A hearing device includes: an input module for provision of an input signal; a time domain filter configured to perform filtering to provide a filter output signal based on the input signal; a processor configured to provide an electrical output signal based on the filter output signal, the processor configured to compensate for hearing loss of a user of the hearing device; a receiver configured to provide an audio output signal based on the electrical output signal; and a controller comprising a machine learning model for provision of a model output based on the input signal, wherein the controller is configured to: determine a first gain based on the model output; determine a filter control signal based on the first gain; and provide the filter control signal to the time domain filter for filtering the input signal based on the filter control signal.