This paper improves monaural source enhancement using SDR as an objective function.
problem Maximizing signal-to-distortion ratio (SDR) for better monaural source enhancement.
method Uses signal-to-distortion ratio (SDR) as an objective function to improve monaural source enhancement.
result The proposed method achieved better performance than conventional methods.
End-to-end denoising framework improves SDR and PESQ metrics.
problem Spectrum and metric mismatches in speech enhancement networks.
method Optimizes network on time-domain signals after ISTFT and uses improved loss functions.
result Significantly improved SDR and PESQ performance.
Proposes a two-step method for sound source separation.
problem Improving sound source separation performance.
method First, learn a latent space transform. Second, train a separation module in the latent space.
result The proposed method achieves better performance than joint learning approaches.
New neural network design improves speech enhancement metrics.
problem Improving speech enhancement metrics in noisy conditions.
method Combination of convolutional and recurrent layers in U-net architecture.
result Proposed solution outperforms current state-of-the-art in SDR, SIR, and STOI metrics.
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on speaker-independent multi-speaker separation. In this paper we extend the baseline system…
This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the recons…
This paper proposes RAS, a novel unsupervised loss function for speech separation.
problem Unsupervised speech separation without teacher models or synthesized mixtures.
method Train a neural network to separate sources given one channel, using Wiener filtering and SI-SDR.
result Achieves significant SDR improvement with minimal labeled data.
Improved music source separation using unlabeled data remixing.
problem Music source separation with deep learning.
method Introduces a simple convolutional and recurrent model and a scheme to leverage unlabeled music.
result Waveform methods can now match spectrogram methods on standard benchmarks.
Wave-U-Net with MHE regularization improves singing voice separation.
problem Singing voice separation from mixed music recordings.
method Wave-U-Net architecture with MHE regularization applied to 1D filters.
result Adding MHE regularization to the loss function consistently improves singing voice separation.
Proposes AWS method for precise speech enhancement using DNN.
problem T-F resolution problem in fixed-resolution short-time frequency transforms.
method Incorporates trainable adaptive window switching into speech enhancement procedure.
result Achieved higher signal-to-distortion ratio than conventional methods.
Hybrid model improves music source separation by 1.4 dB.
problem Improving music source separation accuracy.
method End-to-end hybrid spectrogram and waveform model, using model decision for domain choice.
result 1.4 dB improvement in Signal-to-Distortion (SDR) on MusDB HQ dataset.
SDR outperforms IDR in multimodal data analysis, especially with fewer samples.
problem Understanding and optimizing data efficiency in multimodal representation learning.
method Generative linear model to synthesize multimodal data, comparing IDR and SDR methods.
result Linear SDR methods yield higher-quality, more succinct reduced-dimensional representations with smaller datasets.
Enhanced FastMNMF for better speech separation.
problem Improving blind source separation for speech.
method Gaussian scale mixture (GSM) for heavy-tailed distributions.
result GSM-FastMNMF outperforms existing methods in speech enhancement.
Solves a fundamental problem in statistics and imaging with new methods.
problem Generalized Orthogonal Procrustes Problem (GOPP)
method Semidefinite relaxation (SDR) and generalized power method (GPM)
result GPM converges linearly to the global minimizer under large signal-to-noise ratio.
This paper reviews SDR methods for multivariate response regression.
problem Handling sufficient dimension reduction for multivariate response regression.
method Characterizes SDR estimators as inverse or forward regression methods.
result Pooled marginal, projective resampling, distance-based, ordinary least squares, partial least squares, and semiparametric SDR estimators are discussed.
Deep learning models improve sound separation across various types of sounds.
problem Developing a universal method to separate arbitrary sounds of different types.
method Created a dataset of mixtures containing arbitrary sounds, investigated mask-based separation architectures, and tested different framewise analysis-synthesis bases.
result STFT outperformed learnable bases in universal sound separation tasks.
R package psvmSDR simplifies SDR computation for machine learning.
problem Sufficient dimension reduction in machine learning.
method Principal machine (PM) generalized from PSVM.
result Efficient computation of SDR estimators in various scenarios.
Neural networks simplify SDR in regression tasks.
problem Sufficient dimension reduction in regression problems.
method Applying neural networks with rank regularization to estimate the central mean subspace.
result Neural networks effectively perform SDR, consistent with theoretical estimations.
A new geometry-preserving method for interpreting compositional data.
problem Statistical challenges in high-dimensional compositional data.
method Geometry-preserving framework for dimension reduction of compositional data.
result Identification of a central compositional subspace for compositional predictors.
Enhances SDR via Hellinger correlation for better data dependency understanding.
problem Improving sufficient dimension reduction in single-index models.
method Developed a new method using Hellinger correlation for detecting the dimension reduction subspace.
result Significantly enhances and outperforms existing SDR methods through deeper data dependency understanding.
We present the Shortfall Deviation Risk (SDR), a risk measure that represents the expected loss that occurs with certain probability penalized by the dispersion of results that are worse than such an expectation. SDR combines Expected Shortfall (ES) and Shortfall Deviation (SD), which we also introduce, contemplating t…
FlowSDR learns a low-dimensional projection preserving the response's conditional distribution.
problem Learning a low-dimensional projection that captures the response's conditional distribution.
method FlowSDR uses conditional log-likelihood maximization with monotone rational-quadratic spline flows to learn the projection and conditional density.
result FlowSDR outperforms existing SDR methods in various simulation settings and a face-age prediction task.
POTD estimates SDR subspace using optimal transport for binary response.
problem Insufficient performance of existing SDR methods for categorical responses.
method Principal optimal transport direction (POTD) using optimal transport coupling.
result POTD exclusively estimates SDR subspace for error-free class labels.
Dropout is shown to be a simplified version of SDR, which improves deep learning performance.
problem Overfitting and misspecification in deep learning models.
method SDR redefines weights as random variables, updating them based on prediction error and local history.
result SDR outperforms Dropout on standard benchmarks, achieving similar accuracy in fewer epochs.
A novel MM algorithm optimizes DCOV for SDR and SVS.
problem Dimension reduction and variable selection in nonparametric settings.
method Formulated as a DC program, MM algorithm solves quadratic subproblems on the Stiefel manifold.
result Improves computation efficiency and robustness across various settings.
Survey of SDR methods for high-dimensional regression and embedding.
problem Reducing dimensionality in high-dimensional data.
method Involves both statistical and machine learning approaches, covering inverse and forward regression methods.
result Supervised Kernel Dimension Reduction is equivalent to supervised PCA.
DVSDR reduces data dimensions while preserving label information.
problem Sufficient dimensionality reduction of high-dimensional observations.
method Deep variational approach using variational autoencoders.
result DVSDR performs competitively on classification tasks and generates novel data.
This paper presents a ML-based receiver for SDR that outperforms conventional methods.
problem Complexity and performance issues in multiuser detection.
method Supervised learning for direct symbol detection without parameter estimation.
result The ML-based receiver achieves similar or better performance than SIC and MMSE receivers.
Improved U-Nets with various intermediate blocks enhance singing voice separation.
problem Improving singing voice separation accuracy using U-Net architectures.
method Implemented and compared U-Nets with different intermediate spectrogram transformation blocks.
result A specific block type achieves state-of-the-art SDR by 0.9 dB.
Prob-PIT improves speech separation by considering output-label permutations as random variables.
problem Overconfident output-label assignment in PIT leads to unreliable speech separation.
method Prob-PIT treats output-label permutations as a discrete latent random variable with a uniform prior distribution and maximizes the log-likelihood function.
result Prob-PIT significantly outperforms PIT in terms of Signal to Distortion Ratio and Signal to Interference Ratio.
A method for reducing dimensions in Fréchet regression models.
problem Complex data objects in metric space-valued responses.
method Mapping metric-space valued random objects to real-valued variables and applying classical SDR.
result Consistent and asymptotically convergent method for Fréchet SDR.
Maximum a posteriori (MAP) inference over discrete Markov random fields is a fundamental task spanning a wide spectrum of real-world applications, which is known to be NP-hard for general graphs. In this paper, we propose a novel semidefinite relaxation formulation (referred to as SDR) to estimate the MAP assignment. A…
The purpose of sufficient dimension reduction (SDR) is to find the low-dimensional subspace of input features that is sufficient for predicting output values. In this paper, we propose a novel distribution-free SDR method called sufficient component analysis (SCA), which is computationally more efficient than existing …
In this letter, we propose enhanced factored three way restricted Boltzmann machines (EFTW-RBMs) for speech detection. The proposed model incorporates conditional feature learning by multiplying the dynamical state of the third unit, which allows a modulation over the visible-hidden node pairs. Instead of stacking prev…
New method for nonlinear SDR of complex non-Euclidean data.
problem Nonlinear SDR for complex non-Euclidean random objects.
method Fréchet Cumulative Covariance (FCCov) and neural networks.
result Robust and unbiased nonlinear SDR for complex data.
This paper proposes using DLT to expand SDRs for global stability.
problem Political instability and currency wars threaten global value chains.
method Proposes a two-step approach for IMF to integrate DLT into SDRs.
result SDRs can be redefined as a new reserve currency in a decentralized world.
Paper improves SDR estimation speed and conditions.
problem Improving sufficient dimension reduction for multi-index models.
method Estimating expected smoothed gradient outer product.
result Achieves fast parametric convergence rate of Cd⋅n−1/2. Fast and cheaper next generation sequencing technologies will generate unprecedentedly massive and highly-dimensional genomic and epigenomic variation data. In the near future, a routine part of medical record will include the sequenced genomes. A fundamental question is how to efficiently extract genomic and epigenomi…
Reservoir subspace injection improves online ICA by preserving injected features.
problem Discarding injected features in top-n whitening can degrade performance. method Formalized reservoir subspace injection (RSI) and developed diagnostics (IER, SSO, ρ_x) to identify and mitigate the failure mode.
result RSI controller preserves passthrough retention, improving performance by up to 2.2 dB.
Develops Fourier analysis for SDR, simplifying dimension reduction problems.
problem Finding a reduced subspace for high-dimensional data.
method Formulates SDR as a minimization problem in the Fourier domain, introducing a penalty for support distortion.
result An algorithm for finding a reduced subspace using Fourier transforms and penalties.
We found hidden convexity in FPCA and developed a faster algorithm.
problem Bias in PCA leading to unequal subgroup outcomes.
method Convex optimization via eigenvalue optimization.
result Faster and fairer PCA algorithm.
GenSDR tackles SDR by leveraging generative models to fully recover lower-dimensional structures.
problem Challenges in identifying low-dimensional sufficient structures in nonlinear SDR.
method Proposes GenSDR, a method that uses modern generative models to fully recover information in the central σ-field.
result Establishes consistency of GenSDR estimator for sample-level data and extends its applicability to non-Euclidean responses.
CIR method preserves relation for case-control studies.
problem Learning low-dimensional structure in case-control studies.
method Contrastive inverse regression (CIR) on Stiefel manifold.
result CIR outperforms other methods for high-dimensional data.
SMAVE optimizes SDR by projecting onto a low-dimensional subspace on a Riemannian manifold.
problem High-dimensional regression challenges due to the curse of dimensionality.
method SMAVE combines nearest-neighbor localization and Riemannian stochastic gradient ascent.
result SMAVE achieves almost-sure convergence and matches RMAVE's synthetic subspace recovery rate.
New method reduces data dimensionality using tempered distributions.
problem Unsupervised dimension reduction problem.
method Reformulate UDR as approximating an empirical probability density function by a tempered distribution, inducing a sufficient dimension reduction problem.
result An algorithm for UDR induces an algorithm for SDR and vice versa.
Wave-U-Net improves audio source separation by modeling phase information.
problem Fixed spectral transformations and high sampling rates limit audio source separation performance.
method Wave-U-Net adapts U-Net to time-domain, using repeated resampling to capture different time scales.
result Wave-U-Net achieves comparable performance to spectrogram-based U-Net on singing voice separation.
New method to decompose portfolio performance ratios.
problem Understanding the drivers of portfolio performance ratios.
method Using Euler's theorem, decomposes performance ratios into modified ratios.
result Derives condition for new asset to improve portfolio performance.
Omega ratio is shown to be equivalent to Sharpe ratio under certain distributional assumptions.
problem Comparing Omega ratio to Sharpe ratio as performance indicators.
method Computation and analysis of Omega ratio for normal distribution and proof for elliptic distributions.
result Omega ratio is equivalent to Sharpe ratio for returns with elliptic distributions.