公开(公告)号：US11750984B2

公开(公告)日：2023-09-05

申请号：US17032801

申请日：2020-09-25

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Andrew Todd Sabin ,  Jahn Dmitri Eichfeld

IPC: H04R25/00 ,  G10L15/20

CPC classification number: H04R25/45 ,  G10L15/20 ,  H04R2225/43

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a process includes receiving an audio signal, wherein the audio signal includes a speech component of the user and a noise component; filtering the audio signal with a self-speech filter that utilizes an intrinsic user vector to filter out the speech component, wherein the intrinsic user vector is determined based on a voice input of the user; and outputting a filtered audio signal in which the speech component of the user has been substantially removed from the audio signal.

公开(公告)号：US20220103951A1

公开(公告)日：2022-03-31

申请号：US17032801

申请日：2020-09-25

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Andrew Todd Sabin ,  Jahn Dmitri Eichfeld

IPC: H04R25/00 ,  G10L15/20

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a process includes receiving an audio signal, wherein the audio signal includes a speech component of the user and a noise component; filtering the audio signal with a self-speech filter that utilizes an intrinsic user vector to filter out the speech component, wherein the intrinsic user vector is determined based on a voice input of the user; and outputting a filtered audio signal in which the speech component of the user has been substantially removed from the audio signal.

公开(公告)号：US11553286B2

公开(公告)日：2023-01-10

申请号：US17321865

申请日：2021-05-17

Applicant: Bose Corporation

Inventor： Andrew Todd Sabin ,  Marko Stamenovic ,  Li-Chia Yang

IPC: H04R25/00

Abstract: Various implementations include systems for processing audio signals to remove artifacts introduced by a machine learning system in challenging environments. In particular implementations, a method includes generating a processed audio signal for a hearing assistance device in which the processed audio signal is intended to perceptually dominate a user auditory experience, including: processing an unprocessed audio signal received by the hearing assistance device, wherein the processing includes utilizing a machine learning (ML) system to generate an ML enhanced audio signal; determining a mixing coefficient from an environmental noise assessment; mixing the ML enhanced audio signal with the unprocessed audio signal using the mixing coefficient to generate the processed audio signal; and outputting the processed audio signal.

公开(公告)号：US20210082450A1

公开(公告)日：2021-03-18

申请号：US16782692

申请日：2020-02-05

Applicant: Bose Corporation

Inventor： Carl Jensen ,  Andrew Todd Sabin ,  Andrew Jackson Stockton X ,  Daniel Ross Tengelsen ,  Marko Stamenovic

IPC: G10L21/0232 ,  G10L25/18 ,  H04R1/40 ,  H04R3/00

Abstract: An audio enhancement method includes receiving a first input signal representative of audio captured using an array of two or more sensors, the first input signal characterized by a first signal-to-noise ratio (SNR), with the audio being the signal-of-interest. The method also includes receiving a second input signal representative of the audio, the second input signal characterized by a second SNR. The second SNR is higher than the first SNR. The method further includes computing a spectral mask based on a frequency domain representation of the second input signal, and processing a frequency domain representation of the first input signal based on the spectral mask to generate one or more driver signals. The method further includes driving one or more acoustic transducers using the generated driver signals.

公开(公告)号：US20220078551A1

公开(公告)日：2022-03-10

申请号：US17526070

申请日：2021-11-15

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Li-Chia Yang ,  Carl Ralph Jensen ,  Kenneth Scott Lyons ,  Sara Maree Adkins ,  Jahn Dmitri Eichfeld ,  Daniel Ross Tengelsen

IPC: H04R3/04 ,  G10L21/0232 ,  H04R5/033 ,  H04R5/04

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: an accessory device that includes a first processor for running a machine learning model on an input signal, where the machine learning model includes a classifier configured to generate metadata associated with the input signal; and a wearable audio device configured for wireless communication with the accessory device, the wearable audio device including a second processor that utilizes the metadata from the accessory device to process a source audio signal and output a processed audio signal.

公开(公告)号：US20210289296A1

公开(公告)日：2021-09-16

申请号：US16818074

申请日：2020-03-13

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Li-Chia Yang ,  Carl Ralph Jensen ,  Kenneth Scott Lyons ,  Sara Maree Adkins ,  Jahn Dmitri Eichfeld ,  Daniel Ross Tengelsen

IPC: H04R3/04 ,  H04R5/04 ,  H04R5/033 ,  G10L21/0232

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: a wearable audio device having a transducer and a communication system; and an accessory device configured to wirelessly communicate with the wearable audio device, the accessory device having a processor configured to process a source audio signal according to a method that includes: source separating the source audio signal; and providing a source separated audio signal to the wearable audio device for transduction.

公开(公告)号：US11832072B2

公开(公告)日：2023-11-28

申请号：US17526070

申请日：2021-11-15

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Li-Chia Yang ,  Carl Ralph Jensen ,  Kenneth Scott Lyons ,  Sara Maree Adkins ,  Jahn Dmitri Eichfeld ,  Daniel Ross Tengelsen

IPC: H04R3/04 ,  G10L21/0232 ,  H04R5/033 ,  H04R5/04 ,  G10L21/0216 ,  G10L21/0208

CPC classification number: H04R3/04 ,  G10L21/0232 ,  H04R5/033 ,  H04R5/04 ,  G10L21/0208 ,  G10L2021/02163 ,  H04R2420/07

Abstract: Various implementations include systems for processing audio signals. In particular implementations, a system for processing audio signals includes: an accessory device that includes a first processor for running a machine learning model on an input signal, where the machine learning model includes a classifier configured to generate metadata associated with the input signal; and a wearable audio device configured for wireless communication with the accessory device, the wearable audio device including a second processor that utilizes the metadata from the accessory device to process a source audio signal and output a processed audio signal.

公开(公告)号：US20220369047A1

公开(公告)日：2022-11-17

申请号：US17321865

申请日：2021-05-17

Applicant: Bose Corporation

Inventor： Andrew Todd Sabin ,  Marko Stamenovic ,  Li-Chia Yang

IPC: H04R25/00

Abstract: Various implementations include systems for processing audio signals to remove artifacts introduced by a machine learning system in challenging environments. In particular implementations, a method includes generating a processed audio signal for a hearing assistance device in which the processed audio signal is intended to perceptually dominate a user auditory experience, including: processing an unprocessed audio signal received by the hearing assistance device, wherein the processing includes utilizing a machine learning (ML) system to generate an ML enhanced audio signal; determining a mixing coefficient from an environmental noise assessment; mixing the ML enhanced audio signal with the unprocessed audio signal using the mixing coefficient to generate the processed audio signal; and outputting the processed audio signal.

公开(公告)号：US11062723B2

公开(公告)日：2021-07-13

申请号：US16782692

申请日：2020-02-05

Applicant: Bose Corporation

Inventor： Carl Jensen ,  Andrew Todd Sabin ,  Andrew Jackson Stockton, X ,  Daniel Ross Tengelsen ,  Marko Stamenovic

IPC: G10L21/0232 ,  G10L25/18 ,  H04R3/00 ,  H04R1/40 ,  G10L21/0216

Abstract: An audio enhancement method includes receiving a first input signal representative of audio captured using an array of two or more sensors, the first input signal characterized by a first signal-to-noise ratio (SNR), with the audio being the signal-of-interest. The method also includes receiving a second input signal representative of the audio, the second input signal characterized by a second SNR. The second SNR is higher than the first SNR. The method further includes computing a spectral mask based on a frequency domain representation of the second input signal, and processing a frequency domain representation of the first input signal based on the spectral mask to generate one or more driver signals. The method further includes driving one or more acoustic transducers using the generated driver signals.

公开(公告)号：US12022268B1

公开(公告)日：2024-06-25

申请号：US18530669

申请日：2023-12-06

Applicant: Bose Corporation

Inventor： Marko Stamenovic ,  Li-Chia Yang

IPC: H04R3/02 ,  G06N3/0464 ,  H04R3/04 ,  H04R25/00 ,  H04R27/00

CPC classification number: H04R3/02 ,  H04R3/04 ,  H04R25/453 ,  H04R27/00 ,  G06N3/0464

Abstract: Various implementations include audio processing system having artificial intelligence (AI) acoustic feedback suppression. In some particular aspects, an audio processing system includes: an input adapted to receive an acoustic signal via a microphone; an electroacoustic transducer; an amplifier configured to amplify the acoustic signal and output an amplified signal via the electroacoustic transducer; and an artificial intelligence (AI) system having a machine learning model that processes the acoustic signal prior to amplification to produce a dynamic filter, wherein the AI system applies the dynamic filter to the acoustic signal to suppress feedback in the amplified signal.