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. 发明授权

US06999925B2 Method and apparatus for phonetic context adaptation for improved speech recognition 有权
公开(公告)号：US06999925B2
公开(公告)日：2006-02-14
申请号：US10007990
申请日：2001-11-13
申请人： Volker Fischer , Siegfried Kunzmann , Eric-W. Janke , A. Jon Tyrrell
发明人： Volker Fischer , Siegfried Kunzmann , Eric-W. Janke , A. Jon Tyrrell
IPC分类号： G10L15/06 , G10L15/08 , G10L15/27 , G10L15/18
CPC分类号： G10L15/07
摘要： The present invention provides a computerized method and apparatus for automatically generating from a first speech recognizer a second speech recognizer which can be adapted to a specific domain. The first speech recognizer can include a first acoustic model with a first decision network and corresponding first phonetic contexts. The first acoustic model can be used as a starting point for the adaptation process. A second acoustic model with a second decision network and corresponding second phonetic contexts for the second speech recognizer can be generated by re-estimating the first decision network and the corresponding first phonetic contexts based on domain-specific training data.

2. 发明授权

US08412528B2 Back-end database reorganization for application-specific concatenative text-to-speech systems 有权
标题翻译：适用于特定应用的级联文本到语音系统的后端数据库重组
公开(公告)号：US08412528B2
公开(公告)日：2013-04-02
申请号：US11416217
申请日：2006-05-02
申请人： Volker Fischer , Siegfried Kunzmann
发明人： Volker Fischer , Siegfried Kunzmann
IPC分类号： G01L13/00 , G01L13/06
CPC分类号： G10L13/06
摘要： The present invention relates to computer-generated text-to-speech conversion. It relates in particular to a method and system for updating a Concatenative Text-To-Speech (CTTS) system with a speech database from a base version to a new version. The present invention performs an application-specific re-organization of a synthesizer's speech database by means of certain decision tree modifications. By that reorganization, certain synthesis units are made available for the new application, which are not available in prior art without a new speech session. This allows the creation of application-specific synthesizers with improved output speech quality for arbitrary domains and applications at very low cost.
摘要翻译：本发明涉及计算机生成的文本到语音转换。特别涉及一种用于从基本版本到新版本更新具有语音数据库的连续文本到语音（CTTS）系统的方法和系统。本发明通过某些决策树修改来执行合成器的语音数据库的应用特定的重组。通过该重组，某些合成单元可用于新的应用，这在现有技术中不可用，而没有新的语音会话。这允许以非常低的成本为任意域和应用创建具有改进的输出语音质量的应用专用合成器。

3. 发明授权

US07302393B2 Sensor based approach recognizer selection, adaptation and combination 有权
标题翻译：基于传感器的方法识别器选择，适应和组合
公开(公告)号：US07302393B2
公开(公告)日：2007-11-27
申请号：US10539454
申请日：2003-10-31
申请人： Volker Fischer , Siegfried Kunzmann
发明人： Volker Fischer , Siegfried Kunzmann
IPC分类号： G10L15/20
CPC分类号： G10L15/20 , G10L2015/228
摘要： A method and respective system for operating a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. In order to adapt such system to the dynamically changing acoustic conditions of various operating environments and to the particular requirements of running in embedded systems having only a limited computing power available, it is proposed to a) collect selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, and b) using program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select the best suited recognizer or a combination thereof out of the plurality of available recognizers.
摘要翻译：一种用于操作语音识别系统的方法和相应系统，其中多个识别器程序可被访问以被激活用于语音识别，并且在每个需要基础上被组合，以便有效地改善单个语音识别结果的语音识别结果识别器。为了将这种系统适应于各种操作环境的动态变化的声学条件以及仅具有有限计算能力的嵌入式系统中运行的特定要求，提出了：a）收集表征语音识别边界条件的选择基础数据，例如演讲人和环境噪音等，以及b）使用程序控制的仲裁器装置来评估所收集的数据，例如包括软件机制和物理传感器的决策引擎，以选择最适合的识别器或在多个可用识别器中的组合。

4. 发明申请

US20060173684A1 Sensor based speech recognizer selection, adaptation and combination 有权
标题翻译：基于传感器的语音识别器选择，适应和组合
公开(公告)号：US20060173684A1
公开(公告)日：2006-08-03
申请号：US10539454
申请日：2003-10-31
申请人： Volker Fischer , Siegfried Kunzmann
发明人： Volker Fischer , Siegfried Kunzmann
IPC分类号： G10L15/04
CPC分类号： G10L15/20 , G10L2015/228
摘要： A method and respective system for operating a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. In order to adapt such system to the dynamically changing acoustic conditions of various operating environments and to the particular requirements of running in embedded systems having only a limited computing power available, it is proposed to a) collect selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, and b) using program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select the best suited recognizer or a combination thereof out of the plurality of available recognizers.
摘要翻译：一种用于操作语音识别系统的方法和相应系统，其中多个识别器程序可被访问以被激活用于语音识别，并且在每个需要基础上被组合，以便有效地改善单个语音识别结果的语音识别结果识别器。为了将这种系统适应于各种操作环境的动态变化的声学条件以及仅具有有限计算能力的嵌入式系统中运行的特定要求，提出了：a）收集表征语音识别边界条件的选择基础数据，例如演讲人和环境噪音等，以及b）使用程序控制的仲裁器装置来评估收集的数据，例如包括软件机制和物理传感器的决策引擎，以选择最适合的识别器或在多个可用识别器中的组合。

5. 发明授权

US06789061B1 Method and system for generating squeezed acoustic models for specialized speech recognizer 失效
标题翻译：用于产生用于专门语音识别器的挤压声学模型的方法和系统
公开(公告)号：US06789061B1
公开(公告)日：2004-09-07
申请号：US09638160
申请日：2000-08-14
申请人： Volker Fischer , Siegfried Kunzmann , Claire Waast-Ricard
发明人： Volker Fischer , Siegfried Kunzmann , Claire Waast-Ricard
IPC分类号： G10L1508
CPC分类号： G10L15/144
摘要： Computer-based methods and systems are provided for automatically generating, from a first speech recognizer, a second speech recognizer such that the second speech recognizer is tailored to a certain application and requires reduced resources compared to the first speech recognizer. The invention exploits the first speech recognizer's set of states si and set of probability density functions (pdfs) assembling output probabilities for an observation of a speech frame in said states si. The invention teaches a first step of generating a set of states of the second speech recognizer reduced to a subset of states of the first speech recognizer being distinctive of the certain application. The invention teaches a second step of generating a set of probability density functions of the second speech recognizer reduced to a subset of probability density functions of the first speech recognizer being distinctive of the certain application.
摘要翻译：提供了基于计算机的方法和系统，用于从第一语音识别器自动生成第二语音识别器，使得第二语音识别器针对特定应用而定制，并且与第一语音识别器相比需要减少的资源。本发明利用第一语音识别器的状态集合si和集合的概率密度函数（pdf）组合用于在所述状态si中观察语音帧的输出概率。本发明教导了第一步骤，生成第二语音识别器的一组状态，其被缩减为特定应用的第一语音识别器的状态的子集。本发明教导了产生第二语音识别器的一组概率密度函数的第二步骤，该第二语音识别器被简化为特定应用的第一语音识别器的概率密度函数子集。

6. 发明申请

US20060287861A1 Back-end database reorganization for application-specific concatenative text-to-speech systems 有权
公开(公告)号：US20060287861A1
公开(公告)日：2006-12-21
申请号：US11416217
申请日：2006-05-02
申请人： Volker Fischer , Siegfried Kunzmann
发明人： Volker Fischer , Siegfried Kunzmann
IPC分类号： G10L13/08
CPC分类号： G10L13/06
摘要： The present invention relates to computer-generated text-to-speech conversion. It relates in particular to a method and system for updating a Concatenative Text-To-Speech (CTTS) system with a speech database from a base version to a new version. The present invention performs an application-specific re-organization of a synthesizer's speech database by means of certain decision tree modifications. By that reorganization, certain synthesis units are made available for the new application, which are not available in prior art without a new speech session. This allows the creation of application-specific synthesizers with improved output speech quality for arbitrary domains and applications at very low cost.

7. 发明授权

US09363035B2 Method for testing the transmission modes of a radio device 有权
标题翻译：用于测试无线电设备的传输模式的方法
公开(公告)号：US09363035B2
公开(公告)日：2016-06-07
申请号：US12934433
申请日：2009-03-16
申请人： Andreas Pauly , Martin Mueller , Gerald Tietscher , Heino Gerlach , Volker Fischer , Stefan Ballmann
发明人： Andreas Pauly , Martin Mueller , Gerald Tietscher , Heino Gerlach , Volker Fischer , Stefan Ballmann
IPC分类号： H04W4/00 , H04L1/00 , H04L1/24
CPC分类号： H04L1/0001 , H04L1/24
摘要： A method for determining a channel quality for the transmission of data in the channel by a test device. The test device transmits the data with the determined channel quality to a device to be tested which determines one or more pieces of decision information. The device to be tested forwards the piece(s) of decision information to the test device as a response signal and the test device reads the piece(s) of decision information from the response signal. The piece(s) of decision information from the response signal is/are uniquely attributed to a transmission mode to be adjusted. The initially determined channel quality is also uniquely attributed to an expected transmission mode. The expected transmission mode is compared with the transmission mode to be adjusted in a comparative unit in the evaluation unit, thereby allowing a statement regarding the correctness of the transmission mode to be adjusted.
摘要翻译：一种用于由测试设备确定信道中数据传输的信道质量的方法。测试设备将确定的信道质量的数据发送到确定一个或多个决策信息的待测试设备。要测试的设备将该决定信息片段作为响应信号转发到测试设备，并且测试设备从响应信号中读取决定信息的一部分。来自响应信号的决定信息的一个或多个唯一地归因于要调整的传输模式。初始确定的信道质量也是唯一地归因于期望的传输模式。将预期传输模式与在评估单元中的比较单元中要调整的传输模式进行比较，从而允许调整关于传输模式的正确性的陈述。

8. 发明申请

US20110019579A1 METHOD FOR TESTING THE TRANSMISSION MODES OF A RADIO DEVICE 有权
标题翻译：测试无线电设备传输模式的方法
公开(公告)号：US20110019579A1
公开(公告)日：2011-01-27
申请号：US12934433
申请日：2009-03-16
申请人： Andreas Pauly , Martin Mueller , Gerald Tietscher , Heino Gerlach , Volker Fischer , Stefan Ballmann
发明人： Andreas Pauly , Martin Mueller , Gerald Tietscher , Heino Gerlach , Volker Fischer , Stefan Ballmann
IPC分类号： H04L12/26
CPC分类号： H04L1/0001 , H04L1/24
摘要： A method for determining a channel quality for the transmission of data in the channel by a test device. The test device transmits the data with the determined channel quality to a device to be tested which determines one or more pieces of decision information. The device to be tested forwards the piece(s) of decision information to the test device as a response signal and the test device reads the piece(s) of decision information from the response signal. The piece(s) of decision information from the response signal is/are uniquely attributed to a transmission mode to be adjusted. The initially determined channel quality is also uniquely attributed to an expected transmission mode. The expected transmission mode is compared with the transmission mode to be adjusted in a comparative unit in the evaluation unit, thereby allowing a statement regarding the correctness of the transmission mode to be adjusted.
摘要翻译：一种用于由测试设备确定信道中数据传输的信道质量的方法。测试设备将确定的信道质量的数据发送到确定一个或多个决策信息的待测试设备。要测试的设备将该决定信息片段作为响应信号转发到测试设备，并且测试设备从响应信号中读取决定信息的一部分。来自响应信号的决定信息的一个或多个唯一地归因于要调整的传输模式。初始确定的信道质量也是唯一地归因于期望的传输模式。将预期传输模式与在评估单元中的比较单元中要调整的传输模式进行比较，从而允许调整关于传输模式的正确性的陈述。

9. 发明授权

US4604129A Influencing plant growth 失效
标题翻译：影响植物生长
公开(公告)号：US4604129A
公开(公告)日：1986-08-05
申请号：US640237
申请日：1984-08-14
申请人： Eberhard P. Schott , Volker Fischer , Johann Jung , Henning Rosebrock
发明人： Eberhard P. Schott , Volker Fischer , Johann Jung , Henning Rosebrock
IPC分类号： A01N43/90 , C07D487/08
CPC分类号： C07D487/08 , A01N43/90
摘要： A process for regulating plant growth, wherein the plants, the seed or the soil are treated with a polycyclic nitrogen-containing compound of the formula ##STR1## R.sup.2 is --N.dbd.N-- or --NH--NH, and R.sup.3 is ##STR2## or phenyl which is substituted by halogen, fluoroalkyl of 1 to 2 carbon atoms, NO.sub.2 or C.sub.1 -C.sub.3 -alkyl, the equivalent of less than 100 g of active ingredient being employed per hectare.
摘要翻译：用于调节植物生长的方法，其中用具有下式的多环含氮化合物处理植物，种子或土壤R2为-N = N-或-NH-NH，R3为或被卤素取代的苯基，1至2个碳原子的氟代烷基，NO 2或C 1 -C 3 - 烷基，相当于每公顷使用少于100g的活性成分。

10. 发明授权

US5582452A Member for rubber-sprung rail wheels and rubber-sprung rail wheel 失效
标题翻译：橡胶弹簧轨道车轮和橡胶弹簧轨道车轮的成员
公开(公告)号：US5582452A
公开(公告)日：1996-12-10
申请号：US359471
申请日：1994-12-15
申请人： Franz Murawa , Wilfried Bittner , Jurgen Schneider , Volker Fischer
发明人： Franz Murawa , Wilfried Bittner , Jurgen Schneider , Volker Fischer
IPC分类号： B60B9/16 , B60B17/00 , B60B5/02
CPC分类号： B60B9/16 , B60B17/0034
摘要： A rubber member for rubber-elastic rail wheels which in the expanded state has an oval opening for receiving a flexible current bridge. When the rubber member is incorporated in the rail wheel, the opening assumes a substantially circular cross-section under prestressing.
摘要翻译：用于橡胶弹性轨道轮的橡胶构件，其在膨胀状态下具有用于接收柔性电流桥的椭圆形开口。当橡胶构件结合在轨道车轮中时，开口在预应力下呈现大致圆形的横截面。

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