Recovering speech intelligibility with deep learning and multiple microphones in noisy-reverberant situations for people using cochlear implants
The Journal of the Acoustical Society of America · 2024
DOI: 10.1121/10.0026218 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2024. Verfasst von Clément Gaultier und 1 weiteren Autor:innen. Beteiligte Einrichtung: Cambridge Hearing Group, Medical Research Council Cognition and Brain Sciences Unit, University of Cambridge, Cambridge, CB2 7EF, United Kingdom. Hauptthemen laut MEDLINE: Cochlear Implants, Speech Intelligibility, Noise, Deep Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council, Fondation Pour l'Audition.
Abstract (Originalsprache)
For cochlear implant (CI) listeners, holding a conversation in noisy and reverberant environments is often challenging. Deep-learning algorithms can potentially mitigate these difficulties by enhancing speech in everyday listening environments. This study compared several deep-learning algorithms with access to one, two unilateral, or six bilateral microphones that were trained to recover speech signals by jointly removing noise and reverberation. The noisy-reverberant speech and an ideal noise reduction algorithm served as lower and upper references, respectively. Objective signal metrics were compared with results from two listening tests, including 15 typical hearing listeners with CI simulations and 12 CI listeners. Large and statistically significant improvements in speech reception thresholds of 7.4 and 10.3 dB were found for the multi-microphone algorithms. For the single-microphone algorithm, there was an improvement of 2.3 dB but only for the CI listener group. The objective signal metrics correctly predicted the rank order of results for CI listeners, and there was an overall agreement for most effects and variances between results for CI simulations and CI listeners. These algorithms hold promise to improve speech intelligibility for CI listeners in environments with noise and reverberation and benefit from a boost in performance when using features extracted from multiple microphones.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Cambridge Hearing Group, Medical Research Council Cognition and Brain Sciences Unit, University of Cambridge, Cambridge, CB2 7EF, United Kingdom.
ORCID-Profile: Clément Gaultier, Tobias Goehring
Förderung
- Medical Research Council
- Fondation Pour l'Audition
Zitieren
APA
Gaultier, C., & Goehring, T. (2024). Recovering speech intelligibility with deep learning and multiple microphones in noisy-reverberant situations for people using cochlear implants. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0026218
Vancouver
Gaultier C, Goehring T. Recovering speech intelligibility with deep learning and multiple microphones in noisy-reverberant situations for people using cochlear implants. The Journal of the Acoustical Society of America. 2024. doi:10.1121/10.0026218
BibTeX
@article{Gaultier2024,
author = {Gaultier, Clément and Goehring, Tobias},
title = {Recovering speech intelligibility with deep learning and multiple microphones in noisy-reverberant situations for people using cochlear implants},
journal = {The Journal of the Acoustical Society of America},
year = {2024},
doi = {10.1121/10.0026218}
}
EUVIMED