Phase reconstruction based on recurrent phase unwrapping with deep neural networks
This work addresses a specific challenge in audio synthesis and signal processing for researchers and practitioners, representing an incremental improvement over existing DNN-based methods.
The paper tackled the problem of phase reconstruction from amplitude spectrograms in acoustical signal processing by proposing a two-stage deep neural network method that estimates phase derivatives to avoid sensitivity to waveform shifts, and it outperformed direct phase estimation.
Phase reconstruction, which estimates phase from a given amplitude spectrogram, is an active research field in acoustical signal processing with many applications including audio synthesis. To take advantage of rich knowledge from data, several studies presented deep neural network (DNN)--based phase reconstruction methods. However, the training of a DNN for phase reconstruction is not an easy task because phase is sensitive to the shift of a waveform. To overcome this problem, we propose a DNN-based two-stage phase reconstruction method. In the proposed method, DNNs estimate phase derivatives instead of phase itself, which allows us to avoid the sensitivity problem. Then, phase is recursively estimated based on the estimated derivatives, which is named recurrent phase unwrapping (RPU). The experimental results confirm that the proposed method outperformed the direct phase estimation by a DNN.