-
公开(公告)号:US06850885B2
公开(公告)日:2005-02-01
申请号:US10021776
申请日:2001-12-12
申请人: Daniela Raddino , Ralf Kompe , Thomas Kemp
发明人: Daniela Raddino , Ralf Kompe , Thomas Kemp
CPC分类号: G10L15/142 , G10L2015/088
摘要: To increase the accuracy and the flexibility of a method for recognizing speech which employs a keyword spotting process on the basis of a combination of a keyword model (KM) and a garbage model (GM) it is suggested to associate at least one variable penalty value (Ptrans, P1, . . . , P6) with a global penalty (Pglob) so as to increase the recognition of keywords (Kj).
摘要翻译: 为了提高基于关键词模型(KM)和垃圾模型(GM)的组合的采用关键字识别处理的识别语音的方法的准确性和灵活性,建议将至少一个可变惩罚值 (Ptrans,P1,...,P6),具有全局惩罚(Pglob),以增加关键词(Kj)的识别。
-
22.
公开(公告)号:US07373301B2
公开(公告)日:2008-05-13
申请号:US10209134
申请日:2002-07-31
申请人: Thomas Kemp , Ralf Kompe , Raquel Tato
发明人: Thomas Kemp , Ralf Kompe , Raquel Tato
IPC分类号: G10L11/00
CPC分类号: G10L17/26
摘要: To reduce the error rate when classifying emotions from an acoustical speech input (SI) only, it is suggested to include a process of speaker identification to obtain certain speaker identification data (SID) on the basis of which the process of recognizing an emotional state is adapted and/or configured. In particular, speaker-specific feature extractors (FE) and/or emotion classifiers (EC) are selected based on said speaker identification data (SID).
摘要翻译: 为了在从声学语音输入(SI)分类情绪时降低错误率,建议包括说话者识别的过程以获得某些说话者识别数据(SID),在此基础上识别情感状态的过程是 适应和/或配置。 特别地,基于所述扬声器识别数据(SID)来选择特定于扬声器的特征提取器(FE)和/或情感分类器(EC)。
-
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
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。
-
公开(公告)号:US07620547B2
公开(公告)日:2009-11-17
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
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:US20080319747A1
公开(公告)日:2008-12-25
申请号:US12195136
申请日:2008-08-20
申请人: Ralf Kompe , Thomas Kemp
发明人: Ralf Kompe , Thomas Kemp
IPC分类号: G10L15/06
CPC分类号: G10L15/065 , G10L17/02 , G10L17/04 , G10L2015/223
摘要: The method of operating a man-machine interface unit includes classifying at least one utterance of a speaker to be of a first type or of a second type. If the utterance is classified to be of the first type, the utterance belongs to a known speaker of a speaker data base, and if the utterance is classified to be of the second type, the utterance belongs to an unknown speaker that is not included in the speaker data base. The method also includes storing a set of utterances of the second type, clustering the set of utterances into clusters, wherein each cluster comprises utterances having similar features, and automatically adding a new speaker to the speaker data base based on utterances of one of the clusters.
摘要翻译: 操作人机接口单元的方法包括将扬声器的至少一个话语分类为第一类型或第二类型。 如果发音被分类为第一类型,话语属于扬声器数据库的已知扬声器,并且如果话语被分类为第二类型,话语属于未包括在未知扬声器中的未知扬声器 扬声器数据库。 该方法还包括存储第二类型的话语集合,将该组语音聚类成群集,其中每个群集包括具有相似特征的话语,并且基于该群集中的一个的话语自动地将新的扬声器添加到该扬声器数据库 。
-
公开(公告)号:US08200488B2
公开(公告)日:2012-06-12
申请号:US10731929
申请日:2003-12-10
申请人: Thomas Kemp , Ralf Kompe , Raquel Tato
发明人: Thomas Kemp , Ralf Kompe , Raquel Tato
IPC分类号: G10L15/00
摘要: The invention provides a method for processing speech comprising the steps of receiving a speech input (SI) of a speaker, generating speech parameters (SP) from said speech input (SI), determining parameters describing an absolute loudness (L) of said speech input (SI), and evaluating (EV) said speech input (SI) and/or said speech parameters (SP) using said parameters describing the absolute loudness (L). In particular, the step of evaluation (EV) comprises a step of emotion recognition and/or speaker identification. Further, a microphone array comprising a plurality of microphones is used for determining said parameters describing the absolute loudness. With a microphone array the distance of the speaker from the microphone array can be determined and the loudness can be normalized by the distance. Thus, the absolute loudness becomes independent from the distance of the speaker to the microphone, and absolute loudness can now be used as an input parameter for emotion recognition and/or speaker identification.
摘要翻译: 本发明提供了一种处理语音的方法,包括以下步骤:接收讲话者的语音输入(SI),从所述语音输入(SI)产生语音参数(SP),确定描述所述语音输入的绝对响度(L)的参数 (SI),以及使用描述绝对响度(L)的参数来评估(EV)所述语音输入(SI)和/或所述语音参数(SP)。 特别地,评估步骤(EV)包括情绪识别和/或说话人识别的步骤。 此外,包括多个麦克风的麦克风阵列用于确定描述绝对响度的所述参数。 使用麦克风阵列,可以确定扬声器与麦克风阵列的距离,并且响度可以通过距离归一化。 因此,绝对响度与扬声器与麦克风的距离无关,现在可以将绝对响度用作用于情绪识别和/或扬声器识别的输入参数。
-
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
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。
-
公开(公告)号:US07769588B2
公开(公告)日:2010-08-03
申请号:US12195136
申请日:2008-08-20
申请人: Ralf Kompe , Thomas Kemp
发明人: Ralf Kompe , Thomas Kemp
IPC分类号: G10L15/06
CPC分类号: G10L15/065 , G10L17/02 , G10L17/04 , G10L2015/223
摘要: The method of operating a man-machine interface unit includes classifying at least one utterance of a speaker to be of a first type or of a second type. If the utterance is classified to be of the first type, the utterance belongs to a known speaker of a speaker data base, and if the utterance is classified to be of the second type, the utterance belongs to an unknown speaker that is not included in the speaker data base. The method also includes storing a set of utterances of the second type, clustering the set of utterances into clusters, wherein each cluster comprises utterances having similar features, and automatically adding a new speaker to the speaker data base based on utterances of one of the clusters.
摘要翻译: 操作人机接口单元的方法包括将扬声器的至少一个话语分类为第一类型或第二类型。 如果发音被分类为第一类型,话语属于扬声器数据库的已知扬声器,并且如果话语被分类为第二类型,话语属于未包括在未知扬声器中的未知扬声器 扬声器数据库。 该方法还包括存储第二类型的话语集合,将该组语音聚类成群集,其中每个群集包括具有相似特征的话语,并且基于该群集中的一个的话语自动地将新的扬声器添加到该扬声器数据库 。
-
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
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。
-
-
-
-
-
-
-
-