公开(公告)号：US08111838B2

公开(公告)日：2012-02-07

申请号：US12037426

申请日：2008-02-26

申请人： Toshimichi Tokuda ,  Natsushi Ono ,  Ryoichi Yuge

发明人： Toshimichi Tokuda ,  Natsushi Ono ,  Ryoichi Yuge

IPC分类号： H04R3/00

CPC分类号： H04M1/6033 ,  H04M1/2535

摘要： A voice conference apparatus includes a sound collecting unit and a loudspeaker, while the sound collecting unit has a directional polar sensitivity characteristic which has a higher sensitivity with respect to sounds which are radiated from at least one direction, as compared with sounds radiated from other directions. The sound collecting unit of the voice conference apparatus has a plurality of omnidirectional microphones, and forms a desirable sensitivity characteristic. Since the omnidirectional microphones are employed, aging changes and fluctuations contained in the sensitivity characteristics of the respective sound collecting units can be reduced, so that the sensitivity characteristics thereof can become stable, and thus, full duplex communications with higher qualities can be carried out.

摘要翻译： 语音会议装置包括声音收集单元和扬声器，而声音采集单元具有相对于从其它方向辐射的声音相对于从至少一个方向辐射的声音具有较高灵敏度的方向极性灵敏度特性 。 语音会议装置的声音采集单元具有多个全向麦克风，并形成期望的灵敏度特性。 由于采用了全向麦克风，所以可以减少各个收集单元的灵敏度特性中包含的老化变化和波动，使其灵敏度特性变得稳定，从而可以进行更高质量的全双工通信。

公开(公告)号：US08054991B2

公开(公告)日：2011-11-08

申请号：US12424842

申请日：2009-04-16

申请人： Toshimichi Tokuda ,  Ryota Fujii

发明人： Toshimichi Tokuda ,  Ryota Fujii

IPC分类号： H04R3/00

CPC分类号： H04R29/005 ,  H04M1/6033 ,  H04R3/005

摘要： A sound pickup apparatus includes a plurality of microphones, and a controller that receives signals from the plurality of microphones. When the controller detects a failure in one of the plurality of microphones based on the signals received from the plurality of microphones, the controller restricts a signal from at least one remaining non-failure microphone.

摘要翻译： 一种拾音装置，包括多个麦克风，以及控制器，其接收来自多个麦克风的信号。 当控制器基于从多个麦克风接收到的信号来检测多个麦克风之一中的故障时，控制器限制来自至少一个剩余的非故障麦克风的信号。

公开(公告)号：US07228271B2

公开(公告)日：2007-06-05

申请号：US10325959

申请日：2002-12-23

申请人： Toshimichi Tokuda ,  Takashi Kimura

发明人： Toshimichi Tokuda ,  Takashi Kimura

IPC分类号： G10L11/06

CPC分类号： H04M1/2475 ,  H04M1/60

摘要： The telephone apparatus of the present invention comprises a first voice band expander for generating a voiced signal frequency component by shifting the frequency of the voice signal received, a second voice band expander for generating a voiceless signal frequency component by shifting the frequency of the voice signal received, and a voice composer for composing the voice signal received, the output of the first voice band expander, and the output of the second voice band expander, which is able to output clear voices in aural communication.

摘要翻译： 本发明的电话装置包括：第一语音频带扩展器，用于通过移位接收到的语音信号的频率来生成语音信号频率分量;第二语音频带扩展器，用于通过移动语音信号的频率来产生无声信号频率分量 以及用于构成所接收的语音信号，第一语音频带扩展器的输出和能够在听觉通信中输出清晰语音的第二语音频带扩展器的输出的语音编辑器。

公开(公告)号：US20090268899A1

公开(公告)日：2009-10-29

申请号：US12424842

申请日：2009-04-16

申请人： Toshimichi Tokuda ,  Ryota Fujii

发明人： Toshimichi Tokuda ,  Ryota Fujii

IPC分类号： H04M1/00 ,  H04R3/00

CPC分类号： H04R29/005 ,  H04M1/6033 ,  H04R3/005

摘要： A sound pickup apparatus includes a plurality of microphones, and a controller that receives signals from the plurality of microphones respectively. When the controller detects a failure in one of the plurality of microphones based on the signals received from the plurality of microphones, the controller restricts a signal from at least one remain non-failure microphone.

摘要翻译： 一种拾音装置，包括多个麦克风，以及分别从多个麦克风接收信号的控制器。 当控制器基于从多个麦克风接收到的信号来检测多个麦克风中的一个麦克风的故障时，控制器限制来自至少一个保持的非故障麦克风的信号。

公开(公告)号：US20110200205A1

公开(公告)日：2011-08-18

申请号：US12707319

申请日：2010-02-17

申请人： Toshimichi Tokuda

发明人： Toshimichi Tokuda

IPC分类号： H04R3/00 ,  G10L19/02 ,  H04N5/76

CPC分类号： G10L21/0208 ,  G10L15/20 ,  G10L2021/02166

摘要： A sound pickup apparatus includes: a microphone array including at least three microphones, wherein a first pair of microphones in which two of the at least three microphones are aligned on a first axis, and a second pair of microphones in which two of the at least three microphones are aligned on a second axis; a first null signal generator which outputs a first null signal based on a differential output of the first pair of microphones; a second null signal generator which outputs a second null signal based on a differential output of the second pair of microphones; and a combiner which generates a target signal based on the first null signal and the second null signal, the target signal having a directional characteristic in which the lowest sensitivity is formed in a direction to a line along which the first null surface meets the second null surface.

摘要翻译： 拾音装置包括：麦克风阵列，包括至少三个麦克风，其中第一对麦克风中的至少三个麦克风中的两个在第一轴上对准，第二对麦克风至少包括两个麦克风 三个麦克风在第二轴上对齐; 第一空信号发生器，其基于所述第一对麦克风的差分输出输出第一空信号; 第二空信号发生器，其基于所述第二对麦克风的差分输出输出第二空信号; 以及组合器，其基于所述第一空信号和所述第二空信号产生目标信号，所述目标信号具有方向特性，其中所述最低灵敏度在与所述第一零面相符的第二零面的线的方向上形成 表面。

公开(公告)号：US07856097B2

公开(公告)日：2010-12-21

申请号：US11153902

申请日：2005-06-16

申请人： Toshimichi Tokuda

发明人： Toshimichi Tokuda

IPC分类号： H04M9/08

CPC分类号： H04B3/23 ,  H04B3/234

摘要： Providing echo canceling apparatus, telephone set using the same and an echo canceling method that do not require transmission/reception sound detection and are resistant to environmental noise.Echo canceling apparatus according to the invention includes a calculator 4 for subtracting a pseudo-echo signal pec generated from a reception sound signal from an echo signal ec that is based on an echo generated when the reception sound that is based on the reception sound signal is reflected on a reflective body such as a wall thereby outputting a residual echo signal rec. The echo canceling apparatus further includes a residual echo detector 12 for estimating a residual echo volume by detecting sign inversion of the echo signal ec and the residual echo signal rec and their amplitude values. It is thus possible to compare between the positive and negative signs of the input/output signal of the calculator 4 without using the transmission/reception sound detection to detect the generation of a pseudo-echo signal thereby accurately estimating the residual echo volume.

摘要翻译： 提供回波消除装置，使用其的电话机和不需要发送/接收声音检测并且抵抗环境噪声的回波消除方法。 根据本发明的回波消除装置包括：计算器4，用于从基于基于接收声音信号的接收声音产生的回波的回波信号ec减去从接收声音信号产生的伪回波信号pec 反射在诸如墙壁的反射体上，从而输出残余回波信号rec。 回波消除装置还包括残留回波检测器12，用于通过检测回波信号ec和残留回波信号rec及其振幅值的符号反转来估计残留回波体积。 因此，可以不使用发送/接收声音检测来检测计算机4的输入/输出信号的正负符号，从而可以准确地估计残余回波体积来比较伪回波信号的产生。

公开(公告)号：US20050286714A1

公开(公告)日：2005-12-29

申请号：US11153902

申请日：2005-06-16

申请人： Toshimichi Tokuda

发明人： Toshimichi Tokuda

IPC分类号： H04B3/23 ,  H04M9/08

CPC分类号： H04B3/23 ,  H04B3/234

摘要： Providing echo canceling apparatus, telephone set using the same and an echo canceling method that do not require transmission/reception sound detection and are resistant to environmental noise. Echo canceling apparatus according to the invention includes a calculator 4 for subtracting a pseudo-echo signal pec generated from a reception sound signal from an echo signal ec that is based on an echo generated when the reception sound that is based on the reception sound signal is reflected on a reflective body such as a wall thereby outputting a residual echo signal rec. The echo canceling apparatus further includes a residual echo detector 12 for estimating a residual echo volume by detecting sign inversion of the echo signal ec and the residual echo signal rec and their amplitude values. It is thus possible to compare between the positive and negative signs of the input/output signal of the calculator 4 without using the transmission/reception sound detection to detect the generation of a pseudo-echo signal thereby accurately estimating the residual echo volume.

摘要翻译： 提供回波消除装置，使用其的电话机和不需要发送/接收声音检测并且抵抗环境噪声的回波消除方法。 根据本发明的回波消除装置包括：计算器4，用于从基于基于接收声音信号的接收声音产生的回波的回波信号ec减去从接收声音信号产生的伪回波信号pec 反射在诸如墙壁的反射体上，从而输出残余回波信号rec。 回波消除装置还包括残留回波检测器12，用于通过检测回波信号ec和残留回波信号rec及其振幅值的符号反转来估计残留回波体积。 因此，可以不使用发送/接收声音检测来检测计算机4的输入/输出信号的正负符号，从而可以准确地估计残余回波体积来比较伪回波信号的产生。

公开(公告)号：US5860062A

公开(公告)日：1999-01-12

申请号：US874331

申请日：1997-06-13

申请人： Kenichi Taniguchi ,  Nobuyuki Kono ,  Toshimichi Tokuda ,  Yoshio Ikura

发明人： Kenichi Taniguchi ,  Nobuyuki Kono ,  Toshimichi Tokuda ,  Yoshio Ikura

IPC分类号： G10L15/14 ,  G10L15/20 ,  G01L5/06

CPC分类号： G10L15/142 ,  G10L15/20

摘要： A speech recognition apparatus and method learns in advance a plurality of kinds of noises that can occur in the environment of use to determine a plurality of noise HMMs, synthesizes these noise HMMs into one noise HMM, generates a NOVO-HMM by executing NOVO (voice mixed with noise) conversion for a speech HMM of a reference pattern by using this composite noise HMM, and uses this NOVO-HMM for a speech recognition processing. Since a plurality of noises are incorporated in the NOVO-HMM generated in this manner, the speech can be recognized with high accuracy even when the noise changes.

摘要翻译： 语音识别装置和方法预先学习可以在确定多个噪声HMM的使用环境中发生的多种噪声，将这些噪声HMM合成为一个噪声HMM，通过执行NOVO（语音）产生NOVO-HMM 通过使用该复合噪声HMM对参考图案的语音HMM进行转换，并使用该NOVO-HMM进行语音识别处理。 由于多个噪声被包含在以这种方式产生的NOVO-HMM中，所以即使在噪声变化时也可以高精度地识别语音。