公开(公告)号：US20200090029A1

公开(公告)日：2020-03-19

申请号：US16334425

申请日：2017-09-22

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： RYOJI SUZUKI

IPC: G06N3/063 ,  G10L25/18 ,  G10L25/30 ,  G06N3/04 ,  G06N3/08

Abstract: An audio signal processing device includes a neural network circuit that includes an input layer including input units, an intermediate layer, and an output layer including output units, an input section that executes simultaneous inputting of, at each of unit time intervals, each of pieces of unit data of consecutive sampling units in an input signal data string generated through sampling based on an audio signal string into each of the input units on a one-to-one basis, one of the pieces of unit data input into one of the input units at one of the unit time intervals being input into another of the input units at another of the unit time intervals in the simultaneous inputting at each of the unit time intervals, and an output section that outputs, in accordance with the simultaneous inputting over a plurality of the unit time intervals that are consecutive, a computation result at each of the unit time intervals, the computation result being based on pieces of data output from the output units at each of the unit time intervals.

公开(公告)号：US20180115650A1

公开(公告)日：2018-04-26

申请号：US15737465

申请日：2016-09-29

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： RYOJI SUZUKI ,  HIROMASA OHASHI ,  NAOYA TANAKA

IPC: H04M9/08 ,  H04M3/00 ,  H04M3/40

CPC classification number: H04M9/082 ,  G10L21/0208 ,  G10L2021/02082 ,  G10L2021/02087 ,  H04M3/002 ,  H04M3/40 ,  H04M9/085 ,  H04R3/02 ,  H04R27/00 ,  H04R2499/13

Abstract: A two-way conversation assisting device includes a first microphone that enters a first voice, a first loudspeaker that outputs the first voice, a second microphone that enters a second voice, a second loudspeaker that outputs the second voice, and a first echo and crosstalk canceller. The first echo and crosstalk canceller estimates and calculates, using an input signal into the second loudspeaker, a first interference signal indicative of degrees of a first echo caused when the second voice output from the second loudspeaker enters into the first microphone and first crosstalk caused when the second voice enters into the first microphone, and removes the calculated first interference signal from an output signal of the first microphone.

公开(公告)号：US20180158467A1

公开(公告)日：2018-06-07

申请号：US15889279

申请日：2018-02-06

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： RYOJI SUZUKI ,  HIROMASA OHASHI ,  NAOYA TANAKA

IPC: G10L21/028 ,  H04R3/02 ,  H04R3/14

CPC classification number: G10L21/028 ,  G10L21/0272 ,  H04R3/00 ,  H04R3/02 ,  H04R3/14 ,  H04R2499/13

Abstract: A sound source separation device includes a first microphone that picks up a first voice, a second microphone that picks up a second voice, a first crosstalk canceller that removes, from a voice signal of the first microphone, first crosstalk caused when the second voice is picked up by the first microphone, and a second crosstalk canceller that removes, from a voice signal of the second microphone, second crosstalk caused when the first voice is picked up by the second microphone. The first crosstalk canceller uses a voice signal in which the second crosstalk is removed from the voice signal of the second microphone to estimate and calculate a first interference signal indicative of a degree of the first crosstalk, and to remove the calculated first interference signal from the voice signal of the first microphone. The second crosstalk canceller uses a voice signal in which the first crosstalk is removed from the voice signal of the first microphone to estimate and calculate a second interference signal indicative of a degree of the second crosstalk, and to remove the calculated second interference signal from the voice signal of the second microphone.

公开(公告)号：US20160163334A1

公开(公告)日：2016-06-09

申请号：US14907243

申请日：2014-10-28

Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.

Inventor： RYOJI SUZUKI ,  TOHRU USUKURA

IPC: G10L25/87 ,  G10L21/0388 ,  G10L19/26 ,  G10L21/034

CPC classification number: G10L25/87 ,  G10L19/265 ,  G10L21/034 ,  G10L21/0388 ,  G10L25/93

Abstract: Up-sampler generates an up-sampled sound signal from the sound signal. From the up-sampled sound signal, odd-ordered high-harmonic generator generates an odd-ordered high-harmonic, and even-ordered high-harmonic generator generates an even-ordered high-harmonic. Vowel sound detector identifies whether or not the sound signal is vowel sound, and generates a first gain value and a second gain value. First gain controller amplifies or attenuates the odd-ordered high-harmonic based on the first gain value, and outputs the resultant odd-ordered high-harmonic. Second gain controller amplifies or attenuates the even-ordered high-harmonic based on the second gain value, and outputs the resultant even-ordered high-harmonic. Sound signal processing device adds the gain-adjusted odd-ordered high-harmonic and the gain-adjusted even-ordered high-harmonic to the up-sampled sound signal, and outputs the up-sampled sound signal having the high-harmonics added.

Abstract translation: 上采样器从声音信号产生上采样的声音信号。 从上采样的声音信号中，奇数有序的高次谐波发生器产生奇数有序的高次谐波，偶数阶高次谐波发生器产生均匀有序的高次谐波。 元音声音检测器识别声音信号是否是元音，并产生第一增益值和第二增益值。 第一增益控制器基于第一增益值放大或衰减奇数有序高次谐波，并输出所得到的奇数高次谐波。 第二增益控制器基于第二增益值放大或衰减偶次高次谐波，并输出所得到的偶次高次谐波。 声音信号处理装置将经增益调整的奇数有序高次谐波和经增益调整的偶次高次谐波加到上采样声音信号中，并输出具有高次谐波加法的上采样声信号。