A Phase Aware Audio Declipping Method Using Band Split Recurrent Neural Network in Heavily Noisy Environments

In digital audio systems, clipping occurs when the amplitude of a signal exceeds a threshold, leading to signal distortion and unpleasant noise to the listener. Therefore, a declipping process is required to recover the clipped portion and reconstruct the signal. In conventional deep neural network-based audio enhancement methods, the focus has primarily been on restoring the magnitude spectrum, but recent studies indicate that enhancing the phase spectrum is also crucial for improving quality. In this paper, we propose an audio declipping method based on the BSRNN(band-split recurrent neural network) that utilizes phase-based features such as instantaneous frequency deviation (IFD), or applies the neural vocoder HiFi-GAN (generative adversarial network for efficient and high-fidelity speech synthesis) in the post-processing stage to improve the objective quality of signal. The experimental results show that the proposed method outperforms the conventional magnitude spectrum-based enhancement method and the DCCRN model-based declipping method according to DNSMOS P.835 OVRL score.