公开(公告)号：US09398387B2

公开(公告)日：2016-07-19

申请号：US14075015

申请日：2013-11-08

Applicant: Sony Corporation

Inventor： Takashi Shibuya ,  Mototsugu Abe ,  Masayuki Nishiguchi

IPC: H04R29/00 ,  H04R3/04

CPC classification number: H04R29/00 ,  H04R3/04

Abstract: There is provided a sound processing device including an input signal processing unit configured to calculate a first acoustic feature quantity indicating a likelihood being of a sinusoidal wave of a signal in each time frequency domain and a second acoustic feature quantity different from the first acoustic feature quantity based on an input signal of content to be identified, a reference signal processing unit configured to calculate the first acoustic feature quantity and the second acoustic feature quantity based on a reference signal of content prepared in advance, and a matching processing unit configured to calculate a similarity between the input signal and the reference signal based on the first and second acoustic feature quantities of the input signal and the first and second acoustic feature quantities of the reference signal.

Abstract translation: 提供了一种声音处理装置，包括：输入信号处理单元，被配置为计算指示每个时间频域中的信号的正弦波的似然性的第一声音特征量;以及不同于第一声学特征量的第二声学特征量 基于要识别的内容的输入信号，基准信号处理单元，被配置为基于预先准备的内容的参考信号来计算第一声音特征量和第二声音特征量;以及匹配处理单元， 基于输入信号的第一和第二声学特征量以及参考信号的第一和第二声学特征量，输入信号和参考信号之间的相似度。

公开(公告)号：US10580428B2

公开(公告)日：2020-03-03

申请号：US15501124

申请日：2015-08-06

Applicant: SONY CORPORATION

Inventor： Keiichi Osako ,  Takashi Shibuya ,  Toshiyuki Sekiya ,  Mototsugu Abe

IPC: G10L21/00 ,  G10L21/0232 ,  G10L21/0264 ,  G10L25/84 ,  H04R1/40 ,  G10L21/0208 ,  H04R3/00 ,  H04M9/08 ,  G10L21/0216

Abstract: The present technology relates to an audio processing apparatus, an audio processing method, and a program which enable to appropriately eliminate a noise. An audio processing apparatus includes a sound collector which collects audio, an audio enhancer which enhances audio to be extracted using an audio signal collected by the sound collector, an audio attenuator which attenuates the audio to be extracted using the audio signal collected by the sound collector, a noise environment estimator which estimates a surrounding noise environment, and a post-filtering unit which performs post-filtering processing using an audio-enhanced signal from the audio enhancer and an audio-attenuated signal from the audio attenuator, in which the post-filtering unit sets strength of processing for noise elimination according to the noise environment by the noise environment estimator. The present technology can be applied to an apparatus which performs audio recognition processing, such as a mobile phone.

公开(公告)号：US09762193B2

公开(公告)日：2017-09-12

申请号：US13788488

申请日：2013-03-07

Applicant: Sony Corporation

Inventor： Ryuichi Namba ,  Mototsugu Abe ,  Akira Inoue ,  Keisuke Toyama ,  Shusuke Takahashi ,  Masayuki Nishiguchi

IPC: H03G1/00 ,  G11B27/034 ,  H04N5/77 ,  H04R3/00 ,  G10L21/0208 ,  H04N5/91 ,  H04N9/806

CPC classification number: H03G1/00 ,  G10L2021/02087 ,  G11B27/034 ,  H04N5/772 ,  H04N5/91 ,  H04N9/8063 ,  H04R3/005 ,  H04R2201/401 ,  H04R2430/20 ,  H04S2400/15

Abstract: A sound processing apparatus includes a sound determination portion operable to determine whether an input sound includes a first sound emitted from a particular source based on location information of the source, a sound separation portion operable to separate the input sound into the first sound and a second sound emitted from a source different from the particular source if the sound determination portion determines that the input sound includes the first sound, and a sound mixing portion operable to mix the first sound and the second sound separated by the sound separation portion at a prescribed volume ratio.

公开(公告)号：US20150043737A1

公开(公告)日：2015-02-12

申请号：US14385856

申请日：2013-04-16

Applicant: SONY CORPORATION

Inventor： Mototsugu Abe ,  Masayuki Nishiguchi ,  Yoshinori Kurata

IPC: G10L25/18 ,  G10L25/48 ,  G06F17/30

CPC classification number: G10L25/18 ,  G06F16/686 ,  G10L25/48

Abstract: There is provided a sound detecting apparatus including: a feature value extracting unit which extracts a feature value per every predetermined time from an input time signal; a feature value maintaining unit which maintains a feature value sequence of a predetermined number of detection target sound items; and a comparison unit which respectively compares a feature value sequence extracted by the feature value extracting unit with a feature value sequence of the maintained predetermined number of detecting target sound items and obtains detection results of the predetermined number of detection target sound items every time the feature value extracting unit newly extracts a feature value, wherein the feature value extracting unit includes a time frequency transform unit and a likelihood distribution detecting unit, smooths the obtained likelihood distribution in frequency and time directions, and extracts a feature value per the predetermined time.

Abstract translation: 提供一种声音检测装置，包括：特征值提取单元，其从输入的时间信号中提取每个预定时间的特征值; 特征值维持单元，其维持预定数量的检测目标声音项的特征值序列; 以及比较单元，其分别将由特征值提取单元提取的特征量序列与保持的预定数量的检测目标声音项的特征值序列进行比较，并且每次特征获得预定数量的检测目标声音项的检测结果 值提取单元新提取特征值，其中特征值提取单元包括时间频率变换单元和似然度分布检测单元，在频率和时间方向上平滑所获得的似然分布，并且提取每个预定时间的特征值。

公开(公告)号：US20140140519A1

公开(公告)日：2014-05-22

申请号：US14075015

申请日：2013-11-08

Applicant: Sony Corporation

Inventor： Takashi Shibuya ,  Mototsugu Abe ,  Masayuki Nishiguchi

IPC: H04R29/00

CPC classification number: H04R29/00 ,  H04R3/04

Abstract: There is provided a sound processing device including an input signal processing unit configured to calculate a first acoustic feature quantity indicating a likelihood being of a sinusoidal wave of a signal in each time frequency domain and a second acoustic feature quantity different from the first acoustic feature quantity based on an input signal of content to be identified, a reference signal processing unit configured to calculate the first acoustic feature quantity and the second acoustic feature quantity based on a reference signal of content prepared in advance, and a matching processing unit configured to calculate a similarity between the input signal and the reference signal based on the first and second acoustic feature quantities of the input signal and the first and second acoustic feature quantities of the reference signal.

Abstract translation: 提供了一种声音处理装置，包括：输入信号处理单元，被配置为计算指示每个时间频域中的信号的正弦波的似然性的第一声音特征量;以及不同于第一声学特征量的第二声学特征量 基于要识别的内容的输入信号，基于参考信号处理单元，被配置为基于预先准备的内容的参考信号来计算第一声音特征量和第二声音特征量，以及匹配处理单元， 基于输入信号的第一和第二声学特征量以及参考信号的第一和第二声学特征量，输入信号和参考信号之间的相似度。

公开(公告)号：US20130182857A1

公开(公告)日：2013-07-18

申请号：US13788488

申请日：2013-03-07

Applicant: Sony Corporation

Inventor： Ryuichi Namba ,  Mototsugu Abe ,  Akira Inoue ,  Keisuke Toyama ,  Shusuke Takahashi ,  Masayuki Nishiguchi

IPC: H03G1/00

CPC classification number: H03G1/00 ,  G10L2021/02087 ,  G11B27/034 ,  H04N5/772 ,  H04N5/91 ,  H04N9/8063 ,  H04R3/005 ,  H04R2201/401 ,  H04R2430/20 ,  H04S2400/15

Abstract: A sound processing apparatus includes a sound determination portion operable to determine whether an input sound includes a first sound emitted from a particular source based on location information of the source, a sound separation portion operable to separate the input sound into the first sound and a second sound emitted from a source different from the particular source if the sound determination portion determines that the input sound includes the first sound, and a sound mixing portion operable to mix the first sound and the second sound separated by the sound separation portion at a prescribed volume ratio.

Abstract translation: 一种声音处理装置，包括声音判定部，其可操作以基于源的位置信息来确定输入声音是否包括从特定源发射的第一声音，声音分离部分，其可操作以将输入声音分离成第一声音;以及第二声部 如果声音确定部分确定输入声音包括第一声音，声音混合部分可操作以将声音分离部分分离的第一声音和第二声音混合在规定音量 比。

公开(公告)号：US09674606B2

公开(公告)日：2017-06-06

申请号：US14057066

申请日：2013-10-18

Applicant: Sony Corporation

Inventor： Keiichi Osako ,  Mototsugu Abe

IPC: G10L21/02 ,  H04R3/00 ,  G10L21/0208 ,  G10L21/0232

CPC classification number: H04R3/00 ,  G10L21/0208 ,  G10L21/0232 ,  H04R2499/11

Abstract: There is provided a signal processing device including a feature amount extraction unit configured to extract, from a frequency-domain signal obtained by frequency conversion on a voice signal, a feature amount of the frequency-domain signal, and a determination unit configured to determine, based on the extracted feature amount, presence or absence of noise in the voice signal within a predetermined section. The feature amount is composed of a plurality of elements. The plurality of elements contain an element defined based on a correlation value between a feature amount waveform which is a waveform according to the frequency-domain signal in the voice signal within the predetermined section and a feature amount waveform within another section sequential in time to the predetermined section.

公开(公告)号：US20150046103A1

公开(公告)日：2015-02-12

申请号：US14385531

申请日：2013-02-18

Applicant: SONY CORPORATION

Inventor： Mototsugu Abe ,  Takashi Shibuya ,  Masayuki Nishiguchi

IPC: G01R21/06

CPC classification number: G01R21/06 ,  H02J3/00 ,  H02J2003/003

Abstract: Estimating operational states of a plurality of electrical devices connected to an electrical power line, that is, an electricity usage condition is appropriately carried out.Current and voltage are calculated as time-series from the electrical power line to which the plurality of electrical devices is connected. Signal components of power frequency and harmonics thereof are extracted from the time-series of the current and the voltage. Admittance vector time-series are calculated from the signal components. The admittance vector time-series are compared with combinations of feature vectors of the plurality of electrical devices connected to the electrical power line, to obtain an estimated result of the operational states of the plurality of electrical devices.

Abstract translation: 适当地执行与电力线连接的多个电气装置的运行状态的估计，即电力使用状况。 电流和电压以与多个电气设备连接的电力线的时间序列计算。 从电流和电压的时间序列中提取电力频率和谐波的信号分量。 导纳矢量时间序列由信号分量计算。 将导纳向量时间序列与连接到电力线的多个电气装置的特征向量的组合进行比较，以获得多个电气装置的运行状态的估计结果。

公开(公告)号：US20140303521A1

公开(公告)日：2014-10-09

申请号：US14355732

申请日：2012-10-05

Applicant: Sony Corporation

Inventor： Osamu Nakamura ,  Chika Myoga ,  Mototsugu Abe

IPC: A61B5/00 ,  A61B7/00 ,  A61B7/04

CPC classification number: A61B5/6833 ,  A61B7/003 ,  A61B7/04

Abstract: To easily perform replacement of a fixing member for fixing an object on a skin of a human body.An electronic device includes a biological signal acquisition device, a first sheet, and a second sheet. The biological signal acquisition device acquires a biological signal of the human body in a state of being fixed to the skin of the human body. The first sheet has one surface to be bonded to the biological signal acquisition device and another surface to be bonded to another sheet. Furthermore, a bonding strength per unit area between the other surface of the first sheet and the other sheet is larger than a bonding strength per unit area between the one surface of the first sheet and the biological signal acquisition device. The second sheet includes one surface to be bonded to the other surface of the first sheet and another surface to be bonded to the skin of the human body. Furthermore, the bonding strength per unit area between the one surface of the first sheet and the biological signal acquisition device is larger than a bonding strength per unit area between the other surface of the second sheet and the skin of the human body.

Abstract translation: 为了容易地更换用于将物体固定在人体皮肤上的固定部件。 电子装置包括生物信号采集装置，第一片和第二片。 生物信号采集装置以固定在人体皮肤上的状态获取人体的生物信号。 第一片具有要结合到生物信号采集装置的一个表面和待结合到另一片的另一表面。 此外，第一片材的另一面与另一片材之间的每单位面积的接合强度大于第一片材的一个表面和生物体信号获取装置之间的每单位面积的接合强度。 第二片包括要粘合到第一片的另一表面的一个表面和待结合到人体皮肤的另一表面。 此外，第一片的一个表面和生物信号获取装置之间的每单位面积的结合强度大于第二片的另一表面与人体的皮肤之间的每单位面积的结合强度。

公开(公告)号：US20130255473A1

公开(公告)日：2013-10-03

申请号：US13780179

申请日：2013-02-28

Applicant: SONY CORPORATION

Inventor： Mototsugu Abe ,  Masayuki Nishiguchi

IPC: G10H7/02

CPC classification number: G10H7/02 ,  G10H1/06 ,  G10H2210/031 ,  G10L25/18

Abstract: There is provided a tonal component detection method including performing a time-frequency transformation on an input time signal to obtain a time-frequency distribution, detecting a peak in a frequency direction at a time frame of the time-frequency distribution, fitting a tone model in a neighboring region of the detected peak, and obtaining a score indicating tonal component likeness of the detected peak based on a result obtained by the fitting.

Abstract translation: 提供了一种音调分量检测方法，包括对输入时间信号执行时频变换以获得时间频率分布，在时间频率分布的时间点检测频率方向上的峰值，拟合音调模型 在检测到的峰值的相邻区域中，并且基于通过拟合获得的结果获得表示检测到的峰值的音调分量相似度的分数。