InSE-NET: A Perceptually Coded Audio Quality Model based on CNN

Abstract

Automatic coded audio quality assessment is an important task whose progress is hampered by the scarcity of human annotations, poor generalization to unseen codecs, bitrates, content-types, and a lack of flexibility of existing approaches. One of the typical human-perception-related metrics, ViSQOL v3 (ViV3), has been proven to provide a high correlation to the quality scores rated by humans. In this study, we take steps to tackle problems of predicting coded audio quality by completely utilizing programmatically generated data that is informed with expert domain knowledge. We propose a learnable neural network, entitled InSE-NET, with a backbone of Inception and Squeeze-and-Excitation modules to assess the perceived quality of coded audio at a 48kHz sample rate. We demonstrate that synthetic data augmentation is capable of enhancing the prediction. Our proposed method is intrusive, i.e. it requires Gammatone spectrograms of unencoded reference signals. Besides a comparable performance to ViV3, our approach provides a more robust prediction towards higher bitrates.

arXiv commentAccepted to 151st Audio Engineering Society (AES), Las Vegas, NV, USA, October 2021

References in corpus (4)

• Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Quality
• Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks
• Can we still use PEAQ? A Performance Analysis of the ITU Standard for the Objective Assessment of Perceived Audio Quality
• Deep Learning-Based Single-Ended Objective Quality Measures for Time-Scale Modified Audio