This paper proposes an approach to the joint modeling of the short-time Fourier transform
magnitude and phase spectrograms with a deep generative model. We assume that the …

This paper presents a deep neural network (DNN)-based phase reconstruction from
amplitude spectrograms. In audio signal and speech processing, the amplitude spectrogram …

This paper proposes a new loss using short-time Fourier transform (STFT) spectra for the
aim of training a high-performance neural speech waveform model that predicts raw …

In this paper, we address the problem of reconstructing a time-domain signal (or a phase
spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not …

In this paper we propose a fully convolutional neural network (CNN) for complex
spectrogram processing in speech enhancement. The proposed CNN consists of one …

We propose a learning-based postfilter to reconstruct the high-fidelity spectral texture in
short-term Fourier transform (STFT) spectrograms. In speech-processing systems, such as …

Recently, several papers have demonstrated that neural networks (NN) are able to perform
the feature extraction as part of the acoustic model. Motivated by the Gammatone feature …

This paper reports our recent exploration of the layer-by-layer learning strategy for training a
multi-layer generative model of patches of speech spectrograms. The top layer of the …

In this paper, we investigate multi-stream acoustic modelling using the raw real and
imaginary parts of the Fourier transform of speech signals. Using the raw magnitude …

Magnitude spectrum-based features are the most widely employed front-ends for acoustic
modelling in automatic speech recognition (ASR) systems. In this paper, we investigate the …