The role of window length and shift in complex-domain DNN-based speech enhancement

Abstract

Deep learning techniques have widely been applied to speech enhancement as they show outstanding modeling capa- bilities that are needed for proper speech-noise separation. In contrast to other end-to-end approaches, masking-based meth- ods consider speech spectra as input to the deep neural network, providing spectral masks for noise removal or attenuation. In these approaches, the Short-Time Fourier Transform (STFT) and, particularly, the parameters used for the analysis/synthesis window, plays an important role which is often neglected. In this paper, we analyze the effects of window length and shift on a complex-domain convolutional-recurrent neural network (DCCRN) which is able to provide, separately, magnitude and phase corrections. Different perceptual quality and intelligibil- ity objective metrics are used to assess its performance. As a re- sult, we have observed that phase corrections have an increased impact with shorter window sizes. Similarly, as window overlap increases, phase takes more relevance than magnitude spectrum in speech enhancement.