20240056746. HEARING LOSS AMPLIFICATION THAT AMPLIFIES SPEECH AND NOISE SUBSIGNALS DIFFERENTLY simplified abstract (Chromatic Inc.)
HEARING LOSS AMPLIFICATION THAT AMPLIFIES SPEECH AND NOISE SUBSIGNALS DIFFERENTLY
Organization Name
Inventor(s)
Nicholas Morris of Brooklyn NY (US)
Igor Lovchinsky of New York NY (US)
Andrew J. Casper of Clinton CT (US)
HEARING LOSS AMPLIFICATION THAT AMPLIFIES SPEECH AND NOISE SUBSIGNALS DIFFERENTLY - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240056746 titled 'HEARING LOSS AMPLIFICATION THAT AMPLIFIES SPEECH AND NOISE SUBSIGNALS DIFFERENTLY
Simplified Explanation
The abstract describes a hearing aid that uses neural network circuitry to separate speech and noise from an audio signal. It also includes digital processing circuitry with separate pipelines for speech and noise wide dynamic range compression (WDRC). The speech WDRC applies fitting curves to the speech subsignal based on its level, while the noise WDRC applies fitting curves to the noise subsignal based on its level. The fitting curves for speech and noise are different.
- The hearing aid uses neural network circuitry to separate speech and noise from an audio signal.
- It includes separate pipelines for speech and noise wide dynamic range compression (WDRC).
- The speech WDRC applies fitting curves to the speech subsignal based on its level.
- The noise WDRC applies fitting curves to the noise subsignal based on its level.
- The fitting curves for speech and noise are different.
Potential applications of this technology:
- Hearing aids and assistive listening devices
- Communication devices for individuals with hearing impairments
- Noise cancellation systems
Problems solved by this technology:
- Difficulty in separating speech from background noise in audio signals
- Ineffective noise reduction in hearing aids and communication devices
Benefits of this technology:
- Improved speech intelligibility in noisy environments
- Enhanced listening experience for individuals with hearing impairments
- Better communication and understanding in noisy situations
Original Abstract Submitted
a hearing aid includes neural network circuitry configured to implement a neural network trained to separate a speech subsignal and a noise subsignal from an input audio signal, and digital processing circuitry. the digital processing circuitry includes a speech wide dynamic range compression (wdrc) pipeline and a noise wdrc pipeline. the speech wdrc pipeline is configured to apply a set of speech fitting curves to the speech subsignal based at least in part on the level of the speech subsignal. the noise wdrc pipeline is configured to apply a set of noise fitting curves to the noise subsignal based at least in part on the level of the noise subsignal. the set of speech fitting curves is different from the set of noise fitting curves.
