专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2014029407A Noise suppression device, method and program 有权
标题翻译：噪声抑制装置，方法和程序
公开(公告)号：JP2014029407A
公开(公告)日：2014-02-13
申请号：JP2012169893
申请日：2012-07-31
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： FUJIMOTO MASAKIYO , NAKATANI TOMOHIRO
IPC分类号： G10L21/0264 , G10L21/0232
摘要： PROBLEM TO BE SOLVED: To provide a noise suppression technology which suppresses an unsteady noise signal with respect to an input signal.SOLUTION: Input signal spectral information and sound feature quantity used for parameter estimation of a noise model are extracted from an input signal by using a soundless model and a voice model; a noise model parameter of a noise model and a speaker adaptation parameter dependent on a speaker are estimated by using the sound feature quantity, the soundless model and the voice model; a noise suppression filter is estimated by using the sound feature quantity, the soundless model, the voice model, the noise model parameter and the speaker adaptation parameter; and a target signal is output by applying the noise suppression filter to the spectral information. The noise model is expressed as a weighting mixed probability distribution, and a posterior probability used for the estimation of the noise model parameter and the speaker adaptation parameter is estimated by marginalizing the soundless model, the weighting mixed probability distribution of the input signal acquired by synthesizing the sound model and the noise model, and a posterior probability acquired from the input signal.
摘要翻译：要解决的问题：提供抑制相对于输入信号的不稳定噪声信号的噪声抑制技术。解决方案：通过使用输入信号从输入信号中提取用于噪声模型的参数估计的输入信号频谱信息和声音特征量无声模型和声音模型; 通过使用声音特征量，无声模型和语音模型来估计噪声模型的噪声模型参数和取决于扬声器的扬声器适配参数; 通过使用声音特征量，无声模型，语音模型，噪声模型参数和说话者自适应参数来估计噪声抑制滤波器; 并且通过将噪声抑制滤波器应用于频谱信息来输出目标信号。噪声模型表示为加权混合概率分布，用于估计噪声模型参数和说话者自适应参数的后验概率是通过对无声模型进行边缘化，通过合成获得的输入信号的加权混合概率分布来估计的声音模型和噪声模型，以及从输入信号获取的后验概率。

2. 发明专利

JP2013044908A Background sound suppressor, background sound suppression method and program 有权
标题翻译：声音抑制器，背景声音抑制方法和程序
公开(公告)号：JP2013044908A
公开(公告)日：2013-03-04
申请号：JP2011182277
申请日：2011-08-24
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NAKATANI TOMOHIRO , ARAKI AKIKO , YOSHIOKA TAKUYA , FUJIMOTO MASAKIYO , DELCROIX MARC
IPC分类号： G10L21/0232
摘要： PROBLEM TO BE SOLVED: To provide a more efficient and highly accurate background sound suppressor capable of reducing a calculation cost and utilizing a probability density function with a more complex form.SOLUTION: In a background sound suppressor 20 of the present invention, a feature quantity extraction unit 100 extracts a high resolution sound source position feature quantity and a high resolution spectral feature quantity from an observation signal, a sound source position occupation degree estimation unit 200 obtains a high resolution sound source position occupation degree, a frequency resolution reduction unit 300 reduces frequency resolution of the high resolution spectral feature quantity and the high resolution sound source position occupation degree, a low resolution occupation degree estimation unit 400 estimates a spectral parameter, a high resolution occupation degree re-estimation unit 510 estimates a high resolution occupation degree, and a target speech estimation unit 600 estimates a target speech.
摘要翻译：要解决的问题：提供能够降低计算成本并利用更复杂形式的概率密度函数的更有效和高度准确的背景声音抑制器。解决方案：在本发明的背景声音抑制器20中，特征量提取单元100从观测信号，声源位置占用度估计中提取高分辨率声源位置特征量和高分辨率光谱特征量单元200获得高分辨率声源位置占有度，频率分辨率降低单元300降低高分辨率频谱特征量和高分辨率声源位置占有度的频率分辨率，低分辨率占用度估计单元400估计频谱参数高分辨率占有度重新估计单元510估计高分辨率占用程度，并且目标语音估计单元600估计目标语音。版权所有（C）2013，JPO＆INPIT

3. 发明专利

JP2010054733A Device and method for estimating multiple signal section, its program, and recording medium 有权
标题翻译：用于估计多个信号部分，其程序和记录介质的装置和方法
公开(公告)号：JP2010054733A
公开(公告)日：2010-03-11
申请号：JP2008218677
申请日：2008-08-27
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ARAKI AKIKO , ISHIZUKA KENTARO , FUJIMOTO MASAKIYO , NAKATANI TOMOHIRO , MAKINO SHOJI
IPC分类号： G10L15/04 , G10L15/28 , G10L17/00
摘要： PROBLEM TO BE SOLVED: To give the same index for the same speaker even when the movement of a speaker position occurs during voice recording. SOLUTION: A frequency region conversion part 110 sequentially segments observation signals into frames of prescribed length to be converted into frequency regions for each frame. A voice section estimating part 120 estimates whether each frame corresponds to voice sections based on the observation signals of a frequency region. An incoming direction estimating part 130 estimates an incoming direction of the observation signals of the frequency region for each frame based on the observation signals of the frequency region. An incoming direction classifying part 140 classifies each frame estimated to correspond to the voice sections into clusters of each speaker based on similarity of the incoming direction. A speaker identifying part 250 creates models of speakers concerning the cluster for each cluster based on the observation signals of the frequency region of each frame classified into the same cluster up to a prescribed time point, and estimates the speakers of the observation signals on and after the prescribed time point based on the model of each speaker. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：即使当在录音期间发生扬声器位置的移动时，也为同一扬声器提供相同的索引。解决方案：频率区域转换部分110将观测信号顺序地分段成规定长度的帧，以转换成每帧的频率区域。语音部分估计部120基于频率区域的观测信号来估计每个帧是否对应于语音部分。进入方向估计部130基于频率区域的观测信号来估计每帧的频率区域的观测信号的输入方向。输入方向分类部分140基于输入方向的相似性，将估计的对应于语音部分的每个帧分类为每个说话者的聚类。扬声器识别部分250基于分类到同一簇的每帧的频率区域的观测信号直到规定的时间点，为每个簇创建关于簇的扬声器的模型，并且估计观测信号的扬声器的前后基于每个说话者的模型的规定时间点。版权所有（C）2010，JPO＆INPIT

4. 发明专利

JP2015036769A 雑音抑圧装置、雑音抑圧方法、およびプログラム有权
标题翻译：噪声抑制器，噪声抑制方法和程序
公开(公告)号：JP2015036769A
公开(公告)日：2015-02-23
申请号：JP2013168441
申请日：2013-08-14
申请人：日本電信電話株式会社 , Nippon Telegr & Teleph Corp
发明人： FUJIMOTO MASAKIYO , KUBO YOTARO , NAKATANI TOMOHIRO
IPC分类号： G10L15/20 , G10L21/0208 , G10L21/0232
摘要：【課題】雑音信号の統計的な性質に応じて雑音の確率モデルの構造を適応的に推定することにより、様々な統計的な性質をもつ雑音信号を効果的に抑圧する。【解決手段】雑音信号の確率モデルが1以上の要素分布から構成されるものとし、音声信号の確率モデルを用いて、入力信号に含まれる雑音信号を表す雑音信号の確率モデルの規定パラメータである雑音事前分布のパラメータを推定する。この雑音事前分布のパラメータを用いて、入力信号に含まれる雑音信号を表す雑音信号の確率モデルを構成する要素分布の個数と、当該雑音信号の確率モデルの各要素分布のパラメータと、を推定する。このように推定された要素分布の個数および要素分布パラメータを用いて構成される雑音信号の確率モデルと音声信号の確率モデルを用いて、入力信号に含まれる雑音信号を入力信号から取り除いた信号を出力信号として得る。【選択図】図1
摘要翻译：要解决的问题：通过根据噪声信号的统计特性自适应地估计噪声概率模型的结构来有效地抑制具有各种统计特征的噪声信号。解决方案：噪声的先前分布的参数，其是假设噪声信号的概率模型由一个或多个元素的分布构成，则使用声音信号的概率模型来估计指示包括在输入信号中的噪声信号的噪声信号的概率模型的规定参数。构成表示包含在输入信号中的噪声信号的噪声信号的概率模型的元素分布的数量以及噪声信号的概率模型的每个元素分布的参数被使用估计参数来估计，噪声。通过使用使用估计数量的元素分布和元素分布参数和概率模型配置的噪声信号的概率模型，获得从输入信号中去除输入信号中包括的噪声信号的信号作为输出信号的声音信号。

5. 发明专利

JP2012173592A Sound source parameter estimation device and sound source separation device and method thereof and program therefor 有权
标题翻译：声源参数估计装置和声源分离装置及其方法及其程序
公开(公告)号：JP2012173592A
公开(公告)日：2012-09-10
申请号：JP2011036713
申请日：2011-02-23
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NAKATANI TOMOHIRO , ARAKI AKIKO , YOSHIOKA TAKUYA , FUJIMOTO MASAKIYO
IPC分类号： G10L21/02 , G10L15/14 , H04R1/40 , H04R3/00
摘要： PROBLEM TO BE SOLVED: To provide a sound source parameter estimation device capable of estimating a sound source model parameter in conjunction with a sound source parameter even when no sound source model parameter is given in advance.SOLUTION: A sound source model parameter update section updates a sound source model parameter using a sound source power feature amount, a sound source power parameter, a sound source occupancy, a preliminary probability density function of the sound source power parameter stored in a sound source model storage section, and a model of the sound source power feature amount as inputs. A sound source occupancy update section updates a sound source occupancy for each sound source using a sound source position feature amount, the sound source power feature amount, the updated sound source power parameter for each sound source, a sound source position parameter, the sound source model parameter, the preliminary probability density function of the sound source power parameter stored in the sound source model storage section, and a model of the sound source power feature amount as inputs.
摘要翻译：要解决的问题：提供一种即使在没有提供声源模型参数的情况下也能够结合声源参数来估计声源模型参数的声源参数估计装置。解决方案：声源模型参数更新部分使用声源功率特征量，声源功率参数，声源占用，存储在其中的声源功率参数的初始概率密度函数来更新声源模型参数声源模型存储部分和声源功率特征量的模型作为输入。声源占有更新部分使用声源位置特征量，声源功率特征量，每个声源的更新声源功率参数，声源位置参数，声源来更新每个声源的声源占用模型参数，存储在声源模型存储部分中的声源功率参数的初始概率密度函数，以及声源功率特征量的模型作为输入。版权所有（C）2012，JPO＆INPIT

6. 发明专利

JP2009271183A Multiple signal sections estimation device and its method, and program and its recording medium 有权
标题翻译：多个信号部分估计装置及其方法及程序及其记录介质
公开(公告)号：JP2009271183A
公开(公告)日：2009-11-19
申请号：JP2008119717
申请日：2008-05-01
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： ARAKI AKIKO , ISHIZUKA KENTARO , FUJIMOTO MASAKIYO , MAKINO SHOJI
IPC分类号： G10L21/02 , G01S3/808 , G10L11/02
摘要： PROBLEM TO BE SOLVED: To securely detect a signal section even when multiple signal sources exist at the same time.
SOLUTION: The multiple signals section estimation device includes: a frequency region conversion section; a voice existence probability estimation section; a coming direction estimation section; a coming direction probability calculation section; and a multiplication section. The voice existence probability estimation section calculates a voice existence probability in each frame. The coming direction estimation section and the coming direction probability calculation section estimate a voice coming direction probability in all frequencies in each frame. Then, the multiplication section outputs a value in which the voice existence probability is multiplied by the voice coming direction probability at the multiplication section, as an utterance probability for all sound sources. Accordingly, as existence of multiple sound sources is allowed for each frame, section detection with little deficiency is achieved.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：即使当多个信号源同时存在时，也可以安全地检测信号部分。解决方案：多信号部分估计装置包括：频率区域转换部分; 语音存在概率估计部分; 即将到来的方向估计部分; 即将到达方向概率计算部分; 和乘法部分。语音存在概率估计部分计算每帧中的语音存在概率。前进方向估计部分和到来方向概率计算部分估计每个帧中所有频率中的语音到达方向概率。然后，乘法部在乘法部分输出语音存在概率乘以语音到达方向概率的值，作为所有声源的发声概率。因此，由于每个帧允许存在多个声源，所以实现了几乎没有的部分检测。版权所有（C）2010，JPO＆INPIT

7. 发明专利

JP2008058876A Method of deducing sound signal segment, and device and program and storage medium thereof 有权
标题翻译：降低声音信号分段的方法及其设备及程序及存储介质
公开(公告)号：JP2008058876A
公开(公告)日：2008-03-13
申请号：JP2006238707
申请日：2006-09-04
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： FUJIMOTO MASAKIYO , ISHIZUKA KENTARO , KATO HIROKO
IPC分类号： G10L15/04 , G10L11/00 , G10L11/02
摘要： PROBLEM TO BE SOLVED: To provide a high-accuracy method for deducing a sound signal segment that is applicable, other than the steady-state noise signal, by deducing the non-steady noise signal contained in input acoustic signal, and to provide its device.
SOLUTION: A sound feature is extracted for each frame, by segmenting input signal for each fixed segment by an acoustic signal analysis means. The distribution parameter of the sound feature extracted by the acoustic signal analysis means is generated by a parameter generation unit. The parameter of a clean sound memory unit 24, storing a clean sound probability model without noise, is added to the distribution parameter and processed by using a parallel non-linear Kalman filter and a parallel Kalman smoother, generates the probability model parameter for the noise signal by a noise model parameter estimation means 15. The probability ratio of sound/non-sound state probability is calculated for each frame, by processing a noise model parameter and an input signal by using a sound/non-sound state probability ratio calculation means 16, and the sound/non-sound state for each frame is determined.
COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：提供一种高精度方法，用于通过推导包含在输入声信号中的非稳定噪声信号来推导除了稳态噪声信号之外的适用的声音信号段，并且提供其设备。解决方案：通过声信号分析装置对每个固定段分割输入信号，为每帧提取声音特征。由声学信号分析装置提取的声音特征的分布参数由参数产生单元产生。将没有噪声的清洁声概率模型存储在清洁声音存储器单元24中的参数被添加到分布参数中并通过使用并行非线性卡尔曼滤波器和平行卡尔曼平滑器进行处理，生成噪声的概率模型参数通过噪声模型参数估计装置15来计算声音/非声音状态概率的概率比，通过使用声音/非声音状态概率比计算装置处理噪声模型参数和输入信号， 16，并且确定每帧的声/非声音状态。版权所有（C）2008，JPO＆INPIT

8. 发明专利

JP2013167698A Apparatus and method for estimating spectral shape feature quantity of signal for every sound source, and apparatus, method and program for estimating spectral feature quantity of target signal 有权
标题翻译：用于估计每个声源的光谱特征信号量的装置和方法，以及用于估计目标信号的光谱特征量的装置，方法和程序
公开(公告)号：JP2013167698A
公开(公告)日：2013-08-29
申请号：JP2012029791
申请日：2012-02-14
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NAKATANI TOMOHIRO , YOSHIOKA TAKUYA , ARAKI AKIKO , DELCROIX MARC , FUJIMOTO MASAKIYO
IPC分类号： G10L25/27 , G10L15/02 , G10L21/0308 , G10L25/24
摘要： PROBLEM TO BE SOLVED: To provide a technique for estimating a spectral shape feature quantity of a signal for every sound source, thereby efficiently performing a spectral estimation of a target sound, even using a model in which spectral values have correlation between frequencies.SOLUTION: A prior probability density function (a spectral shape model) of a spectral shape feature quantity corresponding to each sound source, and a conditioned probability density function (a spectral observation model) of the spectral feature quantity when the spectral shape feature quantity is given are used. An optimization function is represented by a product of the conditioned probability density function of the spectral shape feature quantity which has, in a latent variable, an occupancy sound source number representing a sound source of an acoustic signal having maximal energy in each time frequency point and to which the spectral shape feature quantities of all sound sources are given, and the prior probability density function of the spectral shape feature quantity determined for every sound source. The optimization function is maximized by using the spectral shape model and the spectral observation model, to estimate the spectral shape feature quantity for every sound and a sound source occupancy.
摘要翻译：要解决的问题：提供一种用于估计每个声源的信号的频谱形状特征量的技术，从而即使使用其中频谱值具有频率之间的相关性的模型，也可以有效地执行目标声音的频谱估计。解决方案：使用对应于每个声源的光谱形状特征量的先验概率密度函数（光谱形状模型）和当给出光谱形状特征量时的光谱特征量的调节概率密度函数（光谱观察模型）。优化函数由频谱形状特征量的条件概率密度函数的乘积表示，在潜变量中，具有表示每个时间频点具有最大能量的声信号的声源的占用声源数，以及给出了所有声源的光谱形状特征量的特征量，并且为每个声源确定了光谱形状特征量的先验概率密度函数。通过使用光谱形状模型和光谱观测模型，优化功能最大化，以估计每个声音和声源占用的光谱形状特征量。

9. 发明专利

JP2012042664A Sound source parameter estimating device, sound source separating device and their method, and program and memory medium 有权
标题翻译：声源参数估计装置，声源分离装置及其方法，程序和存储介质
公开(公告)号：JP2012042664A
公开(公告)日：2012-03-01
申请号：JP2010183130
申请日：2010-08-18
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： NAKATANI TOMOHIRO , ARAKI AKIKO , YOSHIOKA TAKUYA , FUJIMOTO MASAKIYO
IPC分类号： G10L21/02
摘要： PROBLEM TO BE SOLVED: To provide a sound source parameter estimating device for estimating a sound source parameter in consideration of both a sound source position feature amount of an observation signal and a sound source power feature amount.SOLUTION: A sound source model storage section stores a preliminary probability density function of a plurality of sound source power parameters, and a posterior probability density function at each time frequency point of each sound source signal in a case where the sound source power parameters are given. A sound source power parameter updating section uses as input a sound source occupancy degree, which is the posterior probability density function of an occupational sound source under the conditions that a sound source power feature amount and an observation signal are obtained, and updates the sound source power parameter of each sound source of a plurality of sound sources based on the preliminary probability density function of the sound source power parameter and the posterior probability density function of each sound source signal. A sound source position parameter updating section uses as input a sound source position feature amount and the sound source occupancy degree, and updates the sound source position parameter of each sound source. A sound source occupancy degree updating section updates the sound source occupancy degree of each sound source on the basis of the updated sound source power parameter and the updated sound source position parameter of each sound source.
摘要翻译：要解决的问题：提供一种考虑到观测信号的声源位置特征量和声源功率特征量两者来估计声源参数的声源参数估计装置。解决方案：声源模型存储部分在声源功率的情况下存储多个声源功率参数的初始概率密度函数和每个声源信号的每个时间频点处的后验概率密度函数给出参数。音源功率参数更新部件在获得声源功率特征量和观察信号的条件下，使用作为职业声源的后验概率密度函数的声源占有度作为输入，并且更新声源基于声源功率参数的初始概率密度函数和每个声源信号的后验概率密度函数，多个声源的每个声源的功率参数。声源位置参数更新部使用声源位置特征量和声源占有度作为输入，并且更新每个声源的声源位置参数。声源占有率更新部根据每个声源的更新声源功率参数和更新后的声源位置参数来更新各声源的声源占有度。版权所有（C）2012，JPO＆INPIT

10. 发明专利

JP2010191544A Apparatus, method, and program for processing video voice 有权
标题翻译：用于处理视频语音的装置，方法和程序
公开(公告)号：JP2010191544A
公开(公告)日：2010-09-02
申请号：JP2009033169
申请日：2009-02-16
申请人： Nippon Telegr & Teleph Corp , 日本電信電話株式会社
发明人： OTSUKA KAZUHIRO , MIKAMI DAN , YAMATO JUNJI , ISHIZUKA KENTARO , FUJIMOTO MASAKIYO , ARAKI AKIKO
IPC分类号： G06F3/048 , G06F3/14 , G06F3/16 , G06T19/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To automatically switch a point of view of a virtual space video in order to facilitate a viewer to understand a structure or the like of a conversation. SOLUTION: A video voice processing technology includes: estimating the position of a face, the posture, and the direction of eyes of a conversation participant by using a video obtained from an observation device; estimating the presence/absence and coming direction of an utterance by using a voice obtained from the observation device; calculating the degree of gaze as the degree of gaze of a virtual camera and the azimuthal angle of the virtual camera to the origin of a virtual space by using the position of a face, the direction of eyes, and the presence/absence and coming direction of an utterance, and calculating a control parameter for controlling the point of view of the virtual camera; and projecting a conversation participant image on a partial plane, arranging the partial plane on a horizontal plane on the virtual space so as to correspond to the arrangement of an actual conversation participant, and generating the virtual space video of the point of view of the virtual camera by using the control parameter. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：为了自动切换虚拟空间视频的观点，以便于观众了解对话的结构等。视频语音处理技术包括：通过使用从观察设备获得的视频来估计对话参与者的面部位置，姿势和眼睛的方向; 通过使用从观察装置获得的声音来估计发音的存在/不存在和到来的方向; 通过使用脸部的位置，眼睛的方向以及存在/不存在和未来的方向来计算目视的程度，作为虚拟照相机的凝视度和虚拟照相机的方位角与虚拟空间的原点并且计算用于控制虚拟摄像机的视点的控制参数; 并且将对话参与者图像投影在部分平面上，将所述部分平面布置在所述虚拟空间上的水平面上，以对应于实际对话参与者的布置，并且生成所述虚拟空间视点的虚拟空间视频相机使用控制参数。版权所有（C）2010，JPO＆INPIT

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式