相关论文: Ambisonics Networks -- The Effect Of Radial Functi…

Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While…

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce spectral batch normalization (SBN), a novel effective method to improve generalization by…

Neural upmixing, the task of generating immersive music with an increased number of channels from fewer input channels, has been an active research area, with mono-to-stereo and stereo-to-surround upmixing treated as separate problems. In…

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by…

For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance. As a matter of fact, in sensitive settings misclassification can lead to dramatic consequences. Such misclassifications are likely…

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Spatial audio signal enhancement aims to reduce interfering source contributions while preserving the desired sound field with its spatial cues. Existing methods generally rely on impractical assumptions (e.g. accurate estimations of…

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations,…

This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works…

Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet fully understood. This paper introduces a spherical framework to study the…

Multi-channel speech enhancement extracts speech using multiple microphones that capture spatial cues. Effectively utilizing directional information is key for multi-channel enhancement. Deep learning shows great potential on multi-channel…

This paper presents the 3D soundfield synthesis of the pressure field radiated by directional acoustic sources using both the multimodal method and higher-order ambisonics (HOA). Ambisonics is a technique for encoding and reproducing…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…

To learn and reason in the presence of uncertainty, the brain must be capable of imposing some form of regularization. Here we suggest, through theoretical and computational arguments, that the combination of noise with synchronization…

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly…

Data augmentation methods have shown great importance in diverse supervised learning problems where labeled data is scarce or costly to obtain. For sound event localization and detection (SELD) tasks several augmentation methods have been…

We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by small isotropic normal noise. The addition of such noise may be interpreted as a…

Deep learning has the potential to enhance speech signals and increase their intelligibility for users of hearing aids. Deep models suited for real-world application should feature a low computational complexity and low processing delay of…