Abstract: |
A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility. |
Inventor: |
Xu, Buye (Minnetonka, MN, US); Merks, Ivo (Eden Prairie, MN, US); Mustiere, Frederic Philippe Denis (Chaska, MN, US) |
Applicant: |
Starkey Laboratories, Inc. (Eden Prairie, MN, US) |
Face Assignee: |
Starkey Laboratories, Inc. (Eden Prairie, MN, US) |
Filed: |
2016-04-06 |
Issued: |
2019-11-26 |
Claims: |
20 |
|
US10492008
|
1. A hearing system, comprising:
(2)
(4)
|
|
7. A hearing system configured to be worn by a wearer, comprising:
(3)
(5)
|
|
11. A method for operating a hearing system, comprising:
(5)
(4)
|
|