Abstract
This paper introduces a speech enhancement algorithm for hearing assistive devices, e.g., hearing aids, connected to a remote microphone. Remote microphones are especially beneficial to hearing aid users when they are present in environments with low signal-to-noise ratios. The transmission of the acoustic data from the remote microphone to the hearing aid unit, however, happens through a wireless channel that is prone to network delays. Such delays, that occur in any real-world application, make the remote microphone signal less valuable, in contrast to when the transmission is assumed to be error-free and instantaneous, as is often done in the literature. To make use of the remote microphone signal, despite the delay, we propose an estimator selection method that selects between the minimum mean-square error estimate of the desired signal, made using the hearing aid signals and the delayed remote microphone signal, respectively. This binary selection is made by comparing the normalized mean-square errors of the two desired signal estimates. We show that the proposed method provides a benefit in estimated speech intelligibility, for delays in transmission up to 30 ms at a signal-to-noise ratio of 0 dB, in comparison to the minimum mean-square error estimate made using only the hearing aid microphone signals.
Originalsprog | Engelsk |
---|---|
Titel | 2023 8th International Conference on Frontiers of Signal Processing (ICFSP 2023) |
Antal sider | 5 |
Forlag | IEEE (Institute of Electrical and Electronics Engineers) |
Publikationsdato | 2023 |
Sider | 38-42 |
Artikelnummer | 10372902 |
ISBN (Trykt) | 979-8-3503-0880-8 |
ISBN (Elektronisk) | 979-8-3503-0879-2, 979-8-3503-0878-5 |
DOI | |
Status | Udgivet - 2023 |
Begivenhed | 2023 8th International Conference on Frontiers of Signal Processing (ICFSP) - Corfu, Grækenland Varighed: 23 okt. 2023 → 25 okt. 2023 |
Konference
Konference | 2023 8th International Conference on Frontiers of Signal Processing (ICFSP) |
---|---|
Land/Område | Grækenland |
By | Corfu |
Periode | 23/10/2023 → 25/10/2023 |