公开(公告)号：US20210166714A1

公开(公告)日：2021-06-03

申请号：US16700357

申请日：2019-12-02

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Jonathan Samn ,  Poojitha Bikki ,  Minsik Lee ,  Satya Sreenivas

IPC: G10L21/0264 ,  G10L15/16 ,  G10L15/02 ,  G10L15/26 ,  G10L19/26

Abstract: Isolating and amplifying a conversation between selected participants is provided. A plurality of spectral masks is received. Each spectral mask in the plurality corresponds to a respective participant in a selected group of participants included in a conversation. A composite spectral mask is generated by additive superposition of the plurality of spectral masks. The composite spectral mask is applied to sound captured by a microphone to filter out sounds that do not match the composite spectral mask and amplifying remaining sounds that match the composite spectral mask.

公开(公告)号：US11410675B2

公开(公告)日：2022-08-09

申请号：US16937734

申请日：2020-07-24

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Jonathan Samn ,  Poojitha Bikki ,  Naeem Altaf

IPC: H04R29/00 ,  G10L25/51 ,  H02S40/38 ,  A01K29/00 ,  G06F16/61 ,  H04W84/04

Abstract: An animal audio signature may be collected by a solar powered sound collection device. The solar powered collection device may use a supercapacitor to store power. The animal audio signature may be compared to a database of known animal audio signatures. The database may contain one or more identities for each of the known animal audio signatures. A known animal audio signature that matches the collected animal audio signature may be identified. An identity associated with the known animal audio signature may be transmitted to a data repository over a 5G wireless network.

公开(公告)号：US11257510B2

公开(公告)日：2022-02-22

申请号：US16700357

申请日：2019-12-02

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Jonathan Samn ,  Poojitha Bikki ,  Minsik Lee ,  Satya Sreenivas

IPC: G10L21/0208 ,  G10L21/0264 ,  G10L15/16 ,  G10L15/26 ,  G10L19/26 ,  G10L15/02

Abstract: Isolating and amplifying a conversation between selected participants is provided. A plurality of spectral masks is received. Each spectral mask in the plurality corresponds to a respective participant in a selected group of participants included in a conversation. A composite spectral mask is generated by additive superposition of the plurality of spectral masks. The composite spectral mask is applied to sound captured by a microphone to filter out sounds that do not match the composite spectral mask and amplifying remaining sounds that match the composite spectral mask.

公开(公告)号：US11514892B2

公开(公告)日：2022-11-29

申请号：US16823725

申请日：2020-03-19

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jonathan Samn ,  Poojitha Bikki ,  Jeb R. Linton ,  Minsik Lee

IPC: G10L15/16 ,  G06N3/04 ,  G10L15/32 ,  G10L15/30

Abstract: A system includes a memory having instructions therein and at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to communicate, into a user device, a deep neural network comprising a predictive audio spectral mask. The at least one processor is also configured to execute the instructions to: generate data corresponding to ambient sound via a multi-microphone device; separate amplitude data and/or phase data from the data via the deep neural network comprising the predictive audio spectral mask; and determine, via the user device and based on the amplitude data and/or phase data, a location of origin of target speech relative to the user device. The at least one processor is configured to execute the instructions to display, via the user device, the location of origin of the target speech relative to the user device.

公开(公告)号：US20220028413A1

公开(公告)日：2022-01-27

申请号：US16937734

申请日：2020-07-24

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Jonathan Samn ,  Poojitha Bikki ,  Naeem Altaf

IPC: G10L25/51 ,  H02S40/38 ,  G06F16/61 ,  A01K29/00

Abstract: An animal audio signature may be collected by a solar powered sound collection device. The solar powered collection device may use a supercapacitor to store power. The animal audio signature may be compared to a database of known animal audio signatures. The database may contain one or more identities for each of the known animal audio signatures. A known animal audio signature that matches the collected animal audio signature may be identified. An identity associated with the known animal audio signature may be transmitted to a data repository over a 5G wireless network.

公开(公告)号：US20210295828A1

公开(公告)日：2021-09-23

申请号：US16823725

申请日：2020-03-19

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jonathan Samn ,  Poojitha Bikki ,  Jeb R. Linton ,  Minsik Lee

IPC: G10L15/16 ,  G10L15/30 ,  G10L15/32 ,  G06N3/04

Abstract: A system includes a memory having instructions therein and at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to communicate, into a user device, a deep neural network comprising a predictive audio spectral mask. The at least one processor is also configured to execute the instructions to: generate data corresponding to ambient sound via a multi-microphone device; separate amplitude data and/or phase data from the data via the deep neural network comprising the predictive audio spectral mask; and determine, via the user device and based on the amplitude data and/or phase data, a location of origin of target speech relative to the user device. The at least one processor is configured to execute the instructions to display, via the user device, the location of origin of the target speech relative to the user device.