公开(公告)号：US09489946B2

公开(公告)日：2016-11-08

申请号：US13420828

申请日：2012-03-15

申请人： Kouji Ueno ,  Nobuhiro Shimogori ,  Tomoo Ikeda ,  Osamu Nisiyama ,  Hirokazu Suzuki ,  Manabu Nagao

发明人： Kouji Ueno ,  Nobuhiro Shimogori ,  Tomoo Ikeda ,  Osamu Nisiyama ,  Hirokazu Suzuki ,  Manabu Nagao

IPC分类号： G10L15/26 ,  G06Q10/10 ,  G10L15/22

CPC分类号： G10L15/26 ,  G06Q10/10 ,  G10L2015/221 ,  G10L2015/225

摘要： In an embodiment, a transcription support system includes: a first storage, a playback unit, a second storage, a text generating unit, an estimating unit, and a setting unit. The first storage stores the voice data therein; a playback unit plays back the voice data; and a second storage stores voice indices, each of which associates a character string obtained from a voice recognition process with voice positional information, for which the voice positional information is indicative of a temporal position in the voice data and corresponds to the character string. The text creating unit creates text; the estimating unit estimates already-transcribed voice positional information based on the voice indices; and the setting unit sets a playback starting position that indicates a position at which playback is started in the voice data based on the already-transcribed voice positional information.

摘要翻译： 在一个实施例中，转录支持系统包括：第一存储器，回放单元，第二存储器，文本生成单元，估计单元和设置单元。 第一存储器中存储语音数据; 播放单元播放语音数据; 并且第二存储器存储语音索引，每个声音索引将从语音识别处理获得的字符串与语音位置信息相关联，语音位置信息指示语音数据中的时间位置并对应于字符串。 文本创建单元创建文本; 估计单元基于语音索引估计已经转录的语音位置信息; 并且所述设定单元基于已经转录的语音位置信息，设置指示在所述语音数据中开始重放的位置的重放开始位置。

公开(公告)号：US20060239130A1

公开(公告)日：2006-10-26

申请号：US11391389

申请日：2006-03-29

申请人： Kohei Momosaki ,  Tatsuya Uehara ,  Kazunori Imoto ,  Yasuyuki Masai ,  Kazuhiko Abe ,  Manabu Nagao ,  Munehiko Sasajima

发明人： Kohei Momosaki ,  Tatsuya Uehara ,  Kazunori Imoto ,  Yasuyuki Masai ,  Kazuhiko Abe ,  Manabu Nagao ,  Munehiko Sasajima

IPC分类号： H04B1/20

CPC分类号： G11B27/28 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30758 ,  G06F17/30787 ,  G11B27/322

摘要： An information processing apparatus is provided in which with respect to video/audio data to be recorded and stored, the determination of division and a control point suitable for viewing and listening and the giving of relevant information can be performed without requiring a manual operation each time. The information processing apparatus includes a recording medium 90, a video data acquisition unit 48, a video data specification unit 47, an audio data separation unit 25, a key creation unit 31, a key relevant data acquisition unit 55, and a key data management unit 10. When a key is created while specifying a section in first audio data, a name and attribute information based on a near division point and control point are stored, and when an audio section similar to an audio pattern of the key is detected from second audio data, in accordance with the stored attribute information, a division point and a control point are determined on the basis of starting and terminal ends of the detected section, and the stored name or a name given in accordance with a naming method is set for the divided section, the control point or the whole audio data.

摘要翻译： 提供了一种信息处理装置，其中对于要记录和存储的视频/音频数据，可以执行适合于观看和收听和给出相关信息的划分确定和控制点，而不需要每次手动操作 。 信息处理装置包括记录介质90，视频数据获取单元48，视频数据指定单元47，音频数据分离单元25，密钥创建单元31，密钥相关数据获取单元55和密钥数据管理 单位10 当在第一音频数据中指定部分时创建键时，存储基于近分割点和控制点的名称和属性信息，并且当从第二音频数据检测到与键的音频模式类似的音频部分时 根据所存储的属性信息，基于所检测部分的开始和终点来确定分割点和控制点，并且将所分配的名称或命名方法给出的名称设置为分割 部分，控制点或整个音频数据。

公开(公告)号：US20050259959A1

公开(公告)日：2005-11-24

申请号：US11129381

申请日：2005-05-16

申请人： Manabu Nagao ,  Kohei Momosaki

发明人： Manabu Nagao ,  Kohei Momosaki

IPC分类号： H04N5/76 ,  G11B27/10 ,  G11B27/11 ,  G11B27/28 ,  G11B27/34 ,  H04N5/775 ,  H04N5/781 ,  H04N5/783 ,  H04N5/907

CPC分类号： H04N5/775 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/28 ,  G11B27/34 ,  G11B2220/20 ,  G11B2220/90 ,  H04N5/781 ,  H04N5/907

摘要： A media data memory stores media data including at least one of speech data and image data both playable in time series. A play control display unit displays a plurality of time figures. Each time figure corresponds to a play time of a part of the media data in time series order. A data selection unit selects at least one time figure from the plurality of time figures through the play control display unit. A play control unit moves a play position to a part of the play time corresponding to the at least one time figure in the media data. A play unit plays the media data from the play position moved by the play control unit.

摘要翻译： 媒体数据存储器存储包括能够以时间序列播放的语音数据和图像数据中的至少一个的媒体数据。 播放控制显示单元显示多个时间图。 每个时间图以时间序列顺序对应于媒体数据的一部分的播放时间。 数据选择单元通过播放控制显示单元从多个时间图中选择至少一个时间图。 播放控制单元将播放位置移动到与媒体数据中的至少一个时间图对应的播放时间的一部分。 播放单元从播放控制单元移动的播放位置播放媒体数据。

公开(公告)号：US08275730B2

公开(公告)日：2012-09-25

申请号：US12558761

申请日：2009-09-14

申请人： Manabu Nagao

发明人： Manabu Nagao

IPC分类号： G06F17/00 ,  G06F7/60 ,  G06F7/38

CPC分类号： G06N5/02

摘要： States included in a deterministic finite automaton are classified into states having the same input symbols associated with outgoing transitions and the same finality, and a calculates an intersection set between each of the state sets and a set of transition destination states which is obtained by translating each of states included in the state sets, until the number of states included in the intersection set becomes equal to one, while regarding the set of the transition destination states for each of the input symbol included in the intersection set as new state sets, and plural indistinguishable states are merged into one state by tracing a route in a reverse direction to a transition direction, when the number of states has become equal to one.

摘要翻译： 包含在确定性有限自动机中的状态被分类为具有与输出转变相关联的相同输入符号和相同最终性的状态，并且计算每个状态集与一组转换目的地状态之间的交集，该集合通过翻译每个 包括在状态集中的状态，直到包含在交集中的状态数变为等于1，同时关于包含在交集中的每个输入符号的转移目的地状态的集合作为新的状态集合，并且多个 当状态数变为等于1时，通过跟踪与转换方向相反的方向将不可区分的状态合并成一个状态。

公开(公告)号：US20120046935A1

公开(公告)日：2012-02-23

申请号：US13231065

申请日：2011-09-13

申请人： Manabu Nagao

发明人： Manabu Nagao

IPC分类号： G06F17/20

CPC分类号： G06F17/2775 ,  G10L15/144

摘要： According to one embodiment, a finite state transducer determinizing device includes a symbol determination unit, a state merging unit, and a single-value processing unit. The symbol determination unit generates an identification symbol different from an input symbol assigned to each transition of a finite state transducer. The state merging unit extracts one or more states at a transition destination by the same input symbol from among the states of the finite state transducer and generates states having the extracted states as sub-states. The single-value processing unit applies the input symbol assigned to each transition of the finite state transducer or the identification symbol as an input symbol of a transition between the states generated by the state merging unit to perform determinizing.

摘要翻译： 根据一个实施例，有限状态换能器确定装置包括符号确定单元，状态合并单元和单值处理单元。 符号确定单元生成与分配给有限状态换能器的每个转换的输入符号不同的识别符号。 状态合并单元从有限状态换能器的状态中通过相同的输入符号在转换目的地提取一个或多个状态，并且生成具有提取状态的状态作为子状态。 单值处理单元将分配给有限状态换能器或识别符号的每个转换的输入符号应用于由状态合并单元生成的状态之间的转换的输入符号，以执行确定。

公开(公告)号：US08744836B2

公开(公告)日：2014-06-03

申请号：US13231065

申请日：2011-09-13

申请人： Manabu Nagao

发明人： Manabu Nagao

IPC分类号： G06F17/27 ,  G10L15/00

CPC分类号： G06F17/2775 ,  G10L15/144

摘要： According to one embodiment, a finite state transducer determinizing device includes a symbol determination unit, a state merging unit, and a single-value processing unit. The symbol determination unit generates an identification symbol different from an input symbol assigned to each transition of a finite state transducer. The state merging unit extracts one or more states at a transition destination by the same input symbol from among the states of the finite state transducer and generates states having the extracted states as sub-states. The single-value processing unit applies the input symbol assigned to each transition of the finite state transducer or the identification symbol as an input symbol of a transition between the states generated by the state merging unit to perform determinizing.

摘要翻译： 根据一个实施例，有限状态换能器确定装置包括符号确定单元，状态合并单元和单值处理单元。 符号确定单元生成与分配给有限状态换能器的每个转换的输入符号不同的识别符号。 状态合并单元从有限状态换能器的状态中通过相同的输入符号在转换目的地提取一个或多个状态，并且生成具有提取状态的状态作为子状态。 单值处理单元将分配给有限状态换能器或识别符号的每个转换的输入符号应用于由状态合并单元生成的状态之间的转换的输入符号，以执行确定。

公开(公告)号：US20130030806A1

公开(公告)日：2013-01-31

申请号：US13420828

申请日：2012-03-15

申请人： Kouji Ueno ,  Nobuhiro Shimogori ,  Tomoo Ikeda ,  Osamu Nisiyama ,  Hirokazu Suzuki ,  Manabu Nagao

发明人： Kouji Ueno ,  Nobuhiro Shimogori ,  Tomoo Ikeda ,  Osamu Nisiyama ,  Hirokazu Suzuki ,  Manabu Nagao

IPC分类号： G10L15/26

CPC分类号： G10L15/26 ,  G06Q10/10 ,  G10L2015/221 ,  G10L2015/225

摘要： In an embodiment, a transcription support system includes: a first storage, a playback unit, a second storage, a text generating unit, an estimating unit, and a setting unit. The first storage stores the voice data therein; a playback unit plays back the voice data; and a second storage stores voice indices, each of which associates a character string obtained from a voice recognition process with voice positional information, for which the voice positional information is indicative of a temporal position in the voice data and corresponds to the character string. The text creating unit creates text; the estimating unit estimates already-transcribed voice positional information based on the voice indices; and the setting unit sets a playback starting position that indicates a position at which playback is started in the voice data based on the already-transcribed voice positional information.

摘要翻译： 在一个实施例中，转录支持系统包括：第一存储器，回放单元，第二存储器，文本生成单元，估计单元和设置单元。 第一存储器中存储语音数据; 播放单元播放语音数据; 并且第二存储器存储语音索引，每个声音索引将从语音识别处理获得的字符串与语音位置信息相关联，语音位置信息指示语音数据中的时间位置并对应于字符串。 文本创建单元创建文本; 估计单元基于语音索引估计已经转录的语音位置信息; 并且所述设定单元基于已经转录的语音位置信息，设置指示在所述语音数据中开始重放的位置的重放开始位置。

公开(公告)号：US20130030794A1

公开(公告)日：2013-01-31

申请号：US13412694

申请日：2012-03-06

申请人： Tomoo Ikeda ,  Manabu Nagao ,  Osamu Nishiyama ,  Hirokazu Suzuki ,  Koji Ueno ,  Nobuhiro Shimogori

发明人： Tomoo Ikeda ,  Manabu Nagao ,  Osamu Nishiyama ,  Hirokazu Suzuki ,  Koji Ueno ,  Nobuhiro Shimogori

IPC分类号： G10L15/02 ,  G06F17/27

CPC分类号： G10L21/028 ,  G10L15/26

摘要： According to one embodiment, a speaker clustering apparatus includes a clustering unit, an extraction unit, and an error detection unit. The clustering unit is configured to extract acoustic features for speakers from an acoustic signal, and to cluster utterances included in the acoustic signal into the speakers by using the acoustic features. The extraction unit is configured to acquire character strings representing contents of the utterances, and to extract linguistic features of the speakers by using the character strings. The error detection unit is configured to decide that, when one of the character strings does not fit with a linguistic feature of a speaker into which an utterance of the one is clustered, the utterance is erroneously clustered by the clustering unit.

摘要翻译： 根据一个实施例，扬声器群集设备包括聚类单元，提取单元和错误检测单元。 聚类单元被配置为从声学信号提取扬声器的声学特征，并且通过使用声学特征将包括在声学信号中的声音聚类到扬声器中。 提取单元被配置为获取表示话语内容的字符串，并且通过使用字符串来提取扬声器的语言特征。 错误检测单元被配置为当其中一个字符串不符合一个发音的扬声器的语言特征被聚集时，该话音被该聚类单元错误地聚集。

公开(公告)号：US08019163B2

公开(公告)日：2011-09-13

申请号：US11391389

申请日：2006-03-29

申请人： Kohei Momosaki ,  Tatsuya Uehara ,  Kazunori Imoto ,  Yasuyuki Masai ,  Kazuhiko Abe ,  Manabu Nagao ,  Munehiko Sasajima

发明人： Kohei Momosaki ,  Tatsuya Uehara ,  Kazunori Imoto ,  Yasuyuki Masai ,  Kazuhiko Abe ,  Manabu Nagao ,  Munehiko Sasajima

IPC分类号： H04B1/20

CPC分类号： G11B27/28 ,  G06F17/30743 ,  G06F17/30749 ,  G06F17/30758 ,  G06F17/30787 ,  G11B27/322

摘要： An information processing apparatus is provided in which with respect to video/audio data to be recorded and stored, the determination of division and a control point suitable for viewing and listening and the giving of relevant information can be performed without requiring a manual operation each time. The information processing apparatus includes a recording medium 90, a video data acquisition unit 48, a video data specification unit 47, an audio data separation unit 25, a key creation unit 31, a key relevant data acquisition unit 55, and a key data management unit 10. When a key is created while specifying a section in first audio data, a name and attribute information based on a near division point and control point are stored, and when an audio section similar to an audio pattern of the key is detected from second audio data, in accordance with the stored attribute information, a division point and a control point are determined on the basis of starting and terminal ends of the detected section, and the stored name or a name given in accordance with a naming method is set for the divided section, the control point or the whole audio data.

摘要翻译： 提供了一种信息处理装置，其中对于要记录和存储的视频/音频数据，可以执行适合于观看和收听和给出相关信息的划分确定和控制点，而不需要每次手动操作 。 信息处理装置包括记录介质90，视频数据获取单元48，视频数据指定单元47，音频数据分离单元25，密钥创建单元31，密钥相关数据获取单元55和密钥数据管理 单元10.当在第一音频数据中指定段时创建密钥时，存储基于近分割点和控制点的名称和属性信息，并且当从键的音频图案类似的音频部分被检测到 第二音频数据根据存储的属性信息，基于所检测的部分的开始和终点来确定分割点和控制点，并且设置存储的名称或根据命名方法给出的名称 对于分割部分，控制点或整个音频数据。

公开(公告)号：US20100082522A1

公开(公告)日：2010-04-01

申请号：US12558761

申请日：2009-09-14

申请人： Manabu NAGAO

发明人： Manabu NAGAO

IPC分类号： G06N5/02

CPC分类号： G06N5/02

摘要： States included in a deterministic finite automaton are classified into states having the same input symbols associated with outgoing transitions and the same finality, and a calculates an intersection set between each of the state sets and a set of transition destination states which is obtained by translating each of states included in the state sets, until the number of states included in the intersection set becomes equal to one, while regarding the set of the transition destination states for each of the input symbol included in the intersection set as new state sets, and plural indistinguishable states are merged into one state by tracing a route in a reverse direction to a transition direction, when the number of states has become equal to one.

摘要翻译： 包含在确定性有限自动机中的状态被分类为具有与输出转变相关联的相同输入符号和相同最终性的状态，并且计算每个状态集与一组转换目的地状态之间的交集，该集合通过翻译每个 包括在状态集中的状态，直到包含在交集中的状态数变为等于1，同时关于包含在交集中的每个输入符号的转移目的地状态的集合作为新的状态集合，并且多个 当状态数变为等于1时，通过跟踪与转换方向相反的方向将不可区分的状态合并成一个状态。