Bose Corporation

Marko Stamenovic

Andrew Todd Sabin

Daniel Ross Tengelsen

Carl Ralph Jensen

Li-Chia Yang

Jahn Dmitri Eichfeld

Kenneth S Lyons

Sara Maree Adkins

Wade P Torres

Andrew Jackson Stockton, X

Andrew Jackson Stockton X

Kenneth Scott Lyons

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.

Artificial intelligence (AI) acoustic feedback suppression

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.

Audio processing using distributed machine learning model

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.

Machine learning based self-speech removal

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.

Wearable hearing assist device with artifact remediation

An audio enhancement method includes receiving a first plurality of input signals representative of audio captured using an array of two or more sensors, the first plurality of input signals 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 combining the first plurality of input signals and the second input signal to generate one or more driver signals, and driving one or more acoustic transducers using the one or more driver signals to generate an acoustic signal representative of the audio. The driver signals include spatial information derived from the first plurality of input signals, and are characterized by a third SNR that is higher than the first SNR.

Enhancement of audio from remote audio sources

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.

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.

Growing community of inventors

Jamaica Plain, MA, United States of America

Marko Stamenovic