Phase-Aware Audio Super-resolution for Music Signals Using Wasserstein Generative Adversarial Network
Yanqiao Yan, Binh Thien Nguyen, Yuting Geng, Kenta Iwai, Takanobu Nishiura · 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · 2022
Audio super-resolution (ASR) is a complicated task for generating a high-resolution audio signal from a low-resolution signal. To solve this problem, we propose an ASR system for music signals that involves using deep neural networks in the time-frequency domain. The system has two components: a Wasserstein generative adversarial network-based high frequency magnitude generation model and a fully connected network-based corresponding high frequency band phase estimation model. The conventional high frequency band phase estimation methods require large computational complexity, have slow convergence, and reconstruct low quality high-resolution signals. We compare our proposed high frequency band phase estimation model in the ASR system with conventional phase estimation methods. The results show that our proposed phase estimation model outperforms conventional methods in objective evaluations.