Deep-Learning Framework for Efficient Real-Time Speech Enhancement and Dereverberation
Sensors · 22.01.2025 · 25 (3) · 630
DOI: 10.3390/s25030630 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.01.2025. Verfasst von Tomer Rosenbaum und 3 weiteren Autor:innen. Beteiligte Einrichtung: Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion-Israel Institute of Technology, Haifa 3200003, Israel. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israel Science Foundation, Pazy Research Foundation.
Abstract (Originalsprache)
Deep learning has revolutionized speech enhancement, enabling impressive high-quality noise reduction and dereverberation. However, state-of-the-art methods often demand substantial computational resources, hindering their deployment on edge devices and in real-time applications. Computationally efficient approaches like deep filtering and Deep Filter Net offer an attractive alternative by predicting linear filters instead of directly estimating the clean speech. While Deep Filter Net excels in noise reduction, its dereverberation performance remains limited. In this paper, we present a generalized framework for computationally efficient speech enhancement and, based on this framework, identify an inherent constraint within Deep Filter Net that hinders its dereverberation capabilities. We propose an extension to the Deep Filter Net framework designed to overcome this limitation, demonstrating significant improvements in dereverberation performance while maintaining competitive noise-reduction quality. Our experimental results highlight the potential of this enhanced framework for real-time speech enhancement on resource-constrained devices.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion-Israel Institute of Technology, Haifa 3200003, Israel.
- MISTRIX Ltd., Tel Aviv 6492108, Israel.
- Insoundz Ltd., Tel Aviv 6821231, Israel.
ORCID-Profile: Tomer Rosenbaum, Israel Cohen
Förderung
- Israel Science Foundation
- Pazy Research Foundation
Zitieren
APA
Rosenbaum, T., Winebrand, E., Cohen, O., & Cohen, I. (2025). Deep-Learning Framework for Efficient Real-Time Speech Enhancement and Dereverberation. Sensors, 25(3), 630. https://doi.org/10.3390/s25030630
Vancouver
Rosenbaum T, Winebrand E, Cohen O, Cohen I. Deep-Learning Framework for Efficient Real-Time Speech Enhancement and Dereverberation. Sensors. 2025;25(3):630. doi:10.3390/s25030630
BibTeX
@article{Rosenbaum2025,
author = {Rosenbaum, Tomer and Winebrand, Emil and Cohen, Omer and Cohen, Israel},
title = {Deep-Learning Framework for Efficient Real-Time Speech Enhancement and Dereverberation},
journal = {Sensors},
year = {2025},
volume = {25},
number = {3},
pages = {630},
doi = {10.3390/s25030630}
}
EUVIMED