公开(公告)号：US07593921B2

公开(公告)日：2009-09-22

申请号：US10525665

申请日：2003-08-27

申请人： Silke Goronzy ,  Ralf Kompe ,  Christian Hying ,  Zica Valsan ,  Robert Mencl ,  Helmut Wais ,  Thomas Kemp ,  Sunna Torge ,  Martin Emele

发明人： Silke Goronzy ,  Ralf Kompe ,  Christian Hying ,  Zica Valsan ,  Robert Mencl ,  Helmut Wais ,  Thomas Kemp ,  Sunna Torge ,  Martin Emele

IPC分类号： G06F17/30 ,  G06F7/00

CPC分类号： G06F17/30035 ,  H04H60/46 ,  H04N7/163 ,  H04N21/25891 ,  H04N21/44222 ,  H04N21/6582 ,  H04N21/8106 ,  Y10S707/99933 ,  Y10S707/99934

摘要： A user profile and/or the suggestions computed based thereon are obtained taking a special set of user features into account. The user features are defined to represent a typical general behaviour of an individual user in respect to the application where the user profile is used. In other words, for each application where a user profile is used a special set of user features are defined which are able to represent a typical general behaviour of an individual user. Based on these user features the weights in the list of word-weight pairs or weighted keywords which represents the user profile are computed or influenced during the creation of the user profile, and/or a multi-user profile is split during the creation of an individual user profile from a multi-user profile, and/or during specification of a suggestion a user history which is used to create the user profile, and/or the user profile, and/or the suggestion results are filtered.

摘要翻译： 考虑到用户特征集合的用户简档和/或基于其计算的建议。 用户特征被定义为表示个人用户相对于使用用户简档的应用的典型一般行为。 换句话说，对于使用用户简档的每个应用程序，定义了能够表示单个用户的典型一般行为的一组特定用户特征。 基于这些用户特征，在创建用户简档期间计算或影响表示用户简档的单词权重对或加权关键字列表中的权重，和/或在创建用户简档期间分割多用户简档 和/或在建议的指定期间，用于创建用户简档的用户历史记录和/或用户简档，和/或建议结果的个人用户简档被过滤。

公开(公告)号：US20090069914A1

公开(公告)日：2009-03-12

申请号：US11908944

申请日：2006-03-15

申请人： Thomas Kemp ,  Yin Hay Lam ,  Marta Tolos Rigueiro

发明人： Thomas Kemp ,  Yin Hay Lam ,  Marta Tolos Rigueiro

IPC分类号： G06F17/00

CPC分类号： G10L25/00 ,  G10H1/0008 ,  G10H2240/085 ,  G10H2240/155

摘要： A method for classifying audio data. For a given piece of audio data a location or position for the given audio data within a mood space is generated and compared to a comparison mood space location. As a result of the comparison, comparison data are generated and provided as a classification result with respect to the given audio data.

摘要翻译： 一种分类音频数据的方法。 对于给定的音频数据，产生在心情空间内的给定音频数据的位置或位置，并将其与比较情绪空间位置进行比较。 作为比较的结果，生成比较数据并将其作为关于给定音频数据的分类结果提供。

公开(公告)号：US07376559B2

公开(公告)日：2008-05-20

申请号：US10809162

申请日：2004-03-25

申请人： Raquel Tato ,  Thomas Kemp ,  Antoni Abella

发明人： Raquel Tato ,  Thomas Kemp ,  Antoni Abella

IPC分类号： G10L11/02 ,  G10L21/02 ,  G10L15/20 ,  G10L15/00

CPC分类号： G10L15/02 ,  G10L15/20 ,  G10L21/02

摘要： A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective band-dependent acoustic feature data for each of said respective frequency sub-bands, deriving band-dependent likelihoods for occurrences of speech elements or within said speech signal based on said band-dependent acoustic feature data, analyzing said speech signal within said spectrum, generating full-band acoustic feature data, which are at least in part representative for said speech signal with respect to said spectrum, deriving a full-band likelihood for occurrences of speech elements or of sequences thereof within said speech signal based on said full-band acoustic feature data, deriving an overall likelihood for occurrences of speech elements within said speech signal based on said band-dependent likelihoods and said full-band likelihood.

摘要翻译： 一种用于预处理语音的方法，特别是用于识别语音，包括接收语音信号，将所述语音信号的频谱分解成多个预定频率子频带，分析每个所述频率子频带内的所述语音信号， 针对所述各个频率子带中的每一个产生相应的频带相关的声学特征数据，基于所述频带依赖的声学特征数据导出语音元素的出现或所述语音信号中的频带相关似然，分析所述频谱内的所述语音信号 基于所述全频带声特征数据产生全频带声特征数据，所述全频带声特征数据至少部分地代表针对所述频谱的所述语音信号，在所述语音信号中导出出现语音元素或其序列的全频带似然， 基于所述ba，导出所述语音信号内出现语音元素的总体似然性 nd依赖的可能性和所述全频带可能性。

公开(公告)号：US07356467B2

公开(公告)日：2008-04-08

申请号：US10830835

申请日：2004-04-23

申请人： Thomas Kemp

发明人： Thomas Kemp

IPC分类号： G10L15/06

CPC分类号： G10L15/22

摘要： For processing recognized speech a method is proposed, which comprises the steps of receiving and/or generating (S0) recognized speech data (RSD), determining and/or generating (S1) a current measure of confidence (CMOC) for at least possibly erroneously recognized words of or within said recognized speech data (RSD), wherein an iterative process is performed comprising the following steps to be performed consecutively until a stopping condition (S3) is met: indicating/marking (S2, S5-B) at least some of said possibly erroneously recognized words as current indicated/marked errors (CIME) using said current measure of confidence (CMOC), receiving (S4) selection/correction data (SCD) being descriptive for a selection/correction with respect to said current indicated/marked errors (CIME), determining (S5) and/or generating an improved measure of confidence (IMOC) at least for further or remaining possibly erroneously recognized words of or within said recognized speech data (RSD). If the stopping condition is met, an improved recognition result (IRR) is output (S8).

摘要翻译： 为了处理识别的语音，提出了一种方法，其包括以下步骤：接收和/或产生（S 0）识别的语音数据（RSD），至少确定和/或生成（S1）当前的置信度度量（CMOC） 可能在所述识别语音数据（RSD）内或在所述识别语音数据（RSD）内的错误识别的单词，其中执行迭代处理，包括要连续执行的以下步骤，直到满足停止条件（S 3）：指示/标记（S 2，S 5 - B）使用所述当前的置信度测量（CMOC），接收（S 4）选择/校正数据（SCD）进行选择/校正的描述的至少一些所述可能的错误识别的词作为当前指示/标记的错误（CIME） 对于所述当前指示/标记错误（CIME），至少对于所述识别的语音数据中的或进一步的或可能的错误识别的字进行确定（S 5）和/或生成改进的置信度（IMOC） （RSD）。 如果满足停止条件，则输出改进的识别结果（IRR）（S8）。

公开(公告)号：US07292981B2

公开(公告)日：2007-11-06

申请号：US10957816

申请日：2004-10-04

申请人： Thomas Kemp ,  Yin Hay Lam ,  Krzysztof Marasek

发明人： Thomas Kemp ,  Yin Hay Lam ,  Krzysztof Marasek

IPC分类号： G10L25/14

CPC分类号： G10L15/08 ,  G10L15/02 ,  G10L15/20

摘要： A method for predicting a misrecognition in a speech recognition system, is based on; the insight that variations in a speech input signal are different depending on the origin of the signal being a speech or a non-speech event. The method comprises steps for receiving a speech input signal, extracting at least one signal variation feature of the speech input signal, and applying a signal variation meter to the speech input signal for deriving a signal variation measure.

摘要翻译： 一种用于预测语音识别系统中的误识别的方法是基于的; 根据作为语音或非语音事件的信号的原点，语音输入信号的变化是不同的。 该方法包括步骤：接收语音输入信号，提取语音输入信号的至少一个信号变化特征，以及将信号变化仪应用于语音输入信号以导出信号变化度量。

公开(公告)号：US20060229820A1

公开(公告)日：2006-10-12

申请号：US11188442

申请日：2005-07-25

申请人： Thomas Kemp

发明人： Thomas Kemp

IPC分类号： G06F19/00

CPC分类号： G01N33/0034

摘要： A method is proposed for identifying a chemical substance from a set of output states provided by a chemical sensor array being exposed to the chemical substance. The method comprises steps for selecting from a set of class descriptions for different chemical substances a first class description and one or more further class descriptions, whereby the first class description is related to a first chemical substance and a further class description is related to a further chemical substance, estimating a first likelihood value and one or more further likelihood values, whereby the first likelihood value represents a probability that the set of output states corresponds to the first class description, and a respective further likelihood value represents a probability that the set of output states corresponds to a respective further class description, and determining from the estimated first and further likelihood values the class description with the highest likelihood value. Hereby an estimation of a first and/or further likelihood value combines the likelihood values estimated for at least two subsets of the set of output states corresponding to the first and/or further class description, respectively.

摘要翻译： 提出了一种从暴露于化学物质的化学传感器阵列提供的一组输出状态中鉴定化学物质的方法。 该方法包括从用于不同化学物质的一组类别描述中选择第一类描述和一个或多个另外的类别描述的步骤，其中第一类描述与第一化学物质相关，并且另外的类描述与另外的类描述相关 化学物质，估计第一似然值和一个或多个其它似然值，由此第一似然值表示输出状态集合对应于第一类描述的概率，并且相应的进一步似然值表示该组 输出状态对应于相应的另外的类描述，并且从估计的第一和进一步似然值确定具有最高似然值的类描述。 因此，第一和/或另外的似然值的估计分别针对对应于第一和/或其他类描述的输出状态组的至少两个子集估计的似然值。

公开(公告)号：US20050187770A1

公开(公告)日：2005-08-25

申请号：US11042892

申请日：2005-01-24

申请人： Ralf Kompe ,  Thomas Kemp

发明人： Ralf Kompe ,  Thomas Kemp

IPC分类号： G10L15/06 ,  G10L15/22 ,  G10L17/00 ,  G10L15/00

CPC分类号： G10L15/065 ,  G10L17/02 ,  G10L17/04 ,  G10L2015/223

摘要： The present invention provides a method for operating and/or for controlling a man-machine interface unit (MMI) for a finite user group environment. Utterances out of a group of user are repeatedly received. A process of user identification is carried out based on said received utterances. The process of user identification comprises a set of clustering so as to enable an enrolment-free performance.

摘要翻译： 本发明提供了一种用于操作和/或控制用于有限用户组环境的人机接口单元（MMI）的方法。 重复接收一组用户的语音。 基于所述接收到的话语进行用户识别的处理。 用户识别的过程包括一组聚类，以便能够实现无注册的性能。

公开(公告)号：US20050120368A1

公开(公告)日：2005-06-02

申请号：US10985517

申请日：2004-11-10

申请人： Silke Goronzy ,  Thomas Kemp ,  Ralf Kompe ,  Yin Lam ,  Krzysztof Marasek ,  Raquel Tato

发明人： Silke Goronzy ,  Thomas Kemp ,  Ralf Kompe ,  Yin Lam ,  Krzysztof Marasek ,  Raquel Tato

IPC分类号： G06F17/30 ,  H04N7/16 ,  H04N5/445 ,  G06F3/00 ,  G06F13/00

CPC分类号： G11B27/034 ,  G06F16/735 ,  G06F16/739 ,  G06F16/7834 ,  G11B27/28 ,  H04N7/163 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/4532 ,  H04N21/458 ,  H04N21/4668 ,  H04N21/4826 ,  H04N21/84

摘要： A method and an apparatus for effecting the method are proposed that allow to define a subset of video signals from a source set of video signals on the basis of meta data available for the source set of video signals. The meta data assign a generic term to a sub-section of the audio channel of the source set of video signals, a class description to one or more sub-units of the sub-section for classifying the origin of the respective sub-unit, a category allocation to a segment, which is formed by a string of one or more classified sub-units of a sub-section, and a rating value to the segment for rating the reliability of the category allocation of the segment. The method includes steps for selecting segments of a sub-section with a rating value above a defined threshold value, assigning a priority value to each category, and specifying a first subset of video signals by defining an arrangement of selected segments by an order based on the respective priority and rating values related to each segment.

摘要翻译： 提出了一种用于实现该方法的方法和装置，其允许基于可用于视频信号源组的元数据来定义来自视频信号源集合的视频信号的子集。 元数据将通用术语分配给视频信号源集合的音频信道的子部分，对用于对相应子单元的原点进行分类的子部分的一个或多个子单元的类别描述， 由分段的一个或多个分类子单元的串形成的段的类别分配以及用于对该段的类别分配的可靠性进行评级的段的评级值。 该方法包括用于选择具有高于定义的阈值的评级值的子部分的段的步骤，为每个类别分配优先级值，以及通过基于以下的顺序定义所选择的段的排列来指定视频信号的第一子集： 与每个细分相关的各自的优先级和评级值。

公开(公告)号：US20050114135A1

公开(公告)日：2005-05-26

申请号：US10957816

申请日：2004-10-04

申请人： Thomas Kemp ,  Yin Hay Lam ,  Krzysztof Marasek

发明人： Thomas Kemp ,  Yin Hay Lam ,  Krzysztof Marasek

IPC分类号： G10L15/28 ,  G10L15/02 ,  G10L15/08 ,  G10L15/10 ,  G10L15/14 ,  G10L15/18 ,  G10L15/20

CPC分类号： G10L15/08 ,  G10L15/02 ,  G10L15/20

摘要： Based on the insight that variations in a speech input signal are different depending on the origin of the signal being a speech or a non-speech event, the present invention proposes method for predicting a misrecognition in a speech recognition system with steps for receiving a speech input signal, extracting at least one signal variation feature of the speech input signal, and applying a signal variation meter to the speech input signal for deriving a signal variation measure.

摘要翻译： 基于语音输入信号的变化根据作为语音或非语音事件的信号的原点而不同的观点，本发明提出了一种用于在具有用于接收语音的步骤的语音识别系统中预测误识别的方法 输入信号，提取所述语音输入信号的至少一个信号变化特征，以及将信号变化计应用于所述语音输入信号以导出信号变化度量。

公开(公告)号：US10384016B2

公开(公告)日：2019-08-20

申请号：US13983805

申请日：2012-02-16

申请人： Simon Francis Brereton ,  Thomas Kemp ,  Rosie Burnell ,  Matthew Ekman

发明人： Simon Francis Brereton ,  Thomas Kemp ,  Rosie Burnell ,  Matthew Ekman

IPC分类号： A61M5/20 ,  A61M5/315 ,  A61M5/32 ,  A61M5/46 ,  A61M5/50

摘要： An auto-injector for administering a dose of a liquid medicament (M) is presented having an elongate case, a carrier subassembly comprising a tubular carrier slidably arranged inside the case, where the carrier adapted to contain a syringe with a hollow injection needle. The injector also has, a drive spring and a plunger for forwarding load of the drive spring to a stopper of the syringe, wherein the syringe is lockable for joint axial translation with the carrier. A control spring is arranged around the carrier for translating the carrier in a proximal direction (P) for advancing the needle beyond a proximal end of the auto-injector, and a trigger button is used for releasing the control spring on actuation.