Deep learning improves singing processing tasks.
problem Lack of data and computing resources for singing processing.
method State-of-the-art deep learning techniques.
result Advances in accuracy and sound quality.
A new neural network separates singing voices more effectively.
problem Separating singing voices from mixed signals with high accuracy.
method MBR-FCN that processes different frequency bands with varying resolutions and filters.
result The MBR-FCN achieves better performance with fewer parameters.
WeSinger improves singing voice synthesis with data augmentation and specialized modules.
problem Improving the accuracy and naturalness of synthesized singing voices.
method Developed a multi-singer Chinese neural singing voice synthesis system with deep bi-directional LSTM, Transformer, LPCNet, and data augmentation.
result WeSinger achieves state-of-the-art performance on the Opencpop corpus.
SING improves state inference in latent SDE models for better drift function estimation.
problem Intractable posterior inference in latent SDE models.
method Natural gradient variational inference.
result SING provides faster and more reliable inference in latent SDE models.
Paper proposes singing voice conversion without parallel data.
problem Convert singing voices without parallel data.
method Phonetic posterior feature, DBLSTM, vocoder.
result Successfully converts singing voices without parallel data.
Semi-supervised singing voice separation using synthetic mixtures.
problem Singing voice separation with limited labeled data.
method Trains a single mapping function g on synthetic mixtures of singing and instrumental music.
result Performance comparable to fully supervised methods, better than semi-supervised alternatives.
Deep Autotuner corrects singing pitch using neural networks.
problem Automatic pitch correction for singing performances.
method Neural network model trained on spectrograms of singing and accompaniment.
result Neural network predicts continuous pitch shifts, allowing for improvisation and harmonization.
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.
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.
Deep learning converts one singer's voice to another without supervision.
problem Unsupervised singing voice conversion.
method Deep learning network with a single CNN encoder, WaveNet decoder, and classifier.
result Natural, recognizable singing voices converted without supervision.
We study codimension one (transversally oriented) foliations $\fa$ on oriented closed manifolds M having non-empty compact singular set $\sing(\fa)$ which is locally defined by Bott-Morse functions. We prove that if the transverse type of $\fa$ at each singular point is a center and $\fa$ has a compact leaf with fini…
Jukebox generates high-fidelity songs with singing in raw audio.
problem Generating music with singing in raw audio.
method Multi-scale VQ-VAE for compression, autoregressive Transformers for modeling.
result Generates high-fidelity and diverse songs with coherence up to multiple minutes.
New neural network separates singing voices from music using cross entropy loss.
problem Separating singing voices from music accompaniment.
method Deep Convolutional Neural Network (CNN) trained with Ideal Binary Mask (IBM) and cross entropy loss.
result Proposed CNN outperforms existing systems in MIREX evaluations.
Recently, the principal component pursuit has received increasing attention in signal processing research ranging from source separation to video surveillance. So far, all existing formulations are real-valued and lack the concept of phase, which is inherent in inputs such as complex spectrograms or color images. Thus,…
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…
Simplicial sets deformation retract onto transverse simplices.
problem Deformation retraction of simplicial sets.
method Showed deformation retraction of singular simplicial set onto transverse simplices.
result Singular simplicial set deformation retracts onto transverse simplices.
Parallel transport in a fibre bundle with respect to smooth paths in the base space B have recently been extended to representations of the smooth singular simplicial set Sing_{smooth}(B). Inspired by these extensions,I revisit the development of a notion of `parallel' transport in the topological setting of fibrations…
SING generates musical notes from instruments in real-time.
problem Efficiently generating high-quality audio from MIDI data.
method Frame-by-frame waveform generation with a single decoder, using a new loss function.
result SING produces significantly improved audio quality compared to state-of-the-art models, with 32x faster training and 2,500x faster inference.
We prove the factoriality of the following nodal threefolds: a complete intersection of hypersurfaces F and G⊂P5 of degree n and k respectively, where G is smooth, ∣Sing(F∩G)∣⩽(n+k−2)(n−1)/5, n⩾k; a double cover of a smooth hypersurface $F\subset\mathbb{P}^{…
A new algorithm for training generative models using Sinkhorn divergence.
problem Training generative adversarial networks (GANs).
method Sinkhorn Natural Gradient (SiNG) algorithm for steepest descent on probability space.
result Explicit expression and efficient evaluation of the Sinkhorn information matrix (SIM).
Deep Autotuner corrects singing pitch without scores, using vocal and accompaniment spectral data.
problem Automatic pitch correction without musical scores for singing performances.
method Convolutional Gated Recurrent Unit (CGRU) model trained on karaoke data.
result The model predicts pitch correction from vocal and accompaniment spectral contents, making the voice sound in tune with the accompaniment.
The paper proves smoothness of almost-minimizers' boundaries near the free boundary.
problem Minimizing degenerate area functionals with weighted boundary conditions.
method Epsilon-regularity theorem applied to almost-minimizers.
result Almost-minimizers' boundaries are C1,γ0-smooth, orthogonal to the boundary Ω. New distances defined between surfaces in 4-manifolds, with a new inequality proved.
problem Defining and comparing distances between surfaces in 4-manifolds.
method Using techniques similar to Gabai's proof, proving an inequality between two distance notions.
result Proved that stabilisation distance is at most one more than singularity distance.
{\bf Construction.} For a dominating polynomial mapping {F:Kn→Kl} with an isolated critical value at 0 (K an algebraically closed field of characteristic zero) we construct a closed {\it bundle} GF⊂T∗Kn. We restrict GF over the critical points Sing(F) of F in F−1(0) and partiti…
The singular set of a foliation is always connected under certain conditions.
problem Understanding the connectedness of singular sets in foliations.
method Analyzing the normal sheaf and dimension properties of the singular set.
result The union of irreducible components of dimension k−1 in the singular set is connected. Establishes functoriality of Baum-Bott residues under specific conditions.
problem Functoriality of Baum-Bott residues under certain conditions.
method Establishes functoriality of Baum-Bott residues under specific conditions.
result The singular set of a foliation has dimension at least \( k-1 \).
Analyzes K-homology classes of singular complex spaces.
problem Analyzing K-homology classes of singular complex spaces.
method Examines various L2-∂ complexes and their rolled-up operators. result Analytic K-homology classes of singular spaces can be related to their birational invariants.
Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a n…
Study on singularities of area-minimizing currents, focusing on frequency and branch points.
problem Understanding the nature of singular points in area-minimizing currents.
method Intrinsic frequency function and decomposition theorem for singular set.
result Established properties of the planar frequency function and decomposition of singular set.
Study minimal hypersurfaces with bounded area and high Morse index using combinatorial methods.
problem Understanding minimal hypersurfaces with high Morse index and bounded area.
method Combinatorial argument to study Betti numbers and Hausdorff dimension of singular sets.
result Bounds on Betti numbers and Hausdorff measure of singular sets for minimal hypersurfaces.
Study quantifies properties of PMC hypersurfaces with area bounds.
problem Understanding the topology and singular set of PMC hypersurfaces.
method Established quantitative topological and singularity properties for PMC hypersurfaces.
result Quantitative bounds on Betti numbers and Minkowski content of singular sets.
In this work we prove a Baum-Bott type formula for non-compact complex manifold of the form X~=X−D, where X is a complex compact manifold and D is a normal crossing divisor on X. As applications, we provide a Poincaré-Hopf type Theorem and an optimal description for a smooth hypersur…
Neural networks approximate Calabi-Yau metrics and curvature.
problem Finding Ricci-flat metrics for Calabi-Yau manifolds.
method Use neural networks to approximate metrics within a Kähler class.
result Neural networks can approximate topological characteristics of Calabi-Yau manifolds.
Defines axial curvatures for corank 1 singular manifolds in higher dimensions.
problem Characterizing singular n-manifolds in Rn+k with corank 1 singular points. method Using curvature locus and second fundamental form, defining up to l(n−1) axial curvatures. result Umbilic curvatures are absolute values of our axial curvatures.
Algorithm learns non-Gaussian graphical models via Hessian scores and triangular transport.
problem Learning graph structure from non-Gaussian data.
method Score based on integrated Hessian information, coupled with triangular transport map.
result Algorithm successfully recovers graph structure for non-Gaussian data.
Efficiently generates and selects explanations for neural networks using GANs and FID.
problem Manual selection of hyper-parameters for generating interpretable neural network explanations is slow and requires qualitative evaluation.
method Proposes a novel metric using Fréchet Inception Distance (FID) and a GAN-based method for efficient search and realistic output generation.
result Successfully selects hyper-parameters leading to interpretable examples, avoiding manual evaluation.
Let M be a smooth manifold and let $\F$ be a codimension one, C∞ foliation on M, with isolated singularities of Morse type. The study and classification of pairs $(M,\F)$ is a challenging (and difficult) problem. In this setting, a classical result due to Reeb \cite{Reeb} states that a manifold admitting a …
Let M be a n-dimensional complex manifold and f,g:M→M two distinct holomorphic self-maps. Suppose that f and g coincide on a globally irreducible compact hypersurface S⊂M. We show that if one of the two maps is a local biholomorphism around S′=S−Sing(S) and, if needed, S′ sits into M …
Hybrid f0 extraction method for various speech modes with high accuracy.
problem Reliable f0 extraction across different speech modes.
method Ordinal regression CNN and filtering/autocorrelation for pitch estimation.
result Significantly reduces pitch detection error and generalizes to unseen modes.
Optimal regularity theory for stable minimal hypersurfaces with small singular set.
problem Optimal regularity of stable minimal hypersurfaces with small singular set.
method Analysis of stable minimal hypersurfaces in a specific domain with small singular set.
result Optimal size assumption on the non-immersed singular set guarantees optimal regularity.
Global singularities propagate in magnetic mechanical systems on Riemannian manifolds.
problem Propagation of singularities in magnetic mechanical systems.
method Combines reduction from magnetic to Riemannian systems, analysis of reparameterized flows, and regularization techniques.
result Invariant singular set under generalized gradient flow dynamics.
New bounds on singular set size for harmonic maps into 2-sphere in higher dimensions.
problem Bounding the size of singular set for harmonic maps into 2-sphere.
method Extending previous results to higher dimensions, proving new inequalities.
result Stable bounds on singular set size under small perturbations.
In the top-down approach to multi-name credit modeling, calculation of singe name sensitivities appears possible, at least in principle, within the so-called random thinning (RT) procedure which dissects the portfolio risk into individual contributions. We make an attempt to construct a practical RT framework that enab…
Spectrogram-Channels U-Net separates sounds by treating each channel as a source's spectrogram.
problem Sound source separation in music information retrieval.
method Adapting U-Net to treat each channel of the output as a source's spectrogram, balancing volumes between sources.
result State-of-the-art performance on singing voice and multi-instrument separation.
Framework converts singer identity and vocal technique from non-parallel corpora.
problem Converts singer identity and vocal technique from non-parallel corpora.
method Uses variational autoencoders with separate encoders for singer identity and vocal technique.
result Successfully disentangles and converts singer identity and vocal technique.
Paper presents a provably correct algorithm for CNMF under separable conditions.
problem Convolutive nonnegative matrix factorization (CNMF) under separable assumptions.
method Algorithm exploiting NMF model and existing separable NMF algorithms.
result Guaranteed solution in low noise settings, runs in polynomial time.
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…
We study the asymptotics as p↑2 of stationary p-harmonic maps up∈W1,p(M,S1) from a compact manifold Mn to S1, satisfying the natural energy growth condition ∫M∣dup∣p=O(2−p1). Along a subsequence pj→2, we show that the singular sets Sing(upj) converge to the sup…