Multilayered convolutional neural network-based auto-CODEC for audio signal denoising using mel-frequency cepstral coefficients

The denoising of audio signal and quality enhancement has a substantial contribution in speaker identification, audio transmission, hearing aids, microphones, mobile phones, etc., Hence, an efficient denoising method is required to enhance the audio signal quality securely. A robust multilayered convolutional neural network (MLCNN)-based auto-CODEC for audio signal denoising which is utilizing the mel-frequency cepstral coefficients (MFCCs) has been proposed in this research. The MLCNN takes the input as MFCC with different frames from the noise-contaminated audio signal for training and testing. The proposed MLCNN model has been trained and tested as 80:20 ratios for the available MIT database. After the training, the proposed method has been validated. From the validation, it has been found that the proposed MLCNN model provides an accuracy of 93.25%. The performance of MLCNN has been evaluated and compared with the reported methods using short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ) and cosine similarities. From the performance comparisons, it has been found that the proposed MLCNN model outperforms other models. From the cosine similarity, it has been proved that MLCNN provides high security level which can be used for many secure applications.