Neuro-Fuzzy Voice Quality Improvement for Low-Power, Half-Duplex, Communication
- 15 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 3609-3622
Abstract
Half-duplex mobile radio systems are commonly used for speech communication, often in challenging environments where background noise may prevent speech intelligibility. These systems usually operate with modest battery capacity which strictly limits the available computational power. In this paper, we present a noise suppression approach that uses lightweight machine learning. The machine learning leverages a neuro-fuzzy logic-based neural network to create accurate noise estimation that is used adaptively to create a filter for noise reduction. The system buffers a number of noise samples, triggered by the half-duplex key press, allowing the solution to adapt to recent changes in the background auditory noise. The selection of a neuro-fuzzy logic-based neural network is driven by the necessity for a low-power implementation suitable for mobile, power-constrained terminals. The proposed system is compared with both traditional noise suppression methods as well as with a deep convolutional neural network (DCNN) variant of our system. The results demonstrate that our system significantly outperforms traditional methods in terms of both subjective and objective quality metrics. Further, they show that, although the DCNN variant achieves comparable performance, it has a high computational cost which renders it unsuitable for low-power digital personal radio systems. To validate its practicality, the proposed method is tested in a real-time system, demonstrating its compatibility with constrained devices.Keywords
Funding Information
- Innovate U.K. through Knowledge Transfer Partnership (012507)
This publication has 46 references indexed in Scilit:
- State-of-the-Art Analysis of Deep Learning-Based Monaural Speech Source Separation TechniquesIEEE Access, 2023
- Single-channel speech enhancement using implicit Wiener filter for high-quality speech communicationInternational Journal of Speech Technology, 2022
- A Novel Voice Activity Detection for Multi-Channel Noise ReductionIEEE Access, 2021
- A review of supervised learning algorithms for single channel speech enhancementInternational Journal of Speech Technology, 2019
- Adaptive network based fuzzy inference system (ANFIS) training approaches: a comprehensive surveyArtificial Intelligence Review, 2018
- Adaptive Neuro-Fuzzy Inference System: Overview, Strengths, Limitations, and Solutions2017
- Designing and modeling of ultra low voltage and ultra low power LNA using ANN and ANFIS for Bluetooth applicationsNeurocomputing, 2013
- An Improved Multi-Band Spectral Subtraction Algorithm for Enhancing Speech in Various Noise EnvironmentsProcedia Engineering, 2013
- Noise power spectral density estimation based on optimal smoothing and minimum statisticsIEEE Transactions on Speech and Audio Processing, 2001
- GSC-based spatial voice activity detection for enhanced speech coding in the presence of competing speechIEEE Transactions on Speech and Audio Processing, 2001