相关论文: STFT spectral loss for training a neural speech wa…

Short-time Fourier transform (STFT) is the most common window-based approach for analyzing the spectrotemporal dynamics of time series. To mitigate the effects of high variance on the spectral estimates due to finite-length, independent…

Recently the study of modeling a non-stationary signal as a superposition of amplitude and frequency-modulated Fourier-like oscillatory modes has been a very active research area. The synchrosqueezing transform (SST) is a powerful method…

Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent…

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation…

This paper presents a novel speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra by neural networks. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

Mainstream deep learning-based dysarthric speech detection approaches typically rely on processing the magnitude spectrum of the short-time Fourier transform of input signals, while ignoring the phase spectrum. Although considerable insight…

We consider the classical 1D phase retrieval problem. In order to overcome the difficulties associated with phase retrieval from measurements of the Fourier magnitude, we treat recovery from the magnitude of the short-time Fourier transform…

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that…

The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which…

We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…

State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…

The problem of recovering a signal from the magnitude of its short-time Fourier transform (STFT) is a longstanding one in audio signal processing. Existing approaches rely on heuristics that often perform poorly because of the nonconvexity…

Currently, most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation, we propose an end-to-end learning method for…

An adaptive time-frequency representation (TFR) with higher energy concentration usually requires higher complexity. Recently, a low-complexity adaptive short-time Fourier transform (ASTFT) based on the chirp rate has been proposed. To…

The diverse perceptual consequences of hearing loss severely impede speech communication, but standard clinical audiometry, which is focused on threshold-based frequency sensitivity, does not adequately capture deficits in frequency and…

Transformers have become central to recent advances in audio classification. However, training an audio spectrogram transformer, e.g. AST, from scratch can be resource and time-intensive. Furthermore, the complexity of transformers heavily…

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

Prediction of late reverberation component using multi-channel linear prediction (MCLP) in short-time Fourier transform (STFT) domain is an effective means to enhance reverberant speech. Traditionally, a speech power spectral density (PSD)…