Mitigating Information Interruptions by COVID-19 Face Masks: A Three-Stage Speech Enhancement Scheme

• Published in: IEEE transactions on computational social systems Vol. 11; no. 4; pp. 4790 - 4799
• Main Authors: Dash, Tusar Kanti, Chakraborty, Chinmay, Mahapatra, Satyajit, Panda, Ganapati
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Coronavirus disease 2019 (COVID-19); Coronaviruses; COVID-19; face mask; Face recognition; Faces; Feature extraction; Frequencies; gray wolf optimizer (GWO); information interruptions; Masks; Neural networks; Noise measurement; Parameter modification; Q-factor; Radial basis function; Signal quality; Signal to noise ratio; Speech; Speech enhancement; speech enhancement (SE); Speech processing; Speech recognition; Subtraction; tunable Q-factor wavelet transform (TQWT); Viral diseases; Voice communication; Wavelet transforms
• ISSN: 2329-924X; 2373-7476
• DOI: 10.1109/TCSS.2022.3210988

The coronavirus disease 2019 (COVID-19) preventive measures have resulted in significant lifestyle changes. One of the COVID-19 new normal is the usage of face masks for protection against airborne aerosol which creates distractions and interruptions in voice communication. It has a different influence on speech than the standard concept of noise affecting speech communication. Furthermore, it has varied effects on speech in different frequency bands. To provide a solution to this problem, a three-stage adaptive speech enhancement (SE) scheme is developed in this article. In the first stage, the tunable <inline-formula> <tex-math notation="LaTeX">Q </tex-math></inline-formula>-factor wavelet transform (TQWT) features are extracted by properly setting the quality factor values and the number of levels from the input speech signal. In the second stage, the adjustable parameters of the preemphasis filter and modified multiband spectral subtraction (MBSS) are determined using bio-inspired techniques for different masking and signal-to-noise ratio (SNR) conditions. In the third stage, the weights, center values, standard deviation of the Gaussian radial basis functions, and input patterns of the radial basis function neural networks (RBFNNs) are updated to predict the optimized parameters from the input TQWT-based cepstral features (TQCFs). In the end, the performance of the proposed algorithm is compared with the standard SE algorithms using two speech datasets.