Method, apparatus and system for neural network hearing aid
The disclosure generally relates to a method, system and apparatus for processing audio through a neural network contained in a hearing device. 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; 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 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.
1 . An ear-worn device, comprising:
a first processing path comprising neural network engine (NNE) circuitry configured to separate speech from noise in an incoming audio signal; and
a second processing path comprising digital signal processing (DSP) circuitry configured to perform one or more of dynamic range compression, amplification, and frequency tuning on the incoming audio signal;
wherein:
the ear-worn device is configured to pass the incoming audio signal to the first processing path and the second processing path in parallel;
the ear-worn device is configured to determine whether to transmit the incoming audio signal to the first processing path or not based on user input; and
the NNE circuitry and the DSP circuitry are implemented on different processors.
2 . The ear-worn device of claim 1 , wherein the NNE circuitry is configured to separate the speech from the noise in the incoming audio signal in about 32 milliseconds or less of receipt of the incoming audio signal by the ear-worn device.
3 . The ear-worn device of claim 1 , wherein the NNE circuitry is configured to perform at least 1 billion operations per second.
4 . The ear-worn device of claim 1 , wherein the NNE circuitry is configured to achieve at least 2 billion operations per milliwatt.
5 . The ear-worn device of claim 1 , wherein the NNE circuitry is configured to process a digitized version of the incoming audio signal with an associated power consumption of about 2 milliwatts or less.
6 . The ear-worn device of claim 1 , wherein the NNE circuitry is implemented on a single chip in the ear-worn device.
7 . The ear-worn device of claim 1 , wherein the NNE circuitry and the DSP circuitry are implemented on a system-on-chip.
8 . The ear-worn device of claim 1 , wherein the NNE circuitry is configured to provide supportive computation to the DSP circuitry.