公开(公告)号：US20240290340A1

公开(公告)日：2024-08-29

申请号：US18573932

申请日：2021-06-24

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Rintaro IKESHITA ,  Keisuke KINOSHITA ,  Naoyuki KAMO ,  Tomohiro NAKATANI

IPC分类号： G10L21/0224 ,  G10L21/0208

CPC分类号： G10L21/0224 ,  G10L2021/02082

摘要： Provided is a highly accurate dereverberation technique even under a noise environment or under a poor determination condition. A filter generation device that generates a reverberation prediction filter G[t] used at a time point t from an observation signal x[t] at the time point t, includes a switch determination unit that determines a switch c* according to a predetermined expression, a filter generation unit that sets a reverberation prediction filter G[c*] calculated according to a predetermined expression as the reverberation prediction filter G[t], and a matrix update unit that updates a matrix B[c] according to a predetermined expression.

公开(公告)号：US20240129666A1

公开(公告)日：2024-04-18

申请号：US18273272

申请日：2021-01-29

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Tsubasa OCHIAI ,  Marc DELCROIX ,  Tomohiro NAKATANI ,  Rintaro IKESHITA ,  Keisuke KINOSHITA ,  Shoko ARAKI

IPC分类号： H04R3/00 ,  H04R1/32

CPC分类号： H04R3/005 ,  H04R1/326 ,  H04R1/406

摘要： An estimation apparatus 10 is a signal processing apparatus for processing an acoustic signal and estimates an observation signal of a virtual microphone arranged virtually from an input observation signal of a real microphone using a deep learning model having a neural network (NN) 11.

公开(公告)号：US20240038253A1

公开(公告)日：2024-02-01

申请号：US18265909

申请日：2020-12-14

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Rintaro IKESHITA ,  Tomohiro NAKATANI ,  Shoko ARAKI

IPC分类号： G10L21/0216 ,  G06F17/11 ,  G06F17/16

CPC分类号： G10L21/0216 ,  G06F17/11 ,  G06F17/16

摘要： A sound source signal generation technology based on an optimization algorithm that enables high-speed processing of sound source extraction is provided. A sound source signal generation device includes an optimization unit that optimizes a separation matrix W(f)=[w1(f), . . . , wK(f), WZ(f)] using an observed signal x(f, t), the optimization unit includes an auxiliary function calculation unit that calculates an auxiliary function Vi(f) (i=1, . . . , K) according to a predetermined equation, a first separation filter calculation unit that calculates a separation filters wi(f) (i=1, . . . , K) using auxiliary functions Vi(f) (i=1, . . . , K) and Vz(f), and a second separation filter calculation unit that calculates a separation filter WZ(f) according to a predetermined equation when a convergence condition is satisfied.

公开(公告)号：US20220076690A1

公开(公告)日：2022-03-10

申请号：US17431347

申请日：2020-02-12

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Tsubasa OCHIAI ,  Marc DELCROIX ,  Keisuke KINOSHITA ,  Atsunori OGAWA ,  Tomohiro NAKATANI

IPC分类号： G10L21/0308 ,  G10L25/30

摘要： A signal processing device according to an embodiment of the present invention includes: a conversion unit configured to convert an input mixed acoustic signal into a plurality of first internal states, a weighting unit configured to generate a second internal state which is a weighted sum of the plurality of first internal states based on auxiliary information regarding an acoustic signal of a target sound source when the auxiliary information is input, and generate the second internal state by selecting one of the plurality of first internal states when the auxiliary information is not input, and a mask estimation unit configured to estimate a mask based on the second internal state.

公开(公告)号：US20240105202A1

公开(公告)日：2024-03-28

申请号：US18274767

申请日：2021-02-04

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Rintaro IKESHITA ,  Naoyuki KAMO ,  Tomohiro NAKATANI

IPC分类号： G10L21/0232

CPC分类号： G10L21/0232

摘要： Provided is a reverberation removal device that is highly accurate even in noisy environments and underdetermined conditions. Reverberation is removed by applying a plurality of reverberation prediction filters to an observation signal while switching the plurality of reverberation prediction filters according to each time frequency bin of the observation signal.

公开(公告)号：US20230239616A1

公开(公告)日：2023-07-27

申请号：US18010790

申请日：2020-06-19

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Tomohiro NAKATANI ,  Keisuke KINOSHITA ,  Marc DELCROIX

IPC分类号： H04R3/00 ,  H04R1/40 ,  G10K11/175 ,  G10K11/34 ,  G06N3/084

CPC分类号： H04R3/005 ,  H04R1/406 ,  G10K11/1752 ,  G10K11/34 ,  G06N3/084

摘要： Provided is a target sound extraction technique based on a steering vector generation method enabling instability in a calculation to be prevented when a neural network is trained by using an error back propagation method to reduce an estimation error of a beamformer. A target sound signal generation apparatus generates a target sound signal yt,f corresponding to a target sound included in an observed sound from an observed signal vector xt,f corresponding to the observed sound collected by using a plurality of microphones. The target sound signal generation apparatus includes a mask generation unit, a steering vector generation unit, a beamformer vector generation unit, and a target sound signal generation unit. The mask generation unit is configured as a neural network trained by using an error back propagation method. The steering vector generation unit generates a steering vector hf by determining an eigenvector corresponding to a maximum eigenvalue of a predetermined matrix generated from the observed signal vector xt,f and a mask γt,f by using a power method.

公开(公告)号：US20230087982A1

公开(公告)日：2023-03-23

申请号：US17802090

申请日：2020-02-26

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Rintaro IKESHITA ,  Tomohiro NAKATANI ,  Shoko ARAKI

IPC分类号： G10L21/028 ,  G10L25/21 ,  G10L21/0224

摘要： A signal processing device applies a convolutional separation filter, which is a combined filter of: a rear reverberation removal filter for suppressing a rear reverberation component from a mixed acoustic signal obtained by converting an observed mixed acoustic signal obtained by observing a source signal into a time-frequency domain; and a sound source separation filter for emphasizing components corresponding to source signals from the mixed acoustic signal, to a mixed acoustic signal string including the mixed acoustic signal and a delay signal of the mixed acoustic signal and estimates model parameters of a model for obtaining information corresponding to signals in which the rear reverberation component is suppressed and target signals emitted from target sound sources in the source signal are emphasized.

公开(公告)号：US20230067132A1

公开(公告)日：2023-03-02

申请号：US17794266

申请日：2020-02-14

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Tsubasa OCHIAI ,  Marc DELCROIX ,  Rintaro IKESHITA ,  Keisuke KINOSHITA ,  Tomohiro NAKATANI ,  Shoko ARAKI

IPC分类号： G10L21/0272 ,  H04R3/00 ,  G10L25/93

摘要： A signal processing apparatus includes a neural network (“NN”), a sorting unit, and a spatial covariance matrix calculation unit. The NN converts a mixed signal, in which sounds of a plurality of sound sources input by a plurality of channels are mixed, into a separated signal separated into a signal for each sound source as a signal in a time domain as it is and outputs the separated signal. The sorting unit sorts, for the separated signal of each channel output from the NN, the separated signal of each channel such that the plurality of sound sources of a plurality of the separated signals are aligned among the plurality of channels. The spatial covariance matrix calculation unit calculates a spatial covariance matrix corresponding to each sound source in accordance with the separated signal for each channel output from the sorting unit and sorted.

公开(公告)号：US20190267019A1

公开(公告)日：2019-08-29

申请号：US15998742

申请日：2016-12-20

申请人： Nippon Telegraph and Telephone Corporation

发明人： Nobutaka ITO ,  Shoko ARAKI ,  Tomohiro NAKATANI

IPC分类号： G10L21/028 ,  G10L21/0308 ,  G06K9/62

摘要： A feature extraction unit in a mask estimation apparatus extracts, from a plurality of observation signals obtained by observing a plurality of acoustic signals at different positions, feature vectors obtained by collecting time-frequency components of the observation signals for each time-frequency point. A mask update unit uses the feature vectors, a mixture weight of each component distribution, and a shape parameter that is a model parameter capable of controlling a shape of each component distribution, where a probability distribution of the feature vectors is modeled by a mixture distribution consisting of a plurality of component distributions, to estimate masks indicating a proportion in which each component distribution contributes to each time-frequency point. A mixture weight update unit updates the mixture weight based on the updated masks. A parameter update unit updates the shape parameter by using the feature vectors and the masks.

公开(公告)号：US20240312446A1

公开(公告)日：2024-09-19

申请号：US18571765

申请日：2021-09-30

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Tomohiro NAKATANI ,  Rintaro IKESHITA ,  Keisuke KINOSHITA ,  Hiroshi SAWADA ,  Naoyuki KAMO ,  Shoko ARAKI

IPC分类号： G10K11/178 ,  H04R3/00

CPC分类号： G10K11/17821 ,  G10K11/17881 ,  H04R3/005

摘要： There is provided an acoustic signal enhancement device that receives, as an input, a recording sound obtained by frequency division and updates parameters, the device including: assuming that a switch weight is a weight indicating a ratio of a classification to which a recording sound at each timing belongs in classifications of spatial states where a recording sound temporally changes, a beamformer unit that performs beamformer processing based on a weighted spatial covariance matrix which is updated and updates an auxiliary estimation value of a target sound; a switch unit that updates the switch weight and power of a target sound based on the updated auxiliary estimation value and outputs an estimation value of the target sound; and a weighted spatial covariance estimation unit that updates the weighted spatial covariance matrix based on the updated switch weight and the power.