Related papers: One to Multiple Mapping Dual Learning: Learning Mu…
Music source separation (MSS) aims to extract 'vocals', 'drums', 'bass' and 'other' tracks from a piece of mixed music. While deep learning methods have shown impressive results, there is a trend toward larger models. In our paper, we…
Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…
Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However,…
Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which…
We address a nonstationary blind source separation (BSS) problem. The model includes both nonstationary sources and mixing. Therefore, we introduce an algorithm for joint BSS and estimation of stationarity-breaking deformations and spectra.…
Blind source separation is one of the major analysis tool to extract relevant information from multichannel data. While being central, joint deconvolution and blind source separation (DBSS) methods are scarce. To that purpose, a DBSS…
While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio…
Recent research showed that the dual-pixel sensor has made great progress in defocus map estimation and image defocus deblurring. However, extracting real-time dual-pixel views is troublesome and complex in algorithm deployment. Moreover,…
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same…
Given a time series of multicomponent measurements x(t), the usual objective of nonlinear blind source separation (BSS) is to find a "source" time series s(t), comprised of statistically independent combinations of the measured components.…
This paper deals with a source separation strategy based on second-order statistics, namely, on data covariance matrices estimated at several lags. In general, ``blind'' approaches to source separation do not assume any knowledge on the…
To advance immersive communication, the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge recently introduced Task 4 on Spatial Semantic Segmentation of Sound Scenes (S5). An S5 system takes a multi-channel…
Several attempts have been made to handle multiple source separation tasks such as speech enhancement, speech separation, sound event separation, music source separation (MSS), or cinematic audio source separation (CASS) with a single…
In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the…
We extend frequency-domain blind source separation based on independent vector analysis to the case where there are more microphones than sources. The signal is modelled as non-Gaussian sources in a Gaussian background. The proposed…
Propelled by the breakthrough in deep generative models, audio-to-image generation has emerged as a pivotal cross-modal task that converts complex auditory signals into rich visual representations. However, previous works only focus on…
Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. Two major difficulties in such systems are the arbitrary source…
A multi-modal machine learning system uses multiple unique data sources and types to improve its performance. This article proposes a system that combines results from several types of models, all of which are trained on different data…
Whether listening to overlapping conversations in a crowded room or recording the simultaneous electrical activity of millions of neurons, the natural world abounds with sparse measurements of complex overlapping signals that arise from…
The problem of broadcasting a pair of correlated Gaussian sources using optimal separate source and channel codes is studied. Considerable performance gains over previously known separate source-channel schemes are observed. Although…