘要翻译：描述语音合成系统和方法。语音段数据库引用具有各种不同语音表示结构的语音段。语音段选择器从语音段数据库中选择与目标文本相对应的语音段候选序列。语音段定序器从语音段生成与目标文本相对应的排序的语音段。语音段合成器组合所选择的排序语音段以产生对应于目标文本的合成语音信号输出。

6. 发明申请

US20050182629A1 Corpus-based speech synthesis based on segment recombination 有权
标题翻译：基于片段重组的基于语料库的语音合成
公开(公告)号：US20050182629A1
公开(公告)日：2005-08-18
申请号：US11037545
申请日：2005-01-18
申请人： Geert Coorman , Vincent Pollet , Stefaan Van Gerven , Mario De Bock , Bert Van Coile , Jan De Moortel
发明人： Geert Coorman , Vincent Pollet , Stefaan Van Gerven , Mario De Bock , Bert Van Coile , Jan De Moortel
IPC分类号： G10L13/00 , G10L13/06
CPC分类号： G10L13/06 , G10L13/07
摘要： A system and method generate synthesized speech through concatenation of speech segments that are derived from a large prosodically-rich corpus of speech segments including using an additional dictionary of speech segment identifier sequences.
摘要翻译：系统和方法通过从语音段的大的韵律丰富语料库导出的语音段的级联来产生合成语音，包括使用语音段标识符序列的附加字典。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式