公开(公告)号：US11711648B2

公开(公告)日：2023-07-25

申请号：US16814361

申请日：2020-03-10

Applicant: Intel Corporation

Inventor： Kuba Lopatka ,  Adam Kupryjanow ,  Lukasz Kurylo ,  Karol Duzinkiewicz ,  Przemyslaw Maziewski ,  Marek Zabkiewicz

IPC: H04R3/00 ,  H04R1/40 ,  G10L25/51 ,  G10L25/30 ,  H04R3/04 ,  G10L21/0232 ,  G06N3/08 ,  G10L25/18 ,  G10L21/0216

CPC classification number: H04R3/005 ,  G06N3/08 ,  G10L21/0232 ,  G10L25/18 ,  G10L25/30 ,  G10L25/51 ,  H04R1/406 ,  H04R3/04 ,  G10L2021/02166 ,  H04R2410/07

Abstract: Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.

公开(公告)号：US20250076496A1

公开(公告)日：2025-03-06

申请号：US18954232

申请日：2024-11-20

Applicant: Intel Corporation

Inventor： Mariusz Pietrolaj ,  Lukasz Kurylo ,  Kuba Lopatka ,  Marek Zabkiewicz

IPC: G01S15/04 ,  G06F1/3206

Abstract: Systems and methods are provided for an acoustic-based determination that a device is inside a bag, enabling a device to react early to a potential hot bag scenario before the device begins to overheat. Acoustic cues associated with the device being put in a bag can be detected, and an ultrasonic echo can be analyzed to identify characteristics of reflections from a bag material. Ambient acoustics are used as a cue for hot bag detection, and acoustic analysis can be implemented in an audio digital signal processor, consuming a minimum amount of energy and allowing the acoustic-based device context detection method to function when the device is in standby, sleep, and/or hibernate mode. When the acoustic-based device context detection method determines that the device is inside a bag, the method prevents the device from entering a high power state, providing users with worry-free battery life.

公开(公告)号：US20190043489A1

公开(公告)日：2019-02-07

申请号：US16146416

申请日：2018-09-28

Applicant: INTEL CORPORATION

Inventor： Kuba Lopatka ,  Mateusz Kotarski ,  Tobias Bocklet ,  Marek Zabkiewicz

IPC: G10L15/16 ,  G10L15/22 ,  G06F17/14 ,  G10L15/02 ,  G06N3/04 ,  G06F9/54

CPC classification number: G10L15/16 ,  G06F9/542 ,  G06F17/147 ,  G06K9/00536 ,  G06K9/4628 ,  G06K9/627 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G10L15/02 ,  G10L15/22 ,  G10L25/51

Abstract: Techniques are provided for efficient acoustic event detection with reduced resource consumption. A methodology implementing the techniques according to an embodiment includes calculating frames of power spectra based on segments of received acoustic signals. The method further includes two processes, one for detecting impulsive acoustic events and another for detecting continuous acoustic events. The first process includes generating impulsive acoustic event features associated with first and second power spectrum frames, applying a neural network classifier to the impulsive acoustic event features to generate event scores, and detecting an impulsive acoustic event based on those event scores. The second process includes generating reduced-dimension continuous acoustic event features associated with the first and second power spectrum frames, applying a neural network classifier to the reduced-dimension continuous acoustic event features to generate a second set of event scores, and detecting a continuous acoustic event based on the second set of event scores.

公开(公告)号：US10789941B2

公开(公告)日：2020-09-29

申请号：US16146416

申请日：2018-09-28

Applicant: INTEL CORPORATION

Inventor： Kuba Lopatka ,  Mateusz Kotarski ,  Tobias Bocklet ,  Marek Zabkiewicz

IPC: G10L15/16 ,  G10L15/22 ,  G10L15/02 ,  G06N3/04 ,  G06F17/14 ,  G06K9/00 ,  G06K9/62 ,  G10L25/51 ,  G06N3/08 ,  G06F9/54 ,  G06K9/46

Abstract: Techniques are provided for efficient acoustic event detection with reduced resource consumption. A methodology implementing the techniques according to an embodiment includes calculating frames of power spectra based on segments of received acoustic signals. The method further includes two processes, one for detecting impulsive acoustic events and another for detecting continuous acoustic events. The first process includes generating impulsive acoustic event features associated with first and second power spectrum frames, applying a neural network classifier to the impulsive acoustic event features to generate event scores, and detecting an impulsive acoustic event based on those event scores. The second process includes generating reduced-dimension continuous acoustic event features associated with the first and second power spectrum frames, applying a neural network classifier to the reduced-dimension continuous acoustic event features to generate a second set of event scores, and detecting a continuous acoustic event based on the second set of event scores.

公开(公告)号：US20200213728A1

公开(公告)日：2020-07-02

申请号：US16814361

申请日：2020-03-10

Applicant: Intel Corporation

Inventor： Kuba Lopatka ,  Adam Kupryjanow ,  Lukasz Kurylo ,  Karol Duzinkiewicz ,  Przemyslaw Maziewski ,  Marek Zabkiewicz

IPC: H04R3/00 ,  H04R1/40 ,  G10L25/51 ,  G10L25/30 ,  G10L25/18 ,  H04R3/04 ,  G10L21/0232 ,  G06N3/08

Abstract: Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.