.png){kind=icon}
.png){kind=icon}
Return
Multitude Active Noise cancellation using White Shark Optimized Deep Learning Network
.png){kind=icon}
PRE
AI
DOI：10.33180/InfMIDEM2026.411.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Active noise cancellation (ANC) is an essential feature of audio equipment that reduces unwanted background noise. Unwanted signals in information bearing-signal referred to as noise, could degrade the strength of signals in terms of intelligibility and quality. Over the decade, various researchers developed different algorithms to enhance speech signal quality and for noise reduction. To address the issue, a Multitude Active Noise cancellation using White Shark Optimized Convolutional neural network-Long short-term memory Network (MANC Net) has been proposed. Initially, Dual Tree Complex Wavelet Transform (DTCWT) is utilized to enhance the quality of audio signal with a multitude noise and the signal features are extracted using a community detection based Genetic Algorithm. Afterward based on extracted signal, interference and desired signals are classified using Hybrid Convolutional neural network-Long short-term memory (CNN-LSTM). Additionally, the hyperparameters of CNN-LSTM are tuned using White Shark Optimization (WSO) for better accuracy. The efficiency of the proposed method is evaluated using accuracy, specificity, sensitivity, Normalized Mean Squared Error (NMSE), Short-Time Objective Intelligibility (STOI), and Perceptual Evaluation of Speech Quality (PESQ) parameter values in comparison with other conventional methods. The higher accuracy rate and low NMSE in the classification of audio signals evidenced the efficacy of the proposed MANC Net model. The overall accuracy of the proposed is 9.1%, 8.7%, 7.9%, 3.4%, and 1.5% better than Filtered-X Least Mean Square (FxLMS), deep Active Noise Cancellation (deep ANC), Construction Site Noise Network (CsNNet), Multi-Channel Active Noise Cancellation (MCANC), and Generative fixed-Filter Active Noise Control (GFANC), respectively.
Keywords:
Active noise Cancellation
Multitude noise
Deep learning
Optimization
Journal
I
IF:
0.8
Papers:
14
Citations:
171