Impact of Mask Type as Training Target for Speech Intelligibility and Quality in Cochlear-Implant Noise Reduction
Sensors · 2024
DOI: 10.3390/s24206614 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Fergal Henry und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computing and Electronic Engineering, Atlantic Technological University, Ash Lane, F91YW50 Sligo, Ireland. Hauptthemen laut MEDLINE: Cochlear Implants, Speech Intelligibility, Signal-To-Noise Ratio, Noise. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Southern and Eastern Regional Operational Programme to Lero-The Science Foundation Ireland Research Centre for Software, Science Foundation Ireland.
Abstract (Originalsprache)
The selection of a target when training deep neural networks for speech enhancement is an important consideration. Different masks have been shown to exhibit different performance characteristics depending on the application and the conditions. This paper presents a comprehensive comparison of several different masks for noise reduction in cochlear implants. The study incorporated three well-known masks, namely the Ideal Binary Mask (IBM), Ideal Ratio Mask (IRM) and the Fast Fourier Transform Mask (FFTM), as well as two newly proposed masks, based on existing masks, called the Quantized Mask (QM) and the Phase-Sensitive plus Ideal Ratio Mask (PSM+). These five masks are used to train networks to estimate masks for the purpose of separating speech from noisy mixtures. A vocoder was used to simulate the behavior of a cochlear implant. Short-time Objective Intelligibility (STOI) and Perceptual Evaluation of Speech Quality (PESQ) scores indicate that the two new masks proposed in this study (QM and PSM+) perform best for normal speech intelligibility and quality in the presence of stationary and non-stationary noise over a range of signal-to-noise ratios (SNRs). The Normalized Covariance Measure (NCM) and similarity scores indicate that they also perform best for speech intelligibility/gauging the similarity of vocoded speech. The Quantized Mask performs better than the Ideal Binary Mask due to its better resolution as it approximates the Wiener Gain Function. The PSM+ performs better than the three existing benchmark masks (IBM, IRM, and FFTM) as it incorporates both magnitude and phase information.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computing and Electronic Engineering, Atlantic Technological University, Ash Lane, F91YW50 Sligo, Ireland.
- Electrical and Electronic Engineering, University of Galway, University Road, H91TK33 Galway, Ireland.
ORCID-Profile: Fergal Henry, Martin Glavin, Ashkan Parsi
Förderung
- Southern and Eastern Regional Operational Programme to Lero-The Science Foundation Ireland Research Centre for Software
- Science Foundation Ireland
Zitieren
APA
Henry, F., Glavin, M., Jones, E., & Parsi, A. (2024). Impact of Mask Type as Training Target for Speech Intelligibility and Quality in Cochlear-Implant Noise Reduction. Sensors. https://doi.org/10.3390/s24206614
Vancouver
Henry F, Glavin M, Jones E, Parsi A. Impact of Mask Type as Training Target for Speech Intelligibility and Quality in Cochlear-Implant Noise Reduction. Sensors. 2024. doi:10.3390/s24206614
BibTeX
@article{Henry2024,
author = {Henry, Fergal and Glavin, Martin and Jones, Edward and Parsi, Ashkan},
title = {Impact of Mask Type as Training Target for Speech Intelligibility and Quality in Cochlear-Implant Noise Reduction},
journal = {Sensors},
year = {2024},
doi = {10.3390/s24206614}
}
EUVIMED