Related papers: Audio signal interpolation using optimal transport…

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed…

Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity…

Experimental aeroacoustics is concerned with the estimation of acoustic source power distributions, which are for instance caused by fluid structure interactions on scaled aircraft models inside a wind tunnel, from microphone array…

In this study, methodology of acoustic emission source localization in composite materials based on artificial intelligence was presented. Carbon fiber reinforced plastic was selected for specimen, and acoustic emission signal were measured…

We consider the reconstruction of optical parameters in a domain of interest from photoacoustic data. Photoacoustic tomography (PAT) radiates high frequency electromagnetic waves into the domain and measures acoustic signals emitted by the…

In this work, we propose a novel data augmentation method for clinical audio datasets based on a conditional Wasserstein Generative Adversarial Network with Gradient Penalty (cWGAN-GP), operating on log-mel spectrograms. To validate our…

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

Efficient time integration methods based on operator splitting are introduced for the Westervelt equation, a nonlinear damped wave equation that arises in nonlinear acoustics as mathematical model for the propagation of sound waves in high…

In this paper, we introduce a variant of optimal transport adapted to the causal structure given by an underlying directed graph $G$. Different graph structures lead to different specifications of the optimal transport problem. For…

We propose a novel concept of nonreciprocal devices in acoustics, illustrated by the design of an acoustic diode, or isolator. A boundary control strategy was previously shown to provide direction-dependent propagation properties in…

We present a single-stage casual waveform-to-waveform multichannel model that can separate moving sound sources based on their broad spatial locations in a dynamic acoustic scene. We divide the scene into two spatial regions containing,…

We address the challenge of making spatial audio datasets by proposing a shared mechanized recording space that can run custom acoustic experiments: a Mechatronic Acoustic Research System (MARS). To accommodate a wide variety of…

We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to…

Computing the Wasserstein barycenter of a set of probability measures under the optimal transport metric can quickly become prohibitive for traditional second-order algorithms, such as interior-point methods, as the support size of the…

Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate…

This paper presents a Wasserstein attraction approach for solving dynamic mass transport problems over networks. In the transport problem over networks, we start with a distribution over the set of nodes that needs to be "transported" to a…

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…

The ability to create linear systems that manifest broadband nonreciprocal wave propagation would provide for exquisite control over acoustic signals for electronic filtering in communication and noise control. Until now, acoustic…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…