A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New method uses Multiple Choice Learning for speech separation.
We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for ev…
Quantizes Stäckel integrable systems into self-adjoint operators.
New graph types help identify complex relationships.
Study reveals structure of local minima in GMMs, identifying key cluster centers.
We consider the notion of multiple gap as a finite set of ideals that cannot be separated. We study the different types of such objects that can be found in the Boolean algebra of subsets of the natural numbers modulo finite sets.
We consider an online version of the robust Principle Component Analysis (PCA), which arises naturally in time-varying source separations such as video foreground-background separation. This paper proposes a compressive online robust PCA with prior information for recursively separating a sequences of frames into spars…
The Allen-Cahn system on manifolds yields multiple phase distributions.
Optimal joint separation condition for radar and communications channels in dual-blind deconvolution.
Singing voice separation attempts to separate the vocal and instrumental parts of a music recording, which is a fundamental problem in music information retrieval. Recent work on singing voice separation has shown that the low-rank representation and informed separation approaches are both able to improve separation qu…
Blind single-channel source separation is a long standing signal processing challenge. Many methods were proposed to solve this task utilizing multiple signal priors such as low rank, sparsity, temporal continuity etc. The recent advance of generative adversarial models presented new opportunities in signal regression …
Paper separates financial time series into fast and slow components.
AutoClip automatically adjusts gradient clipping for better audio separation.
The study investigates noise effects on parameter estimation for Ornstein-Uhlenbeck processes.
A new convex model tackles noisy separable NMF with provable correctness.
Researchers create initial data for multiple collapsing boson stars.
Separating an audio scene such as a cocktail party into constituent, meaningful components is a core task in computer audition. Deep networks are the state-of-the-art approach. They are trained on synthetic mixtures of audio made from isolated sound source recordings so that ground truth for the separation is known. Ho…
The paper extends optimal transport for linear separability of sheared distributions in supervised learning.
We quantify the separation between the numbers of labeled examples required to learn in two settings: Settings with and without the knowledge of the distribution of the unlabeled data. More specifically, we prove a separation by multiplicative factor for the class of projections over the Boolean hypercube o…
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, little is known about its effectiveness in other challenging situations such as mus…
Model learns from multiple data sources for D2T and T2D tasks.
SepIt improves speech separation for multiple speakers.
This work introduces sequential neural beamforming, which alternates between neural network based spectral separation and beamforming based spatial separation. Our neural networks for separation use an advanced convolutional architecture trained with a novel stabilized signal-to-noise ratio loss function. For beamformi…
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…
Monoaural audio source separation is a challenging research area in machine learning. In this area, a mixture containing multiple audio sources is given, and a model is expected to disentangle the mixture into isolated atomic sources. In this paper, we first introduce a challenging new dataset for monoaural source sepa…
Metric learning for classification has been intensively studied over the last decade. The idea is to learn a metric space induced from a normed vector space on which data from different classes are well separated. Different measures of the separation thus lead to various designs of the objective function in the metric …
The paper discusses conditions for gluing multiple Alexandrov spaces into an Alexandrov space.
Understanding separation effects on parameter estimation in finite Gaussian mixtures
We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a probabilistic model that first generate noisy positions for each object through a separate linear state-space model, and then renders the positions of all objects in the same image through a high…
Recent progress in separating the speech signals from multiple overlapping speakers using a single audio channel has brought us closer to solving the cocktail party problem. However, most studies in this area use a constrained problem setup, comparing performance when speakers overlap almost completely, at artificially…
Constructs initial data for multiple black holes with specified ADM parameters.
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods while learning separate affine parameters per domain. For each domain,…
Criteria for loop separability on surfaces using Goldman bracket.
In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coe…
New examples of non-bumpy metrics on spheres and projective spaces with multiplicity.
MFCVAE clusters data over multiple facets, improving disentanglement and generation.
Model separates overall uncertainty into aleatoric and epistemic components for active learning.
The task of clustering a set of objects based on multiple sources of data arises in several modern applications. We propose an integrative statistical model that permits a separate clustering of the objects for each data source. These separate clusterings adhere loosely to an overall consensus clustering, and hence the…
Research in deep learning for multi-speaker source separation has received a boost in the last years. However, most studies are restricted to mixtures of a specific number of speakers, called a specific scenario. While some works included experiments for different scenarios, research towards combining data of different…
A new method detects hidden driving forces in systems with multiple observables.
This paper develops a new nonlocal approximation method for minimal surfaces, proving robust estimates and separation properties.
LOFT separates subspace rotation and transformation for orthogonal fine-tuning.
This paper introduces and solves the simultaneous source separation and phase retrieval (SPR) problem. SPR is an important but largely unsolved problem in a number application domains, including microscopy, wireless communication, and imaging through scattering media, where one has multiple independent coherent…
We present a data dependent generalization bound for a large class of regularized algorithms which implement structured sparsity constraints. The bound can be applied to standard squared-norm regularization, the Lasso, the group Lasso, some versions of the group Lasso with overlapping groups, multiple kernel learning a…
High temporal resolution measurements of human brain activity can be performed by recording the electric potentials on the scalp surface (electroencephalography, EEG), or by recording the magnetic fields near the surface of the head (magnetoencephalography, MEG). The analysis of the data is problematic due to the fact …
Study on CMC hypersurfaces with bounded index and area, proving multiplicity one convergence and bounds on genus.
Improved defect detection in layered materials using signal separation methods.
System learns to combine multiple model components for personalized text generation.