专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20050184959A1 Haptic key controlled data input 有权
标题翻译：触觉键控制数据输入
公开(公告)号：US20050184959A1
公开(公告)日：2005-08-25
申请号：US11038447
申请日：2005-01-19
申请人： Ralf Kompe , Jason Williams
发明人： Ralf Kompe , Jason Williams
IPC分类号： G06F3/02 , G06F1/16 , G06F3/00 , G06F3/01 , G06F3/023 , G06F3/0482 , G06F3/0485 , G09G5/00 , G09G5/08
CPC分类号： G06F3/016 , G06F3/0236 , G06F3/0482 , G06F3/0485
摘要： The present invention provides an apparatus for entering data into a computing device. The apparatus comprises at least two haptic keys having more than one state of activation, a graphical user interface for presenting hierarchically organised information to a user of the computing device, and a control means for controlling the generation of input data with respect to a haptic key selected, the current state of activation of the selected haptic key, and the information presented by the graphical user interface.
摘要翻译：本发明提供了一种用于将数据输入计算设备的装置。该装置包括具有多于一个激活状态的至少两个触觉键，用于向计算设备的用户呈现分层组织的信息的图形用户界面，以及用于控制相对于触觉键生成输入数据的控制装置选择的，所选择的触觉键的当前激活状态以及由图形用户界面呈现的信息。

22. 发明授权

US07752044B2 Method for recognizing speech 失效
标题翻译：识别语音的方法
公开(公告)号：US07752044B2
公开(公告)日：2010-07-06
申请号：US10683495
申请日：2003-10-10
申请人： Yin Hay Lam , Ralf Kompe
发明人： Yin Hay Lam , Ralf Kompe
IPC分类号： G10L15/00 , G10L15/04
CPC分类号： G10L15/08 , G10L2015/025
摘要： To increase the robustness and/or the recognition rate of methods for recognizing speech it is proposed to include phone boundary verification measure features in the process of obtaining and/or generating confidence measures obtained recognition results.
摘要翻译：为了增加用于识别语音的方法的鲁棒性和/或识别率，提出在获得和/或产生置信度量获得的识别结果的过程中包括电话边界验证测度特征。

23. 发明授权

US07113908B2 Method for recognizing speech using eigenpronunciations 失效
公开(公告)号：US07113908B2
公开(公告)日：2006-09-26
申请号：US10090861
申请日：2002-03-05
申请人： Silke Goronzy , Ralf Kompe
发明人： Silke Goronzy , Ralf Kompe
IPC分类号： G10L15/06
CPC分类号： G10L15/07
摘要： To increase the recognition rate and quality in a process of recognizing speech an approximative set of pronunciation rules (APR) for a current pronunciation (CP) of a current speaker is determined in a given pronunciation space (PS) and then applied to a current pronunciation lexicon (CL) so as to perform a speaker specific adaptation of said current lexicon (CL).

24. 发明授权

US06535854B2 Speech recognition control of remotely controllable devices in a home network environment 有权
标题翻译：家庭网络环境中遥控设备的语音识别控制
公开(公告)号：US06535854B2
公开(公告)日：2003-03-18
申请号：US09175382
申请日：1998-10-19
申请人： Peter Buchner , Silke Goronzy , Ralf Kompe , Stefan Rapp
发明人： Peter Buchner , Silke Goronzy , Ralf Kompe , Stefan Rapp
IPC分类号： G10L1522
CPC分类号： H04L12/40117 , G10L15/26 , H04L12/2803 , H04L12/282
摘要： Home networks low-cost digital interfaces are introduced that integrate entertainment, communication and computing electronics into consumer multimedia. Normally, these are low-cost, easy to use systems, since they allow the user to remove or add any kind of network devices with the bus being active. To improve the user interface a speech unit (2) is proposed that enables all devices (11) connected to the bus system (31) to be controlled by a single speech recognition device. The properties of this device, e.g. the vocabulary can be dynamically and actively extended by the consumer devices (11) connected to the bus system (31). The proposed technology is independent from a specific bus standard, e.g. the IEEE 1394 standard, and is well-suited for all kinds of wired wireless home networks. The speech unit (2) receives data and messages from the device. The speech unit (2) recognizes speaker-dependent commands. A Speech synthesizer synthesizes messages. A remotely controllable device (11) has access to a medium which may be a CD-ROM. The device may ask for a logical name or identifier.
摘要翻译：家庭网络引入了低成本的数字接口，将娱乐，通信和计算电子整合到消费者多媒体中。通常，这些是低成本，易于使用的系统，因为它们允许用户去除或添加任何类型的网络设备，其中总线是活动的。为了改善用户接口，提出了一种语音单元（2），其使得能够通过单个语音识别设备来控制连接到总线系统（31）的所有设备（11）。该装置的特性，例如可以通过连接到总线系统（31）的消费者设备（11）来动态地和主动地扩展词汇。所提出的技术独立于特定总线标准，例如。 IEEE 1394标准，非常适用于各种有线无线家庭网络。语音单元（2）从设备接收数据和消息。语音单元（2）识别与扬声器相关的命令。语音合成器综合消息。远程可控设备（11）可以访问可以是CD-ROM的介质。该设备可能会要求一个逻辑名称或标识符。

25. 发明授权

US07890862B2 Haptic key controlled data input 有权
标题翻译：触觉键控制数据输入
公开(公告)号：US07890862B2
公开(公告)日：2011-02-15
申请号：US11038447
申请日：2005-01-19
申请人： Ralf Kompe , Jason Williams
发明人： Ralf Kompe , Jason Williams
IPC分类号： G06F3/01 , G06F3/00 , G06F3/048
CPC分类号： G06F3/016 , G06F3/0236 , G06F3/0482 , G06F3/0485
摘要： An apparatus for entering data into a computing device includes a graphical user interface that presents hierarchically organized information in a menu structure of at least two hierarchy levels, including a topmost hierarchy level and at least one further hierarchy level. The apparatus also includes at least two haptic keys, each having more than one state of activation. Each of the haptic keys is assigned to a particular hierarchy level. A first haptic key is assigned to the topmost hierarchy level. A menu on the topmost hierarchy level is directly accessible using the first haptic key. A menu on a hierarchy level higher than one that is currently presented on the graphical user interface is directly accessible using a haptic key assigned to the menu on the higher level, when a hierarchy level of the currently presented menu is one of the at least one further hierarchy level.
摘要翻译：用于将数据输入到计算设备的装置包括图形用户界面，该图形用户界面在至少两个层次级别的菜单结构中呈现分层组织的信息，包括最上层次级别和至少一个其他层次级别。该装置还包括至少两个触觉键，每个具有多于一种的激活状态。每个触觉键被分配到特定的层级。第一个触觉键被分配到最上层次的级别。使用第一触觉键直接访问最上层次级别的菜单。在当前呈现在图形用户界面上的当前呈现的层次级别上的菜单可以使用分配给较高级别的菜单的触觉键直接访问，当当前呈现的菜单的层次级别是至少一个进一步层级。

26. 发明授权

US06999929B2 Recognizing speech by selectively canceling model function mixture components 失效
标题翻译：通过选择性地取消模型函数混合分量识别语音
公开(公告)号：US06999929B2
公开(公告)日：2006-02-14
申请号：US09947109
申请日：2001-09-05
申请人： Ralf Kompe , Silke Goronzy
发明人： Ralf Kompe , Silke Goronzy
IPC分类号： G10L15/20
CPC分类号： G10L15/07 , G10L15/063 , G10L15/142
摘要： A method for recognizing speech is proposed wherein the process of recognition is started using the starting acoustic model (SAM) and wherein the current acoustic model (CAM) is modified by removing or cancelling model function mixture components (MFMjk) which are negligible for the description of the speaking behavior and quality of the current speaker. Therefore, the size of the acoustic model (SAM, CAM) is reduced by adaptation to the current speaker enabling fast performance and increased recognition efficiency.
摘要翻译：提出了一种用于识别语音的方法，其中使用起始声学模型（SAM）开始识别过程，并且其中通过去除或取消模型函数混合分量来修改当前声学模型（CAM）（MFM >），可以忽略当前演讲者的说话行为和质量的描述。因此，声学模型（SAM，CAM）的尺寸通过适应当前扬声器而降低，能够实现快速的性能并提高识别效率。

27. 发明授权

US06882972B2 Method for recognizing speech to avoid over-adaptation during online speaker adaptation 失效
标题翻译：用于识别语音以避免在线说话者适应期间过度适应的方法
公开(公告)号：US06882972B2
公开(公告)日：2005-04-19
申请号：US09972174
申请日：2001-10-05
申请人： Ralf Kompe , Silke Goronzy , Krzysztof Marasek
发明人： Ralf Kompe , Silke Goronzy , Krzysztof Marasek
IPC分类号： G10L15/06 , G10L15/065 , G10L15/14 , G10L15/20
CPC分类号： G10L15/065 , G10L2015/0635
摘要： To avoid an over-adaptation of a current acoustic model (CAM) to certain and frequently occuring words for speech phrases during on-line speaker adaptation of speech recognizers it is suggested to count adaptation numbers (aj) for each of said speech phrases (SPj) as numbers of times in that a distinct speech phrase (SPj) has been used as a basis for adapting said current acoustic model (CAM) and further to make the strength of adaptation of the current acoustic model (CAM) on the basis of said distinct speech phrase (SPj) dependent on its specific adaptation number (aj) so as to decrease the influence of frequent speech phrases (SPj) in the received speech flow on the adaptation process.
摘要翻译：为了避免在语音识别器的在线说话者适应期间将当前声学模型（CAM）过度适应于语音短语的特定和频繁出现的单词，建议对自适应数字进行计数（例如，对于每个所述语音短语（SPj），作为不同语音短语（SPj）已经被用作适应所述当前声学模型（CAM）的基础的次数，并且进一步使得当前声学模型的适应强度（SPJ）的基础上，根据所述不同的语音短语（SPj），根据其特定的自适应编号（a）来减少频率语音短语（SPj）对接收到的语音流的影响适应过程。

28. 发明授权

US06799162B1 Semi-supervised speaker adaptation 失效
标题翻译：半监督说话者适应
公开(公告)号：US06799162B1
公开(公告)日：2004-09-28
申请号：US09461981
申请日：1999-12-15
申请人： Silke Goronzy , Ralf Kompe , Peter Buchner , Naoto Iwahashi
发明人： Silke Goronzy , Ralf Kompe , Peter Buchner , Naoto Iwahashi
IPC分类号： G10L1506
CPC分类号： G10L15/065 , G10L15/063 , G10L2015/0638
摘要： To prevent adaptation to misrecognized words in unsupervised or on-line automatic speech recognition systems confidence measures are used or the user reaction is interpreted to decide whether a recognized phoneme, several phonemes, a word, several words or a whole utterance should be used for adaptation of the speaker independent model set to a speaker adapted model set or not and, in case an adaptation is executed, how strong the adaptation with this recognized utterance or part of this recognized utterance should be performed. Furtheron, a verification of the speaker adaptation performance is proposed to secure that the recognition rate never decreases (significantly), but only increases or stays at the same level.
摘要翻译：为了防止在无监督或在线自动语音识别系统中适应错误识别的单词，使用置信度度量或用户反应来解释是否应将识别的音素，数个音素，单词，多个单词或整个话语用于适应将扬声器独立模型设置为扬声器适配模型集合，并且在执行适应的情况下，应该执行具有该识别话语或部分该识别话语的适应性的强度。此外，提出了说话者适应性能的验证，以确保识别率不会降低（显着），但只增加或保持在同一水平。

29. 发明授权

US06615177B1 Merging of speech interfaces from concurrent use of devices and applications 失效
标题翻译：从并发使用设备和应用程序合并语音界面
公开(公告)号：US06615177B1
公开(公告)日：2003-09-02
申请号：US09546768
申请日：2000-04-11
申请人： Stefan Rapp , Silke Goronzy , Ralf Kompe , Peter Buchner , Franck Giron , Helmut Lucke
发明人： Stefan Rapp , Silke Goronzy , Ralf Kompe , Peter Buchner , Franck Giron , Helmut Lucke
IPC分类号： G10L2100
CPC分类号： G10L15/26 , H04M2201/40
摘要： According to the present invention network devices that can be controlled via a speech unit included in the network can send a device-document describing its functionality and its speech interface to said speech unit. The speech unit combines those documents to a general document that forms the basis to translate recognized user-commands into user-network-commands to control the connected network-devices. A device-document comprises at least the vocabulary and the commands associated therewith for the corresponding device. Furtheron, pronunciation, grammar for word sequences, rules for speech understanding and dialog can be contained in such documents as well as the same information for multiple languages or information for dynamic dialogs in speech understanding. It is possible that one device contains several documents and dynamically sends them to the speech unit in case they are needed. Furtheron, the present invention enables a device to change its functionality dynamically based on changing content, since a network device send its specifications regarding its speech capabilities to the speech unit while the speech unit is in use.
摘要翻译：根据本发明，可以通过网络中包括的语音单元进行控制的网络设备可以将描述其功能的设备文档及其语音接口发送到所述语音单元。语音单元将这些文档组合到一般文档中，该文档构成将识别的用户命令转换为用户网络命令以控制所连接的网络设备的基础。装置文件至少包括与对应装置相关联的词汇表和命令。更重要的是，语言理解和对话语言的发音，语法，语音理解和对话的规则可以包含在这样的文档中，以及用于多种语言的相同信息或用于语音理解中的动态对话的信息。一个设备可能包含多个文档，并在需要时动态地将它们发送到语音单元。因此，本发明使得设备能够基于变化的内容动态地改变其功能，因为网络设备在语音单元正在使用时将其关于其语音能力的规范发送到语音单元。

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