公开(公告)号：US20070223880A1

公开(公告)日：2007-09-27

申请号：US11713610

申请日：2007-03-05

申请人： Ryosuke Ohtsuki ,  Yuji Yamamoto City ,  Tatsuo Koga ,  Satoru Matsumoto

发明人： Ryosuke Ohtsuki ,  Yuji Yamamoto City ,  Tatsuo Koga ,  Satoru Matsumoto

IPC分类号： H04N7/00

CPC分类号： H04N9/8233 ,  G06F16/7834 ,  G11B27/034 ,  G11B27/105 ,  G11B27/28 ,  H04N9/8042 ,  H04N21/4325 ,  H04N21/4334 ,  H04N21/44008 ,  H04N21/8455 ,  H04N21/8456

摘要： A video playback apparatus informs a user of scene change. The video playback apparatus includes a feature extraction unit to extract feature scenes having audio/video content and a playback unit to replay feature scenes that have been extracted by the feature extraction unit. The playback unit further includes an identification information output unit that outputs information that identifies a feature scene being replayed.

摘要翻译： 视频播放装置向用户通知场景变化。 视频播放设备包括：特征提取单元，用于提取具有音频/视频内容的特征场景;以及播放单元，用于重播由特征提取单元提取的特征场景。 回放单元还包括识别信息输出单元，其输出识别被重放的特征场景的信息。

公开(公告)号：US20070212030A1

公开(公告)日：2007-09-13

申请号：US11710978

申请日：2007-02-27

申请人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

发明人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

IPC分类号： H04N7/00 ,  H04N5/91

CPC分类号： H04N5/76 ,  G11B27/105 ,  G11B27/28 ,  G11B27/329 ,  H04N5/781 ,  H04N21/4325 ,  H04N21/4394 ,  H04N21/458 ,  H04N21/812

摘要： A silent detector detects a silent segment based on output of an audio signal of contents. A determination unit determines a segment, in which the time length of each silent segment is essentially a multiplication of the predetermined time, as a first content segment regarding continuous plural silent segments that are detected in the silent detector, to determine a segment in which the time length of each silent segment is not essentially a multiplication of the predetermined time, as a second content segment, and to extract a silent segment between the first content segment and the second content segment as a changing segment. A playback controller sets a playback position of contents to the position before a predetermined time from the changing segment when a first action instruction is received.

摘要翻译： 无声检测器基于内容的音频信号的输出来检测静音段。 确定单元确定其中每个无声段的时间长度实质上是预定时间的乘法的段作为关于在无声检测器中检测到的连续多个静音段的第一内容段，以确定其中 每个静音段的时间长度本质上不是作为第二内容段的预定时间的乘法，并且将第一内容段和第二内容段之间的无声段提取为改变段。 当接收到第一动作指令时，播放控制器将内容的播放位置设置为与改变段之间的预定时间之前的位置。

公开(公告)号：US20070209055A1

公开(公告)日：2007-09-06

申请号：US11710979

申请日：2007-02-27

申请人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

发明人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

IPC分类号： H04N7/173

CPC分类号： H04N21/812 ,  H04N21/4394 ,  H04N21/44008

摘要： An aspect of the invention provides a commercial detection apparatus for detecting commercials that includes a silent detector configured to detect a silent segment based on the strength of the audio signal output in content, and a determination unit configured to determine a sound segment as a commercial if three or more silent segments are detected essentially within a set time span, and if the sound segment is found between two of the three silent segments.

摘要翻译： 本发明的一个方面提供了一种用于检测商业广告的商业检测装置，其包括：静音检测器，其被配置为基于内容中输出的音频信号的强度来检测静音段;以及确定单元，被配置为将声音段确定为商业的 基本上在设定的时间范围内检测三个或更多个无声段，并且如果在三个静音段中的两个之间找到声音段。

公开(公告)号：US20070071406A1

公开(公告)日：2007-03-29

申请号：US11527400

申请日：2006-09-27

申请人： Tatsuo Koga ,  Ryosuke Ohtsuki ,  Yuji Yamamoto ,  Makoto Yamanaka ,  Satoru Matsumoto

发明人： Tatsuo Koga ,  Ryosuke Ohtsuki ,  Yuji Yamamoto ,  Makoto Yamanaka ,  Satoru Matsumoto

IPC分类号： H04N7/00

CPC分类号： G11B27/034 ,  G06F16/739 ,  G06F16/7834 ,  G11B27/105 ,  G11B27/28

摘要： A video recording and reproducing apparatus includes: an audio signal decoder configured to acquire an audio signal from an inputted audio-video signal; a recording section configured to record the inputted audio-video signal; a peak time point detecting section configured to detect, as a peak time point, a time point having a power value, which satisfies a predetermined condition, selected from among power values in the acquired audio signal; a digest scene extracting section configured to select a predetermined number of peak time points from among the detected peak time points, and to extract, as a digest scene, each piece of the audio-video signal within a predetermined digest scene cutting time period set to each of the selected peak time points in advance; and a reproduction controlling section configured to reproduce the extracted digest scenes.

摘要翻译： 视频记录和再现装置包括：音频信号解码器，被配置为从输入的音频 - 视频信号获取音频信号; 记录部，被配置为记录输入的音频 - 视频信号; 峰值时间点检测部分，被配置为从获取的音频信号中的功率值中检测出具有满足预定条件的功率值的时间点作为峰值时间点; 摘要场景提取部，被配置为从检测到的峰值时间点中选择预定数量的峰值时间点，并且将预定摘要场景切换时间段内的每条音频 - 视频信号提取为摘要场景，设置为 每个选定的峰值时间点提前; 以及再现控制部分，被配置为再现所提取的摘要场景。

公开(公告)号：US08010363B2

公开(公告)日：2011-08-30

申请号：US11710979

申请日：2007-02-27

申请人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

发明人： Tatsuo Koga ,  Yuji Yamamoto ,  Ryosuke Ohtsuki ,  Satoru Matsumoto

IPC分类号： G10L11/00

CPC分类号： H04N21/812 ,  H04N21/4394 ,  H04N21/44008

摘要： An aspect of the invention provides a commercial detection apparatus for detecting commercials that includes a silent detector configured to detect a silent segment based on the strength of the audio signal output in content, and a determination unit configured to determine a sound segment as a commercial if three or more silent segments are detected essentially within a set time span, and if the sound segment is found between two of the three silent segments.

摘要翻译： 本发明的一个方面提供了一种用于检测商业广告的商业检测装置，其包括：静音检测器，其被配置为基于内容中输出的音频信号的强度来检测静音段;以及确定单元，被配置为将声音段确定为商业的 基本上在设定的时间范围内检测三个或更多个无声段，并且如果在三个静音段中的两个之间找到声音段。

公开(公告)号：US07985915B2

公开(公告)日：2011-07-26

申请号：US12029643

申请日：2008-02-12

申请人： Satoru Matsumoto ,  Yuji Yamamoto ,  Tatsuo Koga ,  Ryosuke Ohtsuki

发明人： Satoru Matsumoto ,  Yuji Yamamoto ,  Tatsuo Koga ,  Ryosuke Ohtsuki

IPC分类号： G10H1/00

CPC分类号： G10H1/0058 ,  G10H2240/141 ,  G10H2240/325 ,  G11B27/034 ,  G11B27/28 ,  G11B2220/2516

摘要： Characteristic amounts are calculated from each of multiple musical piece contents, and then time points when the characteristic amounts exceed a threshold are detected as cut points. Information on the cut point concerning each of the multiple musical piece contents is stored. Based on the stored information on the cut point, a judgment is made as to whether the multiple musical piece contents match each other.

摘要翻译： 从多个乐曲内容中的每一个计算特征量，然后将特征量超过阈值的时间点作为切点检测。 存储关于多个乐曲内容中的每一个的切割点的信息。 基于存储在切点上的信息，判断多个乐曲内容是否彼此匹配。

公开(公告)号：US20120051550A1

公开(公告)日：2012-03-01

申请号：US13265797

申请日：2010-03-04

申请人： Tatsuo Koga ,  Yuji Yamamoto ,  Satoru Matsumoto ,  Hisatoshi Oomae

发明人： Tatsuo Koga ,  Yuji Yamamoto ,  Satoru Matsumoto ,  Hisatoshi Oomae

IPC分类号： H04R29/00 ,  H04R3/00

CPC分类号： G10L25/87 ,  G10L2025/783 ,  G11B27/22 ,  G11B27/28

摘要： Provided is a sound recording/playback device (1) that records onto a recording medium (5) sound data captured by a microphone (6), pulls the sound data from the recording medium (5), and plays said sound data. The sound recording/playback device is provided with a discrimination means (21, 22, 23, 24) which discriminates between human sound and non-sound audio. Upon recording, the device records the start position and end position of human sound, as determined by the discrimination means (21, 22, 23, 24), and upon playback, the data between the afore-mentioned start position and the subsequent end position is extracted and outputted.

摘要翻译： 提供了一种记录在记录介质（5）上的由麦克风（6）捕获的声音数据的录音/回放设备（1），从记录介质（5）拉出声音数据，并播放所述声音数据。 录音/回放装置设有鉴别人声和非声音音频的鉴别装置（21,22,23,24）。 在记录时，设备记录由判别装置（21,22,23,24）确定的人声的开始位置和结束位置，并且在回放时，上述起始位置与后续终点位置之间的数据 被提取并输出。

公开(公告)号：US07745714B2

公开(公告)日：2010-06-29

申请号：US12053647

申请日：2008-03-24

申请人： Satoru Matsumoto ,  Yuji Yamamoto ,  Tatsuo Koga

发明人： Satoru Matsumoto ,  Yuji Yamamoto ,  Tatsuo Koga

IPC分类号： G10H1/00

CPC分类号： G10H1/0008 ,  G10H2210/046 ,  G10H2210/066 ,  G10H2240/061

摘要： Provided is a recording or playback apparatus capable of separating a musical piece from an audio including the musical piece and a speech through a simple arithmetic process. A cut point detector detects, as a cut point, a time point at which an audio signal level or an amount of change in the audio signal level is not lower than a predetermined value. A frequency characteristic amount calculator calculates a characteristic amount in a frequency area of the audio signal only at each cut point and in its proximity. A cut point judging unit judges an attribute of the cut point on a basis of the calculated characteristic amount of the frequency. A music section detector detects a start and end points of each music section on a basis of the attribute and an interval between sampling points.

摘要翻译： 提供了一种能够通过简单的算术处理将音乐作品与包括音乐作品的音频和语音分离的记录或重放装置。 切点检测器检测音频信号电平或音频信号电平的变化量不低于预定值的时间点作为切点。 频率特征量计算器仅在每个切割点和其接近处计算音频信号的频率区域中的特征量。 切点判定部基于计算出的频率特征量来判断切断点的属性。 音乐部分检测器基于属性和采样点之间的间隔检测每个音乐部分的开始和结束点。

公开(公告)号：US20080050093A1

公开(公告)日：2008-02-28

申请号：US11892350

申请日：2007-08-22

申请人： Tatsuo Koga ,  Yuji Yamamoto

发明人： Tatsuo Koga ,  Yuji Yamamoto

IPC分类号： H04N5/91

CPC分类号： H04N5/782 ,  G11B27/322 ,  H04N5/775 ,  H04N9/8205 ,  H04N21/4147 ,  H04N21/4325 ,  H04N21/4331 ,  H04N21/4334 ,  H04N21/4622 ,  H04N21/47214 ,  H04N21/478 ,  H04N21/6547 ,  H04N21/6581 ,  H04N21/8455

摘要： When a video signal and an audio signal obtained through decoding by a decoder 14 are outputted for the playback of a broadcast program, a scene identification code generator 20 generates and outputs a scene identification code by which to identify the scene currently being played back.

摘要翻译： 输出通过解码器14的解码获得的视频信号和音频信号用于播放广播节目时，场景识别码发生器20产生并输出用于识别当前正在播放的场景的场景识别码。

公开(公告)号：US20120060614A1

公开(公告)日：2012-03-15

申请号：US13228507

申请日：2011-09-09

申请人： Masahiro YOSHIDA ,  Tomoki Oku ,  Tatsuo Koga ,  Kazuma Hara ,  Hisatoshi Oomae ,  Hideto Shimaoka

发明人： Masahiro YOSHIDA ,  Tomoki Oku ,  Tatsuo Koga ,  Kazuma Hara ,  Hisatoshi Oomae ,  Hideto Shimaoka

IPC分类号： G01N29/00

CPC分类号： H04N5/772

摘要： An image sensing device according to the present invention includes: an optical portion that is driven to form an optical image in any state; a sensor portion that acquires, as an image signal, the optical image formed by the optical portion; a sound collection portion that acquires an acoustic signal by collecting sound; an image sensing environment determination portion that determines an image sensing environment which is an environment under which the sensor portion acquires the image signal; and an operation determination portion that determines, based on the image sensing environment determined by the image sensing environment determination portion, at least one of a drive speed of the optical portion and a method of processing the acoustic signal acquired by the sound collection portion when the optical portion is driven.

摘要翻译： 根据本发明的图像感测装置包括：被驱动以形成任何状态的光学图像的光学部分; 获取由所述光学部分形成的光学图像作为图像信号的传感器部分; 声音收集部分，通过收集声音来获取声学信号; 图像感测环境确定部分，其确定作为所述传感器部分获取所述图像信号的环境的图像感测环境; 以及操作确定部分，其基于由所述图像感测环境确定部分确定的图像感测环境，确定所述光学部分的驱动速度和处理由所述声音收集部分获取的所述声学信号的方法中的至少一个， 光学部分被驱动。