公开(公告)号：US20190043488A1

公开(公告)日：2019-02-07

申请号：US16134826

申请日：2018-09-18

Applicant: Intel Corporation

Inventor： Tobias Bocklet ,  Jacek Ossowski ,  Tomasz Dorau ,  Maciej Muchlinski ,  David Pearce ,  Piotr Rozen

IPC: G10L15/16 ,  G10L15/22 ,  G10L15/02 ,  G10L25/84

Abstract: A method and system are directed to autonomous neural network keyphrase detection and includes generating and using a multiple element state score vector by using neural network operations and without substantial use of a digital signal processor (DSP) to perform the keyphrase detection.

公开(公告)号：US20240193981A1

公开(公告)日：2024-06-13

申请号：US18064519

申请日：2022-12-12

Applicant: Intel Corporation

Inventor： David Pearce ,  David Stanhill

IPC: G06V40/10 ,  G06V10/82 ,  G06V40/60

CPC classification number: G06V40/103 ,  G06V10/82 ,  G06V40/60

Abstract: A user computing device includes a camera sensor and a depth sensor. Image data generated by the camera captures an image of a user of the user computing device and is provided as an input to a first machine learning model trained to determine a feature set associated with posture of the user from the image data. Depth data generated by the depth sensor contemporaneously with generation of the image data is provided as input to a second machine learning model along with the first feature set to generate a second feature set as an output of the second machine learning model based on the depth data and the first feature set. The posture of the user is determined from the second feature set to provide feedback to the user.

公开(公告)号：US10236001B2

公开(公告)日：2019-03-19

申请号：US15988710

申请日：2018-05-24

Applicant: INTEL CORPORATION

Inventor： David Pearce

IPC: G10L15/04 ,  G10L15/05 ,  G10L17/04 ,  G10L17/22

Abstract: Techniques for passive enrollment of a user in a speaker identification (ID) device are provided. One technique includes: parsing, by a processor of the speaker ID device, a speech sample, spoken by the user, into a keyword phrase sample and a command phrase sample; identifying, by a text-dependent speaker ID circuit of the speaker ID device, the user as the speaker of the keyword phrase sample; associating the command phrase sample with the identified user; determining if the command phrase sample in conjunction with one or more earlier command phrase samples associated with the user is sufficient command phrase sampling to enroll the user in a text-independent speaker ID circuit of the speaker ID device; and enrolling the user in the text-independent speaker ID circuit using the command phrase samples associated with the user after determining there is sufficient command phrase sampling to enroll the user.

公开(公告)号：US20180277121A1

公开(公告)日：2018-09-27

申请号：US15988710

申请日：2018-05-24

Applicant: INTEL CORPORATION

Inventor： David Pearce

IPC: G10L17/04 ,  G10L15/04 ,  G10L17/22 ,  G10L15/05

CPC classification number: G10L17/04 ,  G10L15/04 ,  G10L15/05 ,  G10L17/22

Abstract: Techniques for passive enrollment of a user in a speaker identification (ID) device are provided. One technique includes: parsing, by a processor of the speaker ID device, a speech sample, spoken by the user, into a keyword phrase sample and a command phrase sample; identifying, by a text-dependent speaker ID circuit of the speaker ID device, the user as the speaker of the keyword phrase sample; associating the command phrase sample with the identified user; determining if the command phrase sample in conjunction with one or more earlier command phrase samples associated with the user is sufficient command phrase sampling to enroll the user in a text-independent speaker ID circuit of the speaker ID device; and enrolling the user in the text-independent speaker ID circuit using the command phrase samples associated with the user after determining there is sufficient command phrase sampling to enroll the user.

公开(公告)号：US09990926B1

公开(公告)日：2018-06-05

申请号：US15457738

申请日：2017-03-13

Applicant: INTEL CORPORATION

Inventor： David Pearce

IPC: G10L15/04 ,  G10L15/05 ,  G10L17/04 ,  G10L15/18 ,  G10L17/02 ,  G10L17/22 ,  G10L15/08

CPC classification number: G10L17/04 ,  G10L15/04 ,  G10L15/05 ,  G10L17/22

Abstract: Techniques for passive enrollment of a user in a speaker identification (ID) device are provided. One technique includes: parsing, by a processor of the speaker ID device, a speech sample, spoken by the user, into a keyword phrase sample and a command phrase sample; identifying, by a text-dependent speaker ID circuit of the speaker ID device, the user as the speaker of the keyword phrase sample; associating the command phrase sample with the identified user; determining if the command phrase sample in conjunction with one or more earlier command phrase samples associated with the user is sufficient command phrase sampling to enroll the user in a text-independent speaker ID circuit of the speaker ID device; and enrolling the user in the text-independent speaker ID circuit using the command phrase samples associated with the user after determining there is sufficient command phrase sampling to enroll the user.