公开(公告)号：US20250124938A1

公开(公告)日：2025-04-17

申请号：US18999380

申请日：2024-12-23

Applicant: Intel Corporation

Inventor： Adam Kupryjanow ,  Lukasz Pindor

IPC: G10L21/0208 ,  G06N3/08 ,  G10L21/0232 ,  G10L25/30 ,  G10L25/78 ,  H04R3/04

Abstract: A method and system of neural network dynamic noise suppression (DNS) is provided for audio processing. The system is a down-scaled DNS model that uses grouping techniques at pointwise convolutional layers to reduce the number of network parameters. According to one technique, audio signal data can be coded into an input vector that that is split into multiple groups, each groups having multiple channels. At a pointwise convolution layer, an output is generated for each group. The outputs can be concatenated to form a single input vector for a next layer of the model. Each group is treated as a channel, such that the reduction in the number of channels reduces the number of parameters used by the neural network. In some examples, the groups are weight sharing groups.

公开(公告)号：US20240406622A1

公开(公告)日：2024-12-05

申请号：US18204856

申请日：2023-06-01

Applicant: Intel Corporation

Inventor： Jaison Fernandez ,  Adam Kupryjanow ,  Srikanth Potluri ,  Tarakesava Reddy Koki ,  Aiswarya M. Pious

IPC: H04R3/00 ,  G10L21/028 ,  G10L25/30 ,  G10L25/60 ,  H04R5/027 ,  H04R29/00 ,  H04S3/00

Abstract: A computer-implemented method of audio processing comprises receiving, by at least one processor, multiple audio signals from multiple microphones. The audio signals are associated with audio emitted from a same source. The method also may include determining an audio quality indicator of individual ones of the audio signals using a neural network, and selecting at least one of the audio signals depending on the audio quality indicators.

公开(公告)号：US12126971B2

公开(公告)日：2024-10-22

申请号：US17132647

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Piotr Klinke ,  Damian Koszewski ,  Przemyslaw Maziewski ,  Jan Banas ,  Kuba Łopatka ,  Adam Kupryjanow ,  Paweł Trella ,  Paweł Pach

IPC: H04R29/00 ,  G01S11/14 ,  G06N3/08 ,  G10L21/0232 ,  G10L25/30 ,  G10L25/51 ,  H04R1/08 ,  G10L21/0208

CPC classification number: H04R29/004 ,  G01S11/14 ,  G06N3/08 ,  G10L21/0232 ,  G10L25/30 ,  G10L25/51 ,  H04R1/08 ,  G10L2021/02082

Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for acoustic signal processing adaptive to microphone distances. An example system includes a microphone to convert an acoustic signal to an electrical signal and one or more processors to: estimate a distance between a source of the acoustic signal and the microphone; select a signal processing mode based on the distance; and process the electrical signal in accordance with the selected processing mode.

公开(公告)号：US20240223948A1

公开(公告)日：2024-07-04

申请号：US18147777

申请日：2022-12-29

Applicant: Intel Corporation

Inventor： Adam Kupryjanow ,  Przemyslaw Maziewski ,  Lukasz Pindor ,  Sebastian Rosenkiewicz

IPC: H04R3/04

CPC classification number: H04R3/04 ,  H04R2410/03

Abstract: A user computing device includes a microphone to generate an audio signal and a self-noise silencer to generate a feature set corresponding to the audio signal, where the input feature identifies, for each of a plurality of frequency components in the audio signal, a respective magnitude value. At least a portion of the feature set is provided as an input to a machine learning model trained to infer frequencies contributing to self-noise generated at the microphone. An attenuation mask is generated, based on an output of the machine learning model, that identifies an attenuation value for at least a subset of the plurality of frequency components. The attenuation mask is applied to at least the subset of the magnitude values of the plurality of frequency components to remove self-noise from the audio signal and generate a denoised version of the audio signal.

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：US20220084535A1

公开(公告)日：2022-03-17

申请号：US17535759

申请日：2021-11-26

Applicant: Intel Corporation

Inventor： Adam Kupryjanow ,  Lukasz Pindor

IPC: G10L21/0208 ,  G06N3/08 ,  G10L25/78 ,  G10L25/30

Abstract: Techniques are provided for dynamic noise suppression. A methodology implementing the techniques according to an embodiment includes generating a magnitude spectrum and a phase spectrum of an input audio signal comprising speech and dynamic noise. The method also includes employing a temporal convolution network (TCN) to generate a separation mask based on the magnitude spectrum. The TCN comprises depth-wise (DW) convolution layers, each DW convolution layer including a state buffer to store a number of previous states of the associated DW convolution layer. The number of stored previous states is based on a dilation factor of the associated DW convolution layer. The method further includes multiplying the separation mask with the magnitude spectrum to separate the speech from the dynamic noise to obtain a denoised magnitude spectrum. The method further includes reconstructing the input audio signal with reduced dynamic noise based on the denoised magnitude spectrum and the phase spectrum.

公开(公告)号：US20220124433A1

公开(公告)日：2022-04-21

申请号：US17561848

申请日：2021-12-24

Applicant: Intel Corporation

Inventor： Adam Kupryjanow ,  Lukasz Pindor

IPC: H04R3/04 ,  G10L21/0232 ,  G06N3/08

Abstract: A method and system of neural network dynamic noise suppression is provided for audio processing.

公开(公告)号：US20200326401A1

公开(公告)日：2020-10-15

申请号：US16914064

申请日：2020-06-26

Applicant: Intel Corporation

Inventor： Hector Cordourier Maruri ,  Adam Kupryjanow ,  Karol Duzinkiewicz ,  Jose Rodrigo Camacho Perez ,  Paulo Lopez Meyer ,  Julio Zamora Esquivel ,  Alejandro Ibarra Von Borstel ,  Jonathan Huang

IPC: G01S3/808 ,  G01S3/86

Abstract: Methods, apparatus, systems, and articles of manufacture to detect the location of sound sources external to computing devices are disclosed. An apparatus, to determine a direction of a source of a sound relative to a computing device, includes a cross-correlation analyzer to generate a vector of values corresponding to a cross-correlation of first and second audio signals corresponding to the sound. The first audio signal is received from a first microphone of the computing device. The second audio signal is received from a second microphone of the computing device. The apparatus also includes a location analyzer to use a machine learning model and a set of the values of the vector to determine the direction of the source of the sound.

公开(公告)号：US10685666B2

公开(公告)日：2020-06-16

申请号：US15946847

申请日：2018-04-06

Applicant: Intel Corporation

Inventor： Przemyslaw Maziewski ,  Adam Kupryjanow ,  Lukasz Kurylo ,  Pawel Trella

IPC: G10L21/0364 ,  G10L15/22 ,  G10L15/20 ,  G06F3/16 ,  H03G3/30 ,  H04R29/00 ,  H03G3/34

Abstract: A mechanism is described for facilitating automatic gain adjustment in audio systems according to one embodiment. A method of embodiments, as described herein, includes determining status of one or more of gain settings, mute settings, and boost settings associated with one or more microphones based on a configuration of a computing device including a voice-enabled device. The method may further comprise recommending adjustment of microphone gain based on the configuration and the status of one or more of the gain, mute, and boost settings, and applying the recommended adjustment of the microphone gain.

公开(公告)号：US10657983B2

公开(公告)日：2020-05-19

申请号：US15388107

申请日：2016-12-22

Applicant: Intel Corporation

Inventor： Przemyslaw Maziewski ,  Adam Kupryjanow

IPC: G10L21/034 ,  H04R1/04 ,  G10L21/0364 ,  G10L25/21 ,  G10L15/20 ,  G10L15/22 ,  G10L21/0232 ,  G10L25/51 ,  H04R1/40 ,  H04R31/00 ,  G10L21/0216 ,  H04R3/00 ,  G10L21/0208 ,  H04R1/28 ,  G10L15/30

Abstract: System and techniques for automatic gain control for speech recognition are described herein. An audio signal may be obtained. A signal-to-noise ratio (SNR) may be derived from the audio signal. The SNR may be compared to a threshold. A stored gain value may be updated when the SNR is beyond the threshold and the stored gain value may be applied to a descendant (e.g., later) of the audio signal otherwise.