Related papers: Audio Time-Scale Modification with Temporal Compre…

Temporal envelope morphing, the process of interpolating between the amplitude dynamics of two audio signals, is an emerging problem in generative audio systems that lacks sufficient perceptual grounding. Morphing of temporal envelopes in a…

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that…

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…

Multi-resolution spectro-temporal features of a speech signal represent how the brain perceives sounds by tuning cortical cells to different spectral and temporal modulations. These features produce a higher dimensional representation of…

Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep…

Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…

We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can…

Conformers have shown great results in speech processing due to their ability to capture both local and global interactions. In this work, we utilize a self-supervised contrastive learning framework to train conformer-based encoders that…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Covert speech involves imagining speaking without audible sound or any movements. Decoding covert speech from electroencephalogram (EEG) is challenging due to a limited understanding of neural pronunciation mapping and the low…

Informed speaker extraction aims to extract a target speech signal from a mixture of sources given prior knowledge about the desired speaker. Recent deep learning-based methods leverage a speaker discriminative model that maps a reference…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER). \textcolor{black}{Generally, different emotions correspond…

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that…

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way. Here, we train a convolutional deep neural network to re-synthesize input…

In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved…