Skip to main content

Research Repository

Advanced Search

Towards individualised speech enhancement: An SNR preference learning system for multi-modal hearing aids

Kirton-Wingate, Jasper; Ahmed, Shafique; Gogate, Mandar; Tsao, Yu; Hussain, Amir


Shafique Ahmed

Yu Tsao



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.

Presentation Conference Type Conference Paper (Published)
Conference Name 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)
Start Date Jun 4, 2023
End Date Jun 10, 2023
Acceptance Date Apr 15, 2023
Online Publication Date Jun 4, 2023
Publication Date 2023
Deposit Date Jan 22, 2024
Publisher Institute of Electrical and Electronics Engineers
Book Title Proceedings of the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)
ISBN 9798350302622
Public URL
Publisher URL

You might also like

Downloadable Citations