Sonova Ag

Claudio Santelli

Paul Anthony Wagner

Manuela Feilner

Harald Krueger

Markus Hofbauer

Sebastian Stenzel

Harald Kruger

Sebastian Kroedel

Christos Dimopoulos

Anahi Balbi

Manon Barbier

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

Methods, hearing systems and neural networks for audio signal processing are described. A hearing system comprises a neural network. An input audio signal is processed into an output audio signal at least partially by means of a processing unit of the hearing system. The audio signal processing of the input audio signal includes executing audio signal processing by the neural network for performing a step of the audio signal processing, determining a confidence parameter resembling the reliability of the audio signal processing by the neural network and steering the audio signal processing in dependence of the confidence parameter. A particularly suitable neural network is configured to solve a regression-based acoustic processing task and additionally determining the confidence parameter.

Method for audio signal processing on a hearing system, hearing system and neural network for audio signal processing

Systems and methods for controlling hearing devices are disclosed. Each hearing device is worn by a user, the users of the hearing devices having a conversation and the hearing devices being communicatively interconnected with each other for data exchange to form a hearing device system. A method includes acquiring a sound signal of each user with a microphone of the hearing device of the user; acquiring spatial information of each user; determining conversation patterns from the spatial information acquired for all users; determining conversation groups from the conversation patterns; outputting the sound signals from the users with a hearing device, such that sound signals from users of a conversation group that the user of the hearing device is a member of are output to the user and that sound signals from users of conversations groups of which the user is not a member are muted.

Grouping of hearing device users based on spatial sensor input

Growing community of inventors

Staefa, Switzerland

Claudio Santelli