Deep Learning-Based Speech Enhancement of an Extrinsic Fabry–Perot Interferometric Fiber Acoustic Sensor System
Sensors · 29.03.2023 · 23 (7) · 3574
DOI: 10.3390/s23073574 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2023. Verfasst von Shiyi Chai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Science, Hubei University of Technology, Wuhan 430068, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department of Hubei Province, outstanding young and middle-aged science and technology innovation teams of colleges and universities in Hubei province, International Science and Technology Cooperation Key Research and Development Program of Science and Technology Agency in Hubei Province.
Abstract (Originalsprache)
To achieve high-quality voice communication technology without noise interference in flammable, explosive and strong electromagnetic environments, the speech enhancement technology of a fiber-optic external Fabry–Perot interferometric (EFPI) acoustic sensor based on deep learning is studied in this paper. The combination of a complex-valued convolutional neural network and a long short-term memory (CV-CNN-LSTM) model is proposed for speech enhancement in the EFPI acoustic sensing system. Moreover, the 3 × 3 coupler algorithm is used to demodulate voice signals. Then, the short-time Fourier transform (STFT) spectrogram features of voice signals are divided into a training set and a test set. The training set is input into the established CV-CNN-LSTM model for model training, and the test set is input into the trained model for testing. The experimental findings reveal that the proposed CV-CNN-LSTM model demonstrates exceptional speech enhancement performance, boasting an average Perceptual Evaluation of Speech Quality (PESQ) score of 3.148. In comparison to the CV-CNN and CV-LSTM models, this innovative model achieves a remarkable PESQ score improvement of 9.7% and 11.4%, respectively. Furthermore, the average Short-Time Objective Intelligibility (STOI) score witnesses significant enhancements of 4.04 and 2.83 when contrasted with the CV-CNN and CV-LSTM models, respectively.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Science, Hubei University of Technology, Wuhan 430068, China.
- Hubei Engineering Technology Research Center of Energy Photoelectric Device and System, Hubei University of Technology, Wuhan 430068, China.
Förderung
- Science and Technology Department of Hubei Province
- outstanding young and middle-aged science and technology innovation teams of colleges and universities in Hubei province
- International Science and Technology Cooperation Key Research and Development Program of Science and Technology Agency in Hubei Province
Zitieren
APA
Chai, S., Guo, C., Guan, C., & Fang, L. (2023). Deep Learning-Based Speech Enhancement of an Extrinsic Fabry–Perot Interferometric Fiber Acoustic Sensor System. Sensors, 23(7), 3574. https://doi.org/10.3390/s23073574
Vancouver
Chai S, Guo C, Guan C, Fang L. Deep Learning-Based Speech Enhancement of an Extrinsic Fabry–Perot Interferometric Fiber Acoustic Sensor System. Sensors. 2023;23(7):3574. doi:10.3390/s23073574
BibTeX
@article{Chai2023,
author = {Chai, Shiyi and Guo, Can and Guan, Chenggang and Fang, Li},
title = {Deep Learning-Based Speech Enhancement of an Extrinsic Fabry–Perot Interferometric Fiber Acoustic Sensor System},
journal = {Sensors},
year = {2023},
volume = {23},
number = {7},
pages = {3574},
doi = {10.3390/s23073574}
}
EUVIMED