Edinburgh Napier University

  Since the advent of deep learning (DL), speech enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic artefacts, sound unnatural, and restrict the ability for a user to hear ambient sound which may be of importance. Hearing Aid (HA) users may wish to customise their SE systems to suit their personal preferences and day-to-day lifestyle. In this paper, we introduce a preference learning based SE (PLSE) model for future multi-modal HAs that can contextually exploit audio and visual information to improve listening comfort (LC). The proposed system estimates the Signal-to-noise ratio (SNR) as a basic objective speech quality measure which quantifies the relative amount of background noise present in speech, and directly correlates to the intelligibility of the signal. This is used alongside a preference elicitation framework which learns a predictive function to determine the target SNR. The system is novel, scaling the output of an AudioVisual (AV) DL-based SE model to provide HA users with individualised SE. Preliminary results support the hypothesis of improving the overall subjective LC, without significantly impeding the speech intelligibility.