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

JPWO2012086834A1 音声強調方法、装置、プログラム、記録媒体有权
标题翻译：语音增强的方法，装置，程序，记录介质
公开(公告)号：JPWO2012086834A1
公开(公告)日：2015-02-23
申请号：JP2012549909
申请日：2011-12-19
申请人：日本電信電話株式会社
发明人：健太丹羽 , 健太丹羽 , 阪内　澄宇 , 澄宇阪内 , 古家　賢一 , 賢一古家 , 羽田　陽一 , 陽一羽田
IPC分类号： H04R3/00 , G10L21/0208 , G10L21/0216 , G10L21/0232 , G10L21/0272 , H04R1/40
CPC分类号： H04R3/00 , G10L21/0232 , G10L2021/02082 , G10L2021/02166 , H04R3/005 , H04R2430/03
摘要：十分なSN比で収音し、任意の方向の音声に追従可能でもありながら、所望方向に対して従来よりも鋭い指向性を有し、マイクロホンアレーからの距離に応じて音声を強調可能な音声強調技術を提供する。音源位置として想定される一つまたは複数の位置方向に含まれる各位置(ただし、各位置を識別するための方向をi、距離をgとする)からの音声の各マイクロホンへの伝達特性ai,gを用いて、音声強調の対象となる位置について、フィルタを求める。各伝達特性ai,gは、方向iと距離gで定まる位置からの音声が直接届く直接音の伝達特性と当該音声が反射物で反射して届く一つ以上の反射音の各伝達特性との和で表される。M個のマイクロホンで音声を収音して得られるM個の収音信号がそれぞれ周波数領域に変換された周波数領域信号に、音声強調の対象となる位置に対応するフィルタを適用して出力信号を得る。
摘要翻译：它拾起足够的SN比，同时还必须遵循的声音的任何方向，具有尖锐的指向性比之前所期望的方向，突出根据来自麦克风阵列的距离可能语言声音提供增强技术。包括在一个或多个被假定作为声源位置的位置，方向的每个位置（但是，用于识别每个i，距离和g位置的方向）的传输特性的AI到每个麦克风的音频从，用克，受试者对语音增强的位置，获得滤波器。每个传输特性AI，g是从由方向确定的位置i和与转印特性的每个传输特性和一个或多个反射所述声音到达时由直接达到直接声音的反射所反射的距离g的声音它是由和表示。 M的M个频域信号收集通过拾取声音获得的声音信号被转换到频域，分别麦克风，通过施加对应于该位置是语音增强滤波器的输出信号得到。

2. 发明专利

JP5235722B2 Speech direction estimating apparatus, method, and program 有权
公开(公告)号：JP5235722B2
公开(公告)日：2013-07-10
申请号：JP2009048223
申请日：2009-03-02
申请人：日本電信電話株式会社
发明人：健太丹羽 , 澄宇阪内 , 賢一古家 , 陽一羽田
IPC分类号： H04R3/00 , G01S3/802 , G10L25/51 , H04R1/40
摘要： PROBLEM TO BE SOLVED: To provide a speech direction estimation device which does not request to arrange many microphones so as to enclose a speaker, and can appropriately estimate the speech direction even under environment in which a reverberation time is long. SOLUTION: The plurality of microphones pick up a sound signal originated by the speaker around a microphone array which is composed of the plurality of microphones. A correlation matrix which represents correlation between voice signals each picked up by each microphone, is created, and it is estimated that the speaker has spoken from what direction to the microphone array from an eigenvector obtained by decomposing the correlation matrix into an eigenvalue matrix and an eigenvector matrix. COPYRIGHT: (C)2010,JPO&INPIT

3. 发明专利

JP5097169B2 Telephone conference equipment and telephone conference system using the same 有权
标题翻译：空值
公开(公告)号：JP5097169B2
公开(公告)日：2012-12-12
申请号：JP2009140879
申请日：2009-06-12
申请人：日本電信電話株式会社
发明人：澄宇阪内 , 朗中川 , 健太丹羽 , 陽一羽田
IPC分类号： H04M1/00 , H04M1/02 , H04M3/56 , H04N7/15

4. 发明专利

JP4209348B2 Echo suppression method, carrying out the process equipment, program, and recording medium 有权
公开(公告)号：JP4209348B2
公开(公告)日：2009-01-14
申请号：JP2004062610
申请日：2004-03-05
申请人：日本電信電話株式会社
发明人：章俊片岡 , 陽一羽田 , 澄宇阪内
IPC分类号： G10L21/02 , H04R3/02 , G10L13/00 , H04B3/20
摘要： PROBLEM TO BE SOLVED: To provide a method, device and program for echo suppression that improve sender's speech quality by suppressing an echo, and a recording medium. SOLUTION: The echo suppressing device is equipped with a received signal frequency analysis part 401, a transmitted signal frequency analysis part 402, an echo component short-time spectrum estimation part 500 which estimates a short-time spectrum of an echo component from a received signal short-time spectrum and a transmitted signal short-time spectrum, an element echo suppression gain calculation part 601 which calculates an element echo suppression gain from the transmitted signal short-time spectrum and echo component short-time spectrum, an echo suppression gain smoothing part 602 which smoothes respective gain coefficients, an echo suppression gain superposition part 509 which superposes the smoothed echo suppression gain on the transmitted signal short-time spectrum to calculate a suppression processing signal short-time spectrum, and a time composition part 403 which reconverts the suppression processing short-time spectrum into a time area and outputs it. COPYRIGHT: (C)2005,JPO&NCIPI

5. 发明专利

JP3607625B2 Multi-channel echo suppression method, the equipment, the program and the recording medium 有权
公开(公告)号：JP3607625B2
公开(公告)日：2005-01-05
申请号：JP2001032422
申请日：2001-02-08
申请人：日本電信電話株式会社
发明人：和彦山森 , 雅史田中 , 陽一羽田 , 澄宇阪内
IPC分类号： H04R3/02 , G10L21/02 , H04B3/23
摘要： PROBLEM TO BE SOLVED: To calculate echo path connection quantity without detecting one side speaking state by a multi-channel system. SOLUTION: Echo propagation delay is detected from each correlation between a sound collection signal y(k) and reception signals x1(k) and x2(k) (3021 and 3022), and the x1(k) and x2(k) are respectively delayed, and the respective power rates of the y(k) to the delayed x1(k) and x2(k) are calculated in each short time (3041 and 3042), and the minimum value is updated so that each echo path connection quantity can be calculated. Then, they are respectively multiplied by the delayed x1(k) and x2(k) so that echo be1(k) and be2(k) can be estimated (3101, 3102), and echo reduction gains G1 and G2 are calculated by using the echo be1(k) and be2(k) and each echo connection quantity and the y(k) (3051 and 3052), and the y(k) is multiplied by the gains G1 and G2 so that echo suppression can be realized (2081 and 2082).

6. 发明专利

JP3583998B2 Multi-channel echo cancellation method, apparatus and program recording medium 有权
公开(公告)号：JP3583998B2
公开(公告)日：2004-11-04
申请号：JP2001033734
申请日：2001-02-09
申请人：日本電信電話株式会社
发明人：朗中川 , 雅史田中 , 陽一羽田 , 澄宇阪内
IPC分类号： H04M1/00 , H04B3/23 , H04M1/60

7. 发明专利

JP5582529B2 Sound source localization method, the sound source localization apparatus, and program 有权
标题翻译：空值
公开(公告)号：JP5582529B2
公开(公告)日：2014-09-03
申请号：JP2010137499
申请日：2010-06-16
申请人：日本電信電話株式会社 , 国立大学法人名古屋大学
发明人：健太丹羽 , 澄宇阪内 , 賢一古家 , 陽一羽田 , 基小笠原 , 隆典西野 , 一哉武田
IPC分类号： H04S5/02 , H04S1/00

8. 发明专利

JP5411807B2 How channel integration, channel integrated device, program 有权
公开(公告)号：JP5411807B2
公开(公告)日：2014-02-12
申请号：JP2010119853
申请日：2010-05-25
申请人：日本電信電話株式会社
发明人：哲小橋川 , 澄宇阪内 , 義和山口 , 浩和政瀧
IPC分类号： G10L15/00 , G10L15/04 , G10L15/28

9. 发明专利

JP5337189B2 Placement method for determining the reflective object in the filter design, equipment, program 有权
公开(公告)号：JP5337189B2
公开(公告)日：2013-11-06
申请号：JP2011084728
申请日：2011-04-06
申请人：日本電信電話株式会社
发明人：健太丹羽 , 澄宇阪内 , 賢一古家 , 陽一羽田
IPC分类号： G10L25/51 , G10L21/0272 , H04R1/40 , H04R3/00
摘要： PROBLEM TO BE SOLVED: To provide technology for determining the placement of a reflection object which reflects voices in designing a filter adopted for voice based information. SOLUTION: In cases where a filter adopted for voice based information is designed on the basis of a prescribed evaluation function by using a spatial correlation matrix expressed by transfer characteristics in plural directions in space, the transfer characteristics each are expressed by the sum of the transfer characteristic of a direct sound and each transfer characteristic of one reflection sound reflecting at a reflection object, and the evaluation function is such a function that the more a voice in at least a target direction is emphasized, the smaller the value it takes. A storage unit has stored therein candidates for the placement of the reflection object for a microphone array or a speaker array. A placement determination unit calculates the values of the evaluation function using a spatial correlation matrix expressed by transfer characteristics determined by the candidate, and determines a candidate for placement corresponding to the smallest of those values as the placement of the reflection object. COPYRIGHT: (C)2013,JPO&INPIT

10. 发明专利

JP5235725B2 Speech direction estimating apparatus, method, and program 有权
公开(公告)号：JP5235725B2
公开(公告)日：2013-07-10
申请号：JP2009048971
申请日：2009-03-03
申请人：日本電信電話株式会社
发明人：健太丹羽 , 澄宇阪内 , 賢一古家 , 陽一羽田
IPC分类号： H04R3/00 , G10L25/51 , H04R1/40
摘要： PROBLEM TO BE SOLVED: To provide a speech direction estimation device which does not request to arrange many microphones so as to enclose a speaker, and can appropriately estimate the speech direction even under environment in which a reverberation time is long. SOLUTION: A correlation matrix calculation unit sequentially generates and outputs an M×M correlation matrix representing correlation between digital sound signals as expected values by frames, and a base matrix generation unit inputs the digital sound signals and information on a speaker position, and generates a base matrix having a base number D. A correlation matrix decomposition unit inputs correlation matrixes and base matrixes by the frames and decomposes the correlation matrixes into component columns projected on the base matrixes, and a frequency averaging processing unit inputs the component columns and outputs a frequency averaged component column averaged with frequencies by the frames. A front-lateral direction decision unit inputs the frequency averaged component column, and estimates whether the speaker has spoken in the front direction by the frames. COPYRIGHT: (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