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

IPC分类号： G10L15/08 ,  G10L15/00 ,  G10L15/10 ,  G10L15/14 ,  G10L15/20

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。

公开(公告)号：US08635065B2

公开(公告)日：2014-01-21

申请号：US10985446

申请日：2004-11-10

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

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

IPC分类号： G10L15/06 ,  G10L21/00 ,  G10L19/12 ,  G10L19/14 ,  G10L17/00

CPC分类号： G10L25/00 ,  G10L15/00 ,  G10L17/26

摘要： The present invention discloses an apparatus for automatic extraction of important events in audio signals comprising: signal input means for supplying audio signals; audio signal fragmenting means for partitioning audio signals supplied by the signal input means into audio fragments of a predetermined length and for allocating a sequence of one or more audio fragments to a respective audio window; feature extracting means for analyzing acoustic characteristics of the audio signals comprised in the audio fragments and for analyzing acoustic characteristics of the audio signals comprised in the audio windows; and important event extraction means for extracting important events in audio signals supplied by the audio signal fragmenting means based on predetermined important event classifying rules depending on acoustic characteristics of the audio signals comprised in the audio fragments and on acoustic characteristics of the audio signals comprised in the audio windows, wherein each important event extracted by the important event extraction means comprises a discrete sequence of cohesive audio fragments corresponding to an important event included in the audio signals.

摘要翻译： 本发明公开了一种用于自动提取音频信号中的重要事件的装置，包括：用于提供音频信号的信号输入装置; 用于将由信号输入装置提供的音频信号划分成预定长度的音频片段并用于将一个或多个音频片段的序列分配到相应音频窗口的音频信号分段装置; 特征提取装置，用于分析包含在音频片段中的音频信号的声学特性并分析包含在音频窗口中的音频信号的声学特性; 以及重要事件提取装置，用于根据包含在音频片段中的音频信号的声学特性以及包含在音频片段中的音频信号的声学特性，基于预定的重要事件分类规则，提取由音频信号分段装置提供的音频信号中的重要事件。 音频窗口，其中由重要事件提取装置提取的每个重要事件包括对应于包括在音频信号中的重要事件的粘性音频片段的离散序列。

公开(公告)号：US07680654B2

公开(公告)日：2010-03-16

申请号：US10985615

申请日：2004-11-10

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

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

IPC分类号： G10L15/00 ,  G10L15/20

CPC分类号： G10L25/00

摘要： An audio data segmentation apparatus for segmenting of audio data including for supplying audio data, dividing the audio data supplied into audio clips of a predetermined length, discriminating the audio clips into predetermined audio classes, the audio classes identifying a kind of audio data included in the respective audio clip and segmenting for segmenting the audio data into audio meta patterns based on a sequence of audio classes of consecutive audio clips, each meta pattern being allocated to a predetermined type of contents of the audio data. It is difficult to achieve good results with known methods for segmentation of audio data into meta patterns since the rules for the allocation of the meta patterns are dissatisfying. This problem is solved by the inventive audio data segmentation apparatus further including a program database including program data units to identify a certain kind of program, a plurality of respective audio meta patterns being allocated to each program data unit, wherein the segmenting segments the audio data into corresponding audio meta patterns on the basis of the program data units of the program database 5.

摘要翻译： 一种用于分割音频数据的音频数据分割装置，包括用于提供音频数据，将提供的音频数据分成预定长度的音频剪辑，将音频剪辑识别为预定音频类别，识别包括在音频数据中的音频数据的种类的音频类别 相应的音频剪辑和分段，用于基于连续音频剪辑的音频类别序列将音频数据分割成音频元模式，每个元模式被分配给音频数据的预定类型的内容。 由于元模式的分配规则不满意，因此将音频数据分割为元模式的已知方法难以获得良好的结果。 本发明的音频数据分割装置还包括程序数据库，该程序数据库包括用于识别特定类型的程序的程序数据单元，分配给每个程序数据单元的多个各自的音频元模式，其中分段将音频数据分段 基于程序数据库5的程序数据单元转换成对应的音频元模式。

公开(公告)号：US20050102135A1

公开(公告)日：2005-05-12

申请号：US10985446

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： G10L15/00 ,  G10L17/26 ,  G10L25/00 ,  H04N5/91

CPC分类号： G10L25/00 ,  G10L15/00 ,  G10L17/26

摘要： The present invention discloses an apparatus for automatic extraction of important events in audio signals comprising: signal input means for supplying audio signals; audio signal fragmenting means for partitioning audio signals supplied by the signal input means into audio fragments of a predetermined length and for allocating a sequence of one or more audio fragments to a respective audio window; feature extracting means for analysing acoustic characteristics of the audio signals comprised in the audio fragments and for analysing acoustic characteristics of the audio signals comprised in the audio windows; and important event extraction means for extracting important events in audio signals supplied by the audio signal fragmenting means based on predetermined important event classifying rules depending on acoustic characteristics of the audio signals comprised in the audio fragments and on acoustic characteristics of the audio signals comprised in the audio windows, wherein each important event extracted by the important event extraction means comprises a discrete sequence of cohesive audio fragments corresponding to an important event included in the audio signals.

摘要翻译： 本发明公开了一种用于自动提取音频信号中的重要事件的装置，包括：用于提供音频信号的信号输入装置; 用于将由信号输入装置提供的音频信号划分成预定长度的音频片段并用于将一个或多个音频片段的序列分配到相应音频窗口的音频信号分段装置; 特征提取装置，用于分析包含在音频片段中的音频信号的声学特性并分析包含在音频窗口中的音频信号的声学特性; 以及重要事件提取装置，用于根据包含在音频片段中的音频信号的声学特性以及包含在音频片段中的音频信号的声学特性，基于预定的重要事件分类规则，提取由音频信号分段装置提供的音频信号中的重要事件。 音频窗口，其中由重要事件提取装置提取的每个重要事件包括对应于包括在音频信号中的重要事件的粘性音频片段的离散序列。

公开(公告)号：US06862497B2

公开(公告)日：2005-03-01

申请号：US10343525

申请日：2002-06-03

申请人： Thomas Kemp ,  Ralf Kompe ,  Raquel Tato ,  Masahiro Fujita ,  Katsuki Minamino ,  Kenta Kawamoto ,  Rika Horinaka

发明人： Thomas Kemp ,  Ralf Kompe ,  Raquel Tato ,  Masahiro Fujita ,  Katsuki Minamino ,  Kenta Kawamoto ,  Rika Horinaka

IPC分类号： B62D57/02 ,  B62D57/032 ,  G05B13/02 ,  G05B19/042 ,  G05B15/00 ,  G05B19/33

CPC分类号： G05B19/042 ,  B62D57/02 ,  B62D57/032 ,  G05B13/0265

摘要： There is proposed a method that may be universally used for controlling a man-machine interface unit. A learning sample is used in order at least to derive and/or initialize a target action (t) to be carried out and to lead the user from an optional current status (ec) to an optional desired target status (et) as the final status (ef). This learning sample (l) is formed by a data triple made up by an initial status (ei) before an optional action (a) carried out by the user, a final status (ef) after the action taken place (a).

摘要翻译： 提出了可以普遍地用于控制人机接口单元的方法。 至少使用学习样本来导出和/或初始化要执行的目标动作（t），并且将用户从可选的当前状态（ec）引导到可选的期望目标状态（et），作为最终的 状态（ef）。 该学习样本（l）由在用户执行的可选动作（a）之前由初始状态（ei）组成的数据三进制形成，（a）动作之后的最终状态（ef）。

公开(公告)号：US07962330B2

公开(公告)日：2011-06-14

申请号：US10985451

申请日：2004-11-10

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

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

IPC分类号： G10L19/00 ,  G10L11/00 ,  G10L15/00 ,  G06F17/00 ,  H04N7/16 ,  H04N7/173

CPC分类号： G10L25/00 ,  G10L15/00 ,  Y10S707/913

摘要： An apparatus for automatic dissection of segmented audio signals, wherein at least one information signal for identifying programs included in said audio signals and for identifying contents included in said programs. Content detection device detects programs and contents belonging to the respective programs in the information signal. Program weighting device weights each program includes in the information signal based on the contents of the respective program detected by the content detection device. Program ranking device indentifies programmers of the same category and ranking said programs based on a weighting result for each program provided by the program weighting device.

摘要翻译： 一种用于自动解剖分段音频信号的装置，其中至少一个信息信号用于识别包括在所述音频信号中的节目，并用于识别包括在所述节目中的内容。 内容检测装置检测信息信号中属于各个节目的节目和内容。 每个程序的程序加权设备权重包括在基于由内容检测设备检测到的相应程序的内容的信息信号中。 程序排名装置识别相同类别的程序员，并且基于由程序加权装置提供的每个程序的加权结果对所述程序进行排序。

公开(公告)号：US20090282034A1

公开(公告)日：2009-11-12

申请号：US12507574

申请日：2009-07-22

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

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 mufti-user profile is split during the creation of an individual user profile from a mufti-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词列表中的权重，和/或在创建用户简档期间分割多个用户简档。 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：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：US20060156326A1

公开(公告)日：2006-07-13

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： H04N7/16 ,  H04N5/445 ,  H04H9/00 ,  G06F3/00

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.

公开(公告)号：US20050131688A1

公开(公告)日：2005-06-16

申请号：US10985295

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： G10L15/10 ,  G10L15/26 ,  G10L25/78 ,  G10L15/12

CPC分类号： G10L25/78 ,  G10L15/26 ,  G11B2220/20

摘要： An apparatus for classifying audio signals comprises audio signal clipping means for partitioning audio signals into audio clips, and class discrimination means for discriminating the audio clips provided by the audio signal clipping means into predetermined audio classes based on predetermined audio class classifying rules, by analysing acoustic characteristics of the audio signals comprised in the audio clips, wherein a predetermined audio class classifying rule is provided for each audio class, and each audio class represents a respective kind of audio signals comprised in the corresponding audio clip. The determination process to find acceptable audio class classifying rules for each audio class according to the prior art is depending on both the used raw audio signals and the personal experience of the person conducting the determination process. Thus, the determination process usually is very difficult, time consuming and subjective. Furthermore, there is a high risk that not all possible peculiarities of the different programmes and the different categories the audio signal can belong to is sufficiently accounted for. This problem is solved in the inventive apparatus for classifying audio signals by class discrimination means calculating an audio class confidence value for each audio class assigned to an audio clip, wherein the audio class confidence value indicates the likelihood the respective audio class characterises the respective kind of audio signals comprised in the respective audio clip correctly. Furthermore, the class discrimination means use acoustic characteristics of audio clips of audio classes having a high audio class confidence value to train the respective audio class classifying rule.

摘要翻译： 用于对音频信号进行分类的装置包括用于将音频信号分割成音频剪辑​​的音频信号限幅装置，以及用于基于预定音频类别分类规则，将由音频信号限幅装置提供的音频片段识别为预定音频类别的类别鉴别装置，通过分析声音 包括在音频剪辑中的音频信号的特征，其中为每个音频类提供预定音频类别分类规则，并且每个音频类表示包括在相应的音频剪辑中的各种音频信号。 根据现有技术，为每个音频类找到可接受的音频类别分类规则的确定过程取决于所使用的原始音频信号和进行确定处理的人的个人经历。 因此，确定过程通常是非常困难，耗时和主观的。 此外，充分考虑到不同于音频信号可能属于不同节目和不同类别的所有可能的特征的高风险。 在本发明的用于对音频信号进行分类的设备中解决了这个问题，该类别鉴别装置为分配给音频剪辑的每个音频类别计算音频类别置信度值，其中，音频类别置信度值表示各个音频类别 包含在相应音频剪辑中的音频信号正确。 此外，等级识别装置使用具有高音频类置信度值的音频类别的音频剪辑的声学特性来训练各个音频类别分类规则。