公开(公告)号：US20090043588A1

公开(公告)日：2009-02-12

申请号：US12187684

申请日：2008-08-07

申请人： Ryu Takeda ,  Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno

发明人： Ryu Takeda ,  Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno

IPC分类号： G10L21/00

CPC分类号： G10L21/0272

摘要： A system capable of reducing the influence of sound reverberation or reflection to improve sound-source separation accuracy. An original signal X(ω,f) is separated from an observed signal Y(ω,f) according to a first model and a second model to extract an unknown signal E(ω,f). According to the first model, the original signal X(ω,f) of the current frame f is represented as a combined signal of known signals S(ω,f−m+1) (m=1 to M) that span a certain number M of current and previous frames. This enables extraction of the unknown signal E(ω,f) without changing the window length while reducing the influence of reverberation or reflection of the known signal S(ω,f) on the observed signal Y(ω,f).

摘要翻译： 一种能够减少声音混响或反射影响以提高声源分离精度的系统。 根据第一模型和第二模型将原始信号X（ω，f）与观察信号Y（ω，f）分离以提取未知信号E（ω，f）。 根据第一模型，当前帧f的原始信号X（ω，f）被表示为已知信号S（ω，f-m + 1）（m = 1到M）的组合信号， 当前帧和前一帧的M个。 这可以在不改变窗口长度的情况下提取未知信号E（ω，f），同时减少已知信号S（ω，f）的混响或反射对观测信号Y（ω，f）的影响。

公开(公告)号：US08416957B2

公开(公告)日：2013-04-09

申请号：US12631434

申请日：2009-12-04

申请人： Hiroshi Tsujino ,  Kazuhiro Nakadai ,  Hiroshi Okuno ,  Takeshi Mizumoto ,  Ikkyu Aihara

发明人： Hiroshi Tsujino ,  Kazuhiro Nakadai ,  Hiroshi Okuno ,  Takeshi Mizumoto ,  Ikkyu Aihara

IPC分类号： H04R29/00

CPC分类号： G01S5/16

摘要： In a sound source localization system using a light emitting device for visualizing sound information, including: a light emitting device (40) including a microphone for receiving sound from a sound source (1, 2) and a light emitting means for emitting light based on the sound from the microphone; a generating section for generating light emitting information for the light emitting device (40); and a sound source localization section (60) for determining a position of the sound source based on the light emitting information from the generating section.

摘要翻译： 在使用发光装置进行可视化声音信息的声源定位系统中，包括：包括用于从声源（1,2）接收声音的麦克风的发光装置（40）和基于 来自麦克风的声音; 用于产生发光装置（40）的发光信息的发生部分; 以及声源定位部分（60），用于基于来自发生部分的发光信息确定声源的位置。

公开(公告)号：US07999168B2

公开(公告)日：2011-08-16

申请号：US12503448

申请日：2009-07-15

申请人： Kazuhiro Nakadai ,  Yuji Hasegawa ,  Hiroshi Tsujino ,  Kazumasa Murata ,  Ryu Takeda ,  Hiroshi Okuno

发明人： Kazuhiro Nakadai ,  Yuji Hasegawa ,  Hiroshi Tsujino ,  Kazumasa Murata ,  Ryu Takeda ,  Hiroshi Okuno

IPC分类号： G10H1/00

CPC分类号： G10H1/36 ,  A63H3/28 ,  G10H1/40 ,  G10H2240/135 ,  G10H2250/371 ,  G10H2250/455

摘要： A robot includes: a sound collecting unit collecting and converting a musical sound into a musical acoustic signal; a voice signal generating unit generating a self-vocalized voice signal; a sound outputting unit converting the self-vocalized voice signal into a sound and outputting the sound; a self-vocalized voice regulating unit receiving the musical acoustic signal and the self-vocalized voice signal; a filtering unit performing a filtering process; a beat interval reliability calculating unit performing a time-frequency pattern matching process and calculating a beat interval reliability; a beat interval estimating unit estimating a beat interval; a beat time reliability calculating unit calculating a beat time reliability; a beat time estimating unit estimating a beat time on the basis of the calculated beat time reliability; a beat time predicting unit predicting a beat time before the current time; and a synchronization unit synchronizing the self-vocalized voice signal.

摘要翻译： 机器人包括：收集单元，收集并将音乐声音转换成音乐声信号; 产生自发声音信号的语音信号产生单元; 声音输出单元，将自发声音信号转换成声音并输出声音; 接收音乐声音信号和自发声音信号的自发声音调节单元; 执行滤波处理的滤波单元; 节拍间隔可靠性计算单元，执行时间频率模式匹配处理并计算节拍间隔可靠性; 估计拍子间隔的拍子间隔估计单元; 节拍时间可靠性计算单元，计算节拍时间可靠性; 拍子时间估计单元，基于所计算的拍子时间可靠性来估计拍子时间; 拍子时间预测单元预测当前时间之前的拍子时间; 以及使自发声音信号同步的同步单元。

公开(公告)号：US20080167869A1

公开(公告)日：2008-07-10

申请号：US11792052

申请日：2005-12-02

申请人： Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno ,  Shunichi Yamamoto

发明人： Kazuhiro Nakadai ,  Hiroshi Tsujino ,  Hiroshi Okuno ,  Shunichi Yamamoto

IPC分类号： G10L15/20 ,  H04B3/00

CPC分类号： G10L15/20 ,  G10L21/028 ,  G10L2021/02166

摘要： A voice recognition system (10) for improving the toughness of voice recognition for a voice input for which a deteriorated feature amount cannot be completely identified. The system comprises at least two sound detecting means (16a, 16b) for detecting a sound signal, a sound source localizing unit (21) for determining the direction of a sound source based on the sound signal, a sound source separating unit (23) for separating a sound by the sound source from the sound signal based on the sound source direction, a mask producing unit (25) for producing a mask value according to the reliability of the separation results, a feature extracting unit (27) for extracting the feature amount of the sound signal, and a voice recognizing unit (29) for applying the mask to the feature amount to recognize a voice from the sound signal.

摘要翻译： 一种语音识别系统（10），用于提高不能完全识别恶化的特征量的语音输入的语音识别的韧性。 该系统包括用于检测声音信号的至少两个声音检测装置（16a，16b），用于基于声音信号确定声源的方向的声源定位单元（21），声源分离单元 23），用于根据声源方向将声音与声音信号分离，用于根据分离结果的可靠性产生掩模值的掩模产生单元（25），用于 提取声音信号的特征量;以及语音识别单元（29），用于将该掩码应用于特征量，以从声音信号识别语音。

公开(公告)号：US07215786B2

公开(公告)日：2007-05-08

申请号：US10296244

申请日：2001-06-08

申请人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

发明人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

IPC分类号： H04B15/00 ,  H04R1/02 ,  B25J5/00

CPC分类号： G10L21/0208 ,  G10L2021/02165

摘要： A robot auditory apparatus and system are disclosed which are made capable of attaining active perception upon collecting a sound from an external target with no influence received from noises generated interior of the robot such as those emitted from the robot driving elements. The apparatus and system are for a robot having a noise generating source in its interior, and include: a sound insulating cladding (14) with which at least a portion of the robot is covered; at least two outer microphones (16 and 16) disposed outside of the cladding (14) for collecting an external sound primarily; at least one inner microphone (17) disposed inside of the cladding (14) for primarily collecting noises from the noise generating source in the robot interior; a processing section (23, 24) responsive to signals from the outer and inner microphones (16 and 16; and 17) for canceling from respective sound signals from the outer microphones (16 and 16), noises signal from the interior noise generating source and then issuing a left and a right sound signal; and a directional information extracting section (27) responsive to the left and right sound signals from the processing section (23, 24) for determining the direction from which the external sound is emitted. The processing section (23, 24) is adapted to detect burst noises owing to the noise generating source from a signal from the at least one inner microphone (17) for removing signal portions from the sound signals for bands containing the burst noises.

摘要翻译： 公开了一种机器人听觉装置和系统，其能够在从机器人内部产生的噪声（例如从机器人驱动元件发射的噪声）中收到来自外部目标的声音而获得主动感知。 该装置和系统用于在其内部具有噪声发生源的机器人，并且包括：绝缘包层（14），至少一部分机器人被覆盖; 至少两个外部麦克风（16和16），其布置在所述包层（14）的外部，用于主要收集外部声音; 设置在所述包层（14）的内部的至少一个内部麦克风（17），用于主要从所述机器人内部的所述噪声发生源收集噪声; 响应于来自外部麦克风（16和16）和17的信号的来自外部麦克风（16和16）的相应声音信号的噪声信号的处理部分（23,24），来自内部噪声发生源的噪声信号;以及 然后发出左右声音信号; 以及响应于来自处理部分（23,24）的左和右声音信号的方向信息提取部分（27），用于确定从其发出外部声音的方向。 处理部分（23,24）适于从来自至少一个内部麦克风（17）的信号中检测由于噪声发生源引起的突发噪声，用于从包含脉冲串噪声的频带的声音信号中去除信号部分。

公开(公告)号：US20060241808A1

公开(公告)日：2006-10-26

申请号：US10506167

申请日：2002-08-30

申请人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

发明人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

IPC分类号： G06F19/00

CPC分类号： G06K9/0057 ,  B25J13/003

摘要： Robotics visual and auditory system is provided which is made capable of accurately conducting the sound source localization of a target by associating a visual and an auditory information with respect to a target. It is provided with an audition module (20), a face module (30), a stereo module (37), a motor control module (40), an association module (50) for generating streams by associating events from said each module (20, 30, 37, and 40), and an attention control module (57) for conducting attention control based on the streams generated by the association module (50), and said association module (50) generates an auditory stream (55) and a visual stream (56) from a auditory event (28) from the auditory module (20), a face event (39) from the face module (30), a stereo event (39a) from the stereo module (37), and a motor event (48) from the motor control module (40), and an association stream (57) which associates said streams, as well as said audition module (20) collects sub-bands having the interaural phase difference (IPD) or the interaural intensity difference (IID) within the preset range by an active direction pass filter (23a) having a pass range which, according to auditory characteristics, becomes minimum in the frontal direction, and larger as the angle becomes wider to the left and right, based on an accurate sound source directional information from the association module (50), and conducts sound source separation by restructuring the wave shape of the sound source.

摘要翻译： 提供了机器人视觉和听觉系统，其能够通过将视觉和听觉信息相对于目标相关联来准确地进行目标的声源定位。 它设置有试听模块（20），面部模块（30），立体声模块（37），电动机控制模块（40），通过将来自所述每个模块的事件相关联来生成流的关联模块（50） 20，30，37和40），以及用于基于由关联模块（50）生成的流进行注意控制的注意力控制模块（57），并且所述关联模块（50）生成听觉流（55）和 来自听觉模块（20）的听觉事件（28）的可视流（56），来自面部模块（30）的面部事件（39），来自立体声模块（37）的立体声事件（39a） 和来自马达控制模块（40）的马达事件（48）以及关联流（57），所述关联流（57）以及所述试奏模块（20）收集具有相位差（IPD）的子带或 通过具有通过的主动方向通过滤波器（23a）在预设范围内的昼间强度差（IID） 根据听觉特性，根据来自关联模块（50）的准确声源方向信息，根据听觉特性在前方方向上变得最小，并且随着角度变宽到更大，并且通过以下方式进行声源分离 重组声源的波形。

公开(公告)号：US07016505B1

公开(公告)日：2006-03-21

申请号：US10130295

申请日：2000-11-01

申请人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

发明人： Kazuhiro Nakadai ,  Hiroshi Okuno ,  Hiroaki Kitano

IPC分类号： A61F11/06 ,  G10K11/16 ,  H03B29/00

CPC分类号： B25J19/026 ,  G10L15/20 ,  G10L21/0216 ,  G10L2021/02165

摘要： The invention is directed to an auditory robot for a human or animal like robot, e.g., a human like robot (10) having a noise generating source such as a driving system in its interior. The apparatus includes a sound insulating cover (14) with which at least a head part (13) of the robot is covered; a pair of outer microphones (16; 16a and 16b) installed outside of the cover and located at a pair of positions where a pair of ears may be provided spaced apart for the robot, respectively, for collecting an external sound primarily; at least one inner microphone (17; 17a and 17b) installed inside of the cover for primarily collecting a noise from the noise generating source in the robot interior; and a processing module (18) on the basis of signals from the outer and inner microphones for removing from sound signals from the outer microphones (16a and 16b), a noise signal from the internal noise generating source. Thus, the robot auditory apparatus of the invention is made capable of effecting active perception by permitting an external sound from a target to be collected unaffected by a noise in the inside of the robot such as from the driving system.

摘要翻译： 本发明涉及用于人或动物如机器人的听觉机器人，例如具有诸如其内部的驱动系统的噪声产生源的人类似的机器人（10）。 所述装置包括隔音盖（14），所述机器人的至少头部（13）与所述绝缘罩（14）相覆盖; 一对外部麦克风（16; 16a和16b），其安装在所述盖子的外部并且分别位于一对位置处，所述一对耳朵可分别设置用于所述机器人，用于主要收集外部声音; 安装在所述盖内部的至少一个内部麦克风（17; 17a和17b），用于主要收集来自所述机器人内部的噪声发生源的噪声; 以及基于来自外麦克风和内麦克风的信号的处理模块（18），用于从外麦克风（16a和16b）的声音信号中去除来自内部噪声产生源的噪声信号。 因此，本发明的机器人听觉装置能够通过允许来自目标的外部声音被收集而不受来自诸如驱动系统的机器人内部的噪声的影响而影响主动感知。

公开(公告)号：US09002024B2

公开(公告)日：2015-04-07

申请号：US13036937

申请日：2011-02-28

申请人： Kazuhiro Nakadai ,  Ryu Takeda ,  Hiroshi Okuno

发明人： Kazuhiro Nakadai ,  Ryu Takeda ,  Hiroshi Okuno

IPC分类号： H04B3/20 ,  H04R3/04 ,  H04S7/00

CPC分类号： H04R3/04 ,  H04S7/305

摘要： A reverberation suppressing apparatus, includes: a sound acquiring unit which acquires a sound signal; a reverberation data computing unit which computes reverberation data from the acquired sound signal; a reverberation characteristics estimating unit which estimates reverberation characteristics based on the computed reverberation data; a filter length estimating unit which estimates a filter length of a filter which is used to suppress a reverberation based on the estimated reverberation characteristics; and a reverberation suppressing unit which suppresses the reverberation based on the estimated filter length.

摘要翻译： 一种混响抑制装置，包括：声音获取单元，其获取声音信号; 混响数据计算单元，其从所获取的声音信号计算混响数据; 混响特性估计单元，其基于所计算的混响数据来估计混响特性; 滤波器长度估计单元，其基于估计的混响特性来估计用于抑制混响的滤波器的滤波器长度; 以及基于估计的滤波器长度来抑制混响的混响抑制单元。

公开(公告)号：US08577678B2

公开(公告)日：2013-11-05

申请号：US13044737

申请日：2011-03-10

申请人： Kazuhiro Nakadai ,  Toru Takahashi ,  Hiroshi Okuno

发明人： Kazuhiro Nakadai ,  Toru Takahashi ,  Hiroshi Okuno

IPC分类号： G10L15/06 ,  G10L15/20 ,  G10L19/14 ,  G10L15/14 ,  G10L15/28 ,  G10L15/00

CPC分类号： G10L21/028 ,  G10L15/20 ,  G10L2021/02087 ,  G10L2021/02166

摘要： A speech recognition system according to the present invention includes a sound source separating section which separates mixed speeches from multiple sound sources from one another; a mask generating section which generates a soft mask which can take continuous values between 0 and 1 for each frequency spectral component of a separated speech signal using distributions of speech signal and noise against separation reliability of the separated speech signal; and a speech recognizing section which recognizes speeches separated by the sound source separating section using soft masks generated by the mask generating section.

摘要翻译： 根据本发明的语音识别系统包括：声源分离部，其将来自多个声源的混合语音彼此分离; 掩模生成部，其生成软掩模，该软掩模使用语音信号和噪声的分布对分离的语音信号的分离可靠性进行分离的语音信号的每个频谱分量的0和1之间的连续值; 以及语音识别部，其使用由所述掩模生成部生成的软掩模来识别由所述声源分离部分隔开的语音。

公开(公告)号：US08392185B2

公开(公告)日：2013-03-05

申请号：US12543759

申请日：2009-08-19

申请人： Kazuhiro Nakadai ,  Toru Takahashi ,  Hiroshi Okuno

发明人： Kazuhiro Nakadai ,  Toru Takahashi ,  Hiroshi Okuno

IPC分类号： G10L15/20 ,  G10L19/14 ,  G10L15/06 ,  G10L15/26 ,  G10L17/00 ,  G10L15/14 ,  G10L15/28 ,  G10L15/00

CPC分类号： G10L15/20 ,  G10L21/0272

摘要： The speech recognition system of the present invention includes: a sound source separating section which separates mixed speeches from multiple sound sources; a mask generating section which generates a soft mask which can take continuous values between 0 and 1 for each separated speech according to reliability of separation in separating operation of the sound source separating section; and a speech recognizing section which recognizes speeches separated by the sound source separating section using soft masks generated by the mask generating section.

摘要翻译： 本发明的语音识别系统包括：声源分离部分，用于将多个声源的混合语音分离; 掩模生成部，根据所述声源分离部的分离动作的分离的可靠性，生成能够对每个分离的语音取0〜1的连续值的软掩模; 以及语音识别部，其使用由所述掩模生成部生成的软掩模来识别由所述声源分离部分隔开的语音。