Extracts attended speaker from noisy speech mixtures using EEG and microphone arrays.
problem Extract attended speaker from noisy speech mixtures.
method Modular processing flow: extract speech envelopes, select attended speech based on EEG, use for speech separation and denoising.
result Strong suppression of interfering speech and background noise, preserved attended speech.
Proposes a probabilistic model for better hearing aid fitting.
problem Inadequate fitting of hearing aids leading to unsatisfactory sound experiences.
method Generative probabilistic model for hearing loss, automated inference of signal processing algorithm, fitting solution, and performance evaluation.
result Automated fitting solution and performance evaluation metric for hearing aids.
Study predicts hearing recovery in MD patients using TEOAE signals.
problem Predicting hearing recovery in MD patients during acute episodes.
method Applied machine learning to TEOAE signals from MD patients, using SVM for classification.
result Baseline TEOAE parameters can predict hearing recovery in MD patients.
CLCNet improves noise reduction in hearing aids with deep learning.
problem Noise reduction in hearing aids is challenging due to real-time and frequency resolution constraints.
method Proposes CLCNet, a deep learning framework based on complex linear coding.
result CLCNet outperforms traditional methods in noisy environments.
HEAR benchmark evaluates audio representations for diverse tasks.
problem Developing a general-purpose audio representation for various tasks.
method Evaluated 29 models across 19 tasks using 16 datasets.
result No single audio representation performs holistically.
Study shows surfaces sound the same everywhere if they have a transitive isometry group.
problem Can you hear your location on a manifold?
method Analyzing the isometry group and geodesics on compact surfaces.
result Compact surfaces without boundary that sound the same everywhere have a transitive isometry group.
We use an extension of Sunada's theorem to construct a nonisometric pair of isospectral simply connected domains in the Euclidean plane, thus answering negatively Kac's question, ``can one hear the shape of a drum?'' In order to construct simply connected examples, we exploit the observation that an orbifold whose unde…
Study shows agents benefit from hearing in addition to vision.
problem Limited effectiveness of vision-only reinforcement learning agents.
method Used audio as complementary information to visual cues in state representation.
result Agents perform better when hearing is added to vision.
Which properties of an orbifold can we ``hear,'' i.e., which topological and geometric properties of an orbifold are determined by its Laplace spectrum? We consider this question for a class of four-dimensional Kähler orbifolds: weighted projective planes $M:=\C P^2(N_1,N_2,N_3)$ with three isolated singularities. We s…
TinyLSTMs reduces speech enhancement model size and latency for hearing aids.
problem Large RNNs limit practical deployment in hearing aid hardware.
method Model compression techniques (pruning, integer quantization, state update skipping) for RNN speech enhancement.
result Reduction in model size and operations by 11.9imes and 2.9imes, respectively, without perceptual degradation. Inverse spectral theory reveals shapes from sound.
problem Can the shape of a drum be determined by its sound?
method Inverse isospectral techniques applied to specific shapes.
result The regular n-gon can be uniquely determined by its eigenvalues.
Human cochlear models improve DNN noise suppression systems.
problem DNN-based noise suppression systems lack robustness to unseen noise conditions.
method Coupled cochlear models with DNNs to improve noise suppression.
result Cochlear models enhance DNN generalizability to various noise conditions.
To a compact hyperbolic Riemann surface, we associate a finitely summable spectral triple whose underlying topological space is the limit set of a corresponding Schottky group, and whose ``Riemannian'' aspect (Hilbert space and Dirac operator) encode the boundary action through its Patterson-Sullivan measure. We prove …
Corners can be identified by a drum's sound spectrum.
problem Determining the presence of corners in a drum's shape from its sound.
method Proving spectral invariance of corners in domains with Lipschitz, piecewise smooth boundaries.
result Corners are uniquely determined by a drum's spectrum among domains with fixed genus.
A `platycosm' is a flat Riemannian 3-manifold without boundary. In this paper we prove that there is (up to scale) a unique isospectral pair of compact platycosms.
We study the inverse spectral problem for weighted projective spaces using wave-trace methods. We show that in many cases one can "hear" the weights of a weighted projective space.
Paper shows surfaces can't be heard to be orientable.
problem Determining orientability from spectral data.
method Applied Sunada's and Buser's methods to orbifolds.
result Constructed isospectral flat surfaces with different orientability.
AIDA designs personalized audio processing algorithms for hearing aids.
problem Improving hearing aid performance based on user feedback.
method Active inference-based agent with Bayesian trial design.
result AIDA proposes optimal alternative values for hearing aid parameters.
FCN improves speech clarity in noisy environments.
problem Improving speech clarity in noisy environments.
method Fully convolutional neural network (FCN) for speech enhancement.
result FCN can generalize to new speakers and robust to varying noise.
Domain adaptation reduces prosthetic training time for amputees.
problem Reducing training time for non-invasive myoelectric prostheses.
method Evaluation of domain adaptation algorithms on amputee and intact subjects data.
result Previous experience from other subjects reduces training time by about an order of magnitude.
We give a number of examples of isospectral pairs of plane domains, and a particularly simple method of proving isospectrality. One of our examples is a pair of domains that are not only isospectral but homophonic: Each domain has a distinguished point such that corresponding normalized Dirichlet eigenfunctions take eq…
Take a torus with a Riemannian metric. Lift the metric on its universal cover. You get a distance which in turn yields balls. On these balls you can look at the Laplacian. Focus on the spectrum for the Dirichlet or Neumann problem. We describe the asymptotic behaviour of the eigenvalues as the radius of the balls goes …
Researchers confirm Mark Kac's question for specific 3D and 4D orbifold lens spaces.
problem Can one hear the shape of a drum?
method Investigated 3D and 4D lens spaces, used heat kernel coefficients.
result Confirmed isospectrality for specific lens spaces, showed coefficients not sufficient.
Automatic segmentation of auditory ossicles from CT images using Ricci curvature.
problem Automatic diagnosis of ossicles' diseases from 3D CT images of the head.
method Proposes a completely automatic method that locates and segments ossicles without manual labels or templates, using Ricci curvature in an energy function.
result Performance of the proposed method using discrete Forman-Ricci curvature is superior to state-of-the-art methods.
We answer Mark Kacs famous question - can one hear the shape of a drum - in the negative for orbifolds that are spherical space forms. This is done by extending the techniques developed by A. Ikeda on Lens Spaces to the orbifold setting. Several results are proved to show that with certain restrictions on the dimension…
Characterizes how the shape of a polygon affects billiard dynamics.
problem Understanding how the shape of a billiard table influences its dynamics.
method New theorem linking Liouville current support to flat cone metrics.
result Only right-angled tables with affine differences have identical bounce spectra.
New findings show fundamental group is not audible in spherical space forms.
problem Isospectral spherical space forms with non-cyclic fundamental groups.
method Revisited and found new examples of spherical space forms.
result Fundamental group is not audible among spherical space forms.
Halal products sales in non-Muslim countries like Europe grew significantly in 2010.
problem Understanding the growth and motives behind halal products in non-Muslim economies.
method Analyzing sales data and market trends.
result Halal products sales in non-Muslim countries have been growing rapidly since 2010.
We uniquely and explicitly reconstruct the instantaneous intrinsic metric of the Kerr-Newman Event Horizon from the spectrum of its Laplacian. In the process we find that the angular momentum parameter, radius, area; and in the uncharged case, mass, can be written in terms of these eigenvalues. In the uncharged case th…
Perimeter on manifolds leads to new symmetrization methods.
problem Applying symmetrization methods to quasilinear elliptic problems on RN. method Generalization of perimeter to manifolds, using hear kernel regularization.
result New symmetrization method on spheres for quasilinear elliptic problems.
Orbifold local orientability can be detected by heat invariants.
problem Detecting local orientability in orbifolds.
method Using heat invariants to show Laplace isospectrality.
result Locally orientable orbifolds are distinguishable by heat invariants.
The musical notes from a hyperbolic marimba can identify the shape of hyperbolic surfaces.
problem Identifying hyperbolic surfaces based on their musical notes.
method Assigning musical notes to geodesics hitting labeled curves on hyperbolic surfaces.
result The melodies produced by hyperbolic marimbas can characterize hyperbolic surfaces up to isometry.
Paper shows hyperbolic 3-manifolds can sound the same but have different cohomology.
problem Cannot determine rational cohomology ring from sound of hyperbolic 3-manifolds.
method Implemented computer program to find nullity of cup product map.
result Example of strongly isospectral hyperbolic 3-manifolds with nonisomorphic rational cohomology rings.
Study reveals how to determine area and curvature from fluid flow resonances.
problem Determining geometric properties from fluid flow data.
method Asymptotic expansion of heat kernel and Steklov spectral invariants.
result Area and total mean curvature can be inferred from Steklov eigenvalues.
The paper investigates exotic smooth structures on manifolds with group actions.
problem Existence of homeomorphic but not diffeomorphic smooth manifolds with shared basic spectra.
method Investigates Riemannian Laplacian eigenvalues and eigenfunctions on manifolds with compact Lie group actions.
result Establishes the existence of homeomorphic yet not diffeomorphic manifolds with shared basic spectra.
AeGAN improves speech clarity in noisy environments.
problem Improving speech recognition in crowded noisy environments.
method Generative adversarial networks (GAN) with a novel architecture.
result The proposed framework outperforms traditional and learning-based methods.
Let M^{2n} be a symplectic toric manifold with a fixed T^n-action and with a toric Kähler metric g. Abreu asked whether the spectrum of the Laplace operator Δg on C∞(M) determines the moment polytope of M, and hence by Delzant's theorem determines M up to symplectomorphism. We report on some progre…
Deep networks learn new words from few examples, like humans.
problem Deep learning requires large datasets to learn new concepts.
method Inspired by human learning, a simple technique to learn new words from little data.
result Deep networks can learn useful representations for new words from minimal data.
New method reveals corners of drum shapes.
problem Determining the shape of drum corners from its sound.
method Locality principle and calculations of heat kernels.
result Corners are spectral invariants of the Laplacian.
Master thesis applies deep learning to sEMG hand gesture recognition, improving accuracy.
problem Reliability issues in sEMG-based hand gesture recognition due to motion artefacts and variability.
method Used deep learning on Unibo-INAIL dataset, collecting data over 8 sessions of 7 subjects.
result Deep learning architecture yields 81.2% inter-posture test accuracy and 75.9% inter-day test accuracy.
Curiosity enhanced by audio-visual associations improves learning efficiency.
problem Challenges in reinforcement learning, especially predicting the future.
method Exploits multiple modalities (audio and vision) to predict novel associations.
result Improves exploration and learning efficiency in various environments.
Compactness proven for isospectral Birkhoff billiard tables.
problem Proving compactness of isospectral Birkhoff billiard tables.
method Derived a hierarchical structure for integral invariants and used interpolating Hamiltonian.
result Compactness of equivalence classes of marked length isospectral Birkhoff billiard tables.
Mathematicians decode geometric properties from eigenvalues over 112 years.
problem Recovering geometric properties from eigenvalues of Laplace equations.
method Analyzing the relationship between eigenvalues, domain volume, and dimensionality.
result Deep connection between eigenvalues and geometric properties elucidated by Weyl's law.
Graph neural networks improve odor prediction from molecular structure.
problem Predicting odor from molecular structure is challenging and important.
method Used graph neural networks for QSOR modeling.
result Graph neural networks significantly outperform prior methods on a novel data set.
Researchers found a Weyl law for Liouville quantum gravity eigenvalues.
problem Understanding the spectral geometry of Liouville quantum gravity.
method Obtained a Weyl law for eigenvalues of Liouville Brownian motion.
result The n-th eigenvalue grows linearly with n, with a constant determined by the Liouville area and a specific cγ. In 1985 Kevin Walker in his study of topology of polygon spaces raised an interesting conjecture in the spirit of the well-known question "Can you hear the shape of a drum?" of Marc Kac. Roughly, Walker's conjecture asks if one can recover relative lengths of the bars of a linkage from intrinsic algebraic properties of…
Proposes a new method for parallelizing SGD that combines partial results from all workers.
problem Slow workers (stragglers) cause convergence issues in synchronous SGD.
method Fixes worker computation time and combines partial results from all workers.
result Improves convergence significantly compared to existing methods.
No floating point, no multiplications, no problem! Training efficient networks for resource-constrained devices.
problem Designing efficient neural networks for resource-constrained devices without floating-point operations.
method Discretizing both in-network non-linearities and network weights to avoid floating-point and multiplication operations.
result Training networks without floating-point operations can achieve comparable performance to those using floating-point operations, with less memory usage.