Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network
This work addresses a specific bottleneck in audio and speech processing for improving synthetic speech quality, representing an incremental advancement.
The paper tackles the problem of unnatural artifacts in synthetic speech caused by the Griffin-Lim method for phase reconstruction from amplitude spectrograms, and it introduces a von-Mises-distribution deep neural network with a group-delay loss, achieving better speech quality than the conventional method.
This paper presents a deep neural network (DNN)-based phase reconstruction from amplitude spectrograms. In audio signal and speech processing, the amplitude spectrogram is often used for processing, and the corresponding phase spectrogram is reconstructed from the amplitude spectrogram on the basis of the Griffin-Lim method. However, the Griffin-Lim method causes unnatural artifacts in synthetic speech. Addressing this problem, we introduce the von-Mises-distribution DNN for phase reconstruction. The DNN is a generative model having the von Mises distribution that can model distributions of a periodic variable such as a phase, and the model parameters of the DNN are estimated on the basis of the maximum likelihood criterion. Furthermore, we propose a group-delay loss for DNN training to make the predicted group delay close to a natural group delay. The experimental results demonstrate that 1) the trained DNN can predict group delay accurately more than phases themselves, and 2) our phase reconstruction methods achieve better speech quality than the conventional Griffin-Lim method.