Audio signal quality enhancement using multi-layered convolutional neural network based auto encoder–decoder

Abstract

In this research article, a multi-layered convolutional neural network (MLCNN) based auto-CODEC for audio signal enhancement which is utilizing the Mel-frequency cepstral coefficients (MFCC) has been proposed. The proposed MLCNN takes the input as MFCC with different frames from the noise contaminated audio signal for training and testing. The proposed MLCNN models has been trained and tested as 80:20 and 70:30 ratios from the available database. The proposed method has been verified and validated MNIST database. 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 using short-time objective intelligibility, perceptual evaluation of speech quality and Cosine similarities. The proposed MLCNN model has been compared with the reported models. Form the comparisons; it has been observed 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.