Sonova Ag

Sebastian Stenzel

Amre El-Hoiydi

Hilmar Meier

Harald Krueger

Evert Dijkstra

Claudio Santelli

Sebastian Kroedel

Christos Dimopoulos

System and methods are presented for detecting an authentic copy of a deep neural network in a device without reverse engineering the device. For example, the device can be a hearing device. A method is presented that includes providing audio signals to a deep neural network located in a hearing device, receiving signals from the deep neural network that are triggered by the transmitted audio signals, and determining whether the received signals were the expected signals. Specifically, the system can determine that an unauthorized entity embedded an unauthorized copy of the deep neural network in a hearing device.

System and methods for detecting a copy of a deep neural network in a hearing device

Provided is an audio transmission method between at least two audio communication systems including a transmitting audio communication system with first and second audio transmitting devices and a receiving audio communication system with at least one audio receiving device. The method includes transmitting a first wireless audio stream, via a first wireless audio link, by the first audio transmitting device and a second wireless audio stream, via a second wireless audio link, by the second audio transmitting device; and selecting, by the at least one audio receiving device, one of the first wireless audio stream or the second wireless audio stream based on quality parameters of the first audio link and the second wireless audio link.

Dual wireless audio streams transmission allowing for spatial diversity or own voice pickup (OVPU)

Growing community of inventors

Stafa, Switzerland

Sebastian Stenzel