Butterfly Network, Inc.

Bfly Operations, Inc.

Chromatic Inc.

Fortell Research Inc.

Matthew De Jonge

David Elgena

Igor Lovchinsky

Jonathan Marc Rothberg

Nicholas Morris

Andrew J Casper

Jonathan Macoskey

Christopher Thomas McNulty

Tomer Gafner

Stephen M Christopher

Alex Rothberg

Abraham Neben

Philip Meyers, Iv

Paul Maxted

Michal Sofka

Jonathan C Schultz

Benjamin Chopra

Jimmy Jia

Cristina Shin

Karl E Thiele

Jaime Scott Zahorian

Keith Glen Fife

Tyler S Ralston

Nevada J Sanchez

Susan A Alie

Paul Francis Cristman

Robert Schneider

Nathan Silberman

Neil Ferrier

Kevin Coss

Daniel Nouri

Jason Z Fischman

Ryan Silvestri

Timothy A Hyde

Adam Mekeel Mack

Audrey Howell

Yang Liu

Israel Malkin

Mark Michalski

Dominick L Mastri

Jonathan M Rothberg

Jake Eisner

Vineet Shah

Kirthi Bellamkonda

Swaminathan Sankaranarayanan

Maxim Zaslavsky

Brandon Lane

Kurt Guenther

Eamon Duffy

Matthew R Hageman

An ear-worn device may include two or more microphones configured to generate time-domain audio signals, each of the two or more microphones configured to generate one of the time-domain audio signals; processing circuitry comprising analog processing circuitry, digital processing circuitry, beamforming circuitry, and short-time Fourier transformation (STFT) circuitry, the processing circuitry configured to generate, from the time-domain audio signals, one or more frequency-domain non-beamformed audio signals and one or more frequency-domain beamformed signals; and enhancement circuitry comprising neural network circuitry configured to receive multiple frequency-domain input audio signals originating from the one or more frequency-domain non-beamformed audio signals and the one or more frequency-domain beamformed signals, and implement a single neural network trained to generate, based on the multiple frequency-domain input audio signals, a noise-reduced and spatially-focused output audio signal or an output for generating a noise-reduced and spatially-focused output audio signal.

Ear-worn device with neural network for noise reduction and/or spatial focusing using multiple input audio signals

A hearing aid may include a neural network chip having tiles arranged in an array, each tile including memory, 16-128 multiplier-accumulator circuits (MACs), and routing circuitry. The memory of each tile may be configured to store a portion of elements of a matrix A comprising weights of a recurrent neural network. Each tile may be configured to receive and store elements of an activation vector X, and all tiles in a column of the array may be configured to receive the same elements of X. The plurality of tiles may be configured to perform a matrix-vector multiplication A*X by performing multiply-and-accumulate sub-operations in parallel among the plurality of tiles. The routing circuitry from the tiles in each respective row of tiles may be configured to combine results of the multiply-and-accumulate sub-operations.

Neural network chip for ear-worn device

An ear-worn device is provided that operates to isolate and individually treat the received speech of a target speaker or multiple target speakers from an audio input signal detected in a multi-speaker environment. The ear-worn device uses a machine learning model that receives a voice signature of each of one or more target speakers as input signals, to identify and isolate the component of the audio input signal attributable to the target speaker(s). Once isolated, the target speaker's speech may be enhanced, de-emphasized, or otherwise processed in a manner desired by the wearer of the ear-worn device. The wearer may use an external electronic device, e.g., a phone, to select one or more target speakers in a conversation and/or configure various settings associated with processing the speech on the ear-worn device.

System and method for enhancing speech of target speaker from audio signal in an ear-worn device using voice signatures

The disclosure generally relates to a method, system and apparatus to improve a user's understanding of speech in real-time conversations by processing the audio through a neural network contained in a hearing device. The hearing device may be a headphone or hearing aid. In one embodiment, the disclosure relates to an apparatus to enhance incoming audio signal. The apparatus includes a controller to receive an incoming signal and provide a controller output signal; a neural network engine (NNE) circuitry in communication with the controller, the NNE circuitry activatable by the controller, the NNE circuitry configured to generate an NNE output signal from the controller output signal; and a digital signal processing (DSP) circuitry to receive one or more of controller output signal or the NNE circuitry output signal to thereby generate a processed signal; wherein the controller determines a processing path of the controller output signal through one of the DSP or the NNE circuitries as a function of one or more of predefined parameters, incoming signal characteristics and NNE circuitry feedback.

Method, apparatus and system for neural network hearing aid

Method, apparatus and system for neural network enabled hearing aid

According to some embodiments, an ear-worn device, e.g., a hearing aid, is provided that operates both as an over-the-counter device, as well as a prescription device. Features stored on the ear-worn device may be used to amplify, enhance, de-noise, or otherwise process audio signals in a manner desired by the user. Some features, or settings of those features, process audio signals in a manner that is unsafe for users with mild-to-moderate hearing loss and thus are disabled when the ear-worn device is operating as an over-the-counter device. Such features and settings may be enabled after the ear-worn device is fit to the user by a licensed professional.

Ear-worn device configured for over-the-counter and prescription use

Aspects of the technology described herein relate to techniques for calculating, during imaging, a quality of a sequence of images collected during the imaging. Calculating the quality of the sequence of images may include calculating a probability that a medical professional would use a given image for clinical evaluation and a confidence that an automated analysis segmentation performed on the given image is correct. Techniques described herein also include receiving a trigger to perform an automatic measurement on a sequence of images, calculating a quality of the sequence of images, determining whether the quality of the sequence of images exceeds a threshold quality, and performing the automatic measurement on the sequence of images based on determining that the quality of the sequence of images exceeds the threshold quality.

Quality indicators for collection of and automated measurement on ultrasound images

A hearing aid includes a non-programmable user input device that is not programmable by a user nor by an audiologist, control circuitry configured to receive an activation signal from the non-programmable user input device, one or more microphones, neural network circuitry configured to denoise audio signals received by the one or more microphones, and communication circuitry. The hearing aid is configured to detect, using the control circuitry, user activation of the non-programmable user input device on the hearing aid; control, using the control circuitry and based on detecting the activation of the non-programmable user input device on the hearing aid, switching between enabling and disabling the neural network circuitry; and transmit, using the communication circuitry, an indication of the enabling or disabling of the neural network circuitry to a processing device in operative communication with the hearing aid.

Neural-network based denoising of audio signals received by an ear-worn device controlled based on activation of a user input device on the ear-worn device

Growing community of inventors

Brooklyn, NY, United States of America

Matthew De Jonge