Breath sounds can identify speakers with high accuracy.
problem Identifying speakers from breath sounds.
method Examined breath sounds during continuous speech, focusing on inhalation phase.
result Breath sounds carry unique speaker-specific information, enabling accurate speaker identification.
Paper aims to find joint representation between vocal tract geometry and speech sound acoustics.
problem Finding a joint latent representation between articulatory and acoustic domains for vowel sounds.
method Invertible neural network models, convolutional autoencoder, normalizing flows, semi-supervised learning.
result Satisfactory performance in articulatory-to-acoustic and acoustic-to-articulatory mapping.
Proposes a speaker-independent GlotNet vocoder using WaveNet for speech generation.
problem Lack of efficient multi-speaker WaveNet models with limited resources.
method Uses source-filter model of speech production to train a WaveNet for glottal excitation.
result Proposed GlotNet vocoder performs favorably to direct WaveNet vocoder in speech quality.
End-to-end speech recognition system trained on GPUs and CPUs.
problem Building state-of-the-art speech recognition systems.
method Utilizes CPUs and GPUs for training, data augmentation, and neural network updates. Uses vocal tract length perturbation and acoustic simulator for data augmentation. Employed Horovod allreduce for training.
result Achieved 7.92% WER on proprietary English Bixby open domain test set using a Bidirectional Full Attention (BFA) model.
Geometric framework for aligning fiber tracts across subjects.
problem Challenges in finding direct tract correspondence across multiple individuals.
method Geometric framework using intrinsic mean and deformation fields, parallel transport for registration.
result Bundle alignment results on 43 healthy adult subjects.
Novel 3D U-Net method for fast, reproducible white matter tract segmentation.
problem Challenges in fast and consistent white matter tract segmentation from diffusion tensor MRI.
method Convolutional neural network (3D U-Net) trained on a large DTI dataset.
result Reproducibility and accuracy of tract-specific diffusion measures.
New method clusters infant vocalizations using topological data.
problem Clustering infant vocalizations for developmental analysis.
method Topologically augmented signal representation with Dirichlet process mixture model.
result 8 clusters of vocalizations identified in the first 12 months of life.
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.
A fusion approach combines audio and video features for emotion recognition.
problem Continuous emotion recognition using both visual and auditory modalities.
method Pre-trained CNN features from video frames and minimalistic auditory descriptors. Fusion at feature or prediction level. SVR for prediction.
result Improves CCCs of 0.749 and 0.565 for arousal and valence respectively.
Understanding how housing values evolve over time is important to policy makers, consumers and real estate professionals. Existing methods for constructing housing indices are computed at a coarse spatial granularity, such as metropolitan regions, which can mask or distort price dynamics apparent in local markets, such…
Cheap model diagnoses vocal disorders accurately.
problem Diagnosing vocal disorders without expensive equipment.
method Used Mel-Cepstrum vectors and Support Vector Machine.
result Accurately diagnosed three vocal disorders.
Deep learning model classifies gastrointestinal diseases with high accuracy.
problem Disease detection in the gastrointestinal tract.
method Global features and deep neural networks.
result 95.80% accuracy, 95.87% precision, 95.80% F1-score.
Paper analyzes human vocal sentiment using various techniques.
problem Improving accuracy in emotion-level classification of human vocal expressions.
method Conventional vocal feature extraction, deep-learning approaches, context-level analysis, hyperparameter sweeps, data augmentation.
result Improved performance in emotion-level classification.
Study improves machine learning models for GI tract disease detection using comprehensive evaluations and cross-dataset testing.
problem Incomplete or incorrect evaluation of machine learning models for GI tract diseases.
method Comprehensive evaluations of five machine learning models using Global Features and Deep Neural Networks, introducing performance hexagons and cross-dataset testing.
result Demonstrates the need for more sophisticated performance metrics and evaluation methods to build generalizable models.
Study examines equity in post-Snow Uri recovery, finds disparities.
problem Disproportionate impacts on vulnerable populations during recovery.
method County and census tract level data analysis, satellite imagery, statistical procedures.
result Negative associations between non-Hispanic whites and outages, positive associations with certain demographic variables.
Deep learning model estimates multiple f0s, melodies, vocals, and bass lines from music.
problem Estimating f0s and other musical elements from polyphonic music.
method Multitask deep learning architecture trained on a large dataset.
result Multitask model outperforms single-task models.
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.
Diffusion magnetic resonance imaging (dMRI) and tractography provide means to study the anatomical structures within the white matter of the brain. When studying tractography data across subjects, it is usually necessary to align, i.e. to register, tractographies together. This registration step is most often performed…
Proposes deep learning method for GCI detection from pathological speech.
problem Detecting glottal closure instants (GCI) in pathological acoustic speech.
method Convolutional neural network with fused deep acoustic speech and linear prediction residual features.
result Significantly better than state-of-the-art methods in GCI detection.
A new model cleans vocal note event annotations in music.
problem Erroneous labels in music datasets.
method Contrastive learning to automatically create local deformations of likely correct labels.
result Transcription model accuracy improves with the proposed strategy.
Hybrid CNN improves segmentation and registration of white matter tracts.
problem Accurate analysis of longitudinal brain imaging data.
method A hybrid CNN integrating segmentation and registration into a single procedure.
result Hybrid CNN outperforms multistage pipelines in segmentation accuracy, consistency, and speed.
New algorithm separates vocals from music recordings efficiently.
problem Separate vocal and instrumental parts in music recordings.
method Informed group-sparse representation for linear-time singing voice separation.
result Efficacy confirmed on iKala dataset; music accompaniment follows group-sparse structure.
DC-SIS selects features faster than mRMR for Parkinson's vocal diagnosis.
problem Feature selection for Parkinson's disease vocal data.
method DC-SIS (Distance Correlation Sure Independence Screening) using distance correlation measure.
result 90 times faster feature selection with similar accuracy.
ConvNet classifies whale vocalizations and ambient noise in acoustic recordings.
problem Automated detection and classification of marine mammal vocalizations in acoustic recordings.
method Convolutional Neural Network with a novel acoustic representation.
result Classifier accurately detects and classifies whale vocalizations and ambient noise.
SCM-GAN converts any song to sound like a different singer.
problem Converting songs to sound like a different artist.
method Transfer learning and GANs to separate vocals and instruments, then convert and merge.
result SCM-GAN improves song conversion metrics by 35% GV and 13% MS.
Holomorphic vector bundles on Hopf manifolds admit flat connections.
problem Understanding flat connections on holomorphic vector bundles over Hopf manifolds.
method Defining resonant and non-resonant Mall bundles, proving the existence of flat connections on non-resonant bundles, and applying the Poincare-Dulac theorem.
result Non-resonant Hopf manifolds are linearizable, generalizing Kodaira's result.
New resonance theory for Anosov flows connects spectral properties to mixing measures.
problem Defining and analyzing Ruelle-Taylor resonances for Anosov actions.
method Combining microlocal methods and J. Taylor's cohomological theory, defining Ruelle-Taylor resonances and proving Fredholm theory.
result Ruelle-Taylor resonances form a discrete subset of Cκ with λ=0 being a leading resonance. We study the distribution of resonances for geometrically finite hyperbolic surfaces of infinite area by countting resonances numerically. The resonances are computed as zeros of the Selberg zeta function, using an algorithm for computation of the zeta function for Schottky groups. Our particular focus is on three aspe…
This paper addresses converting speech to EGG signals without hardware, improving accuracy.
problem Estimating EGG signals from speech without hardware.
method Optimization of evidence lower bound with KL-divergence minimization.
result The method generates EGG signals that agree with gold standard and outperforms state-of-the-art.
Inverse problem solved for rotationally symmetric manifolds using eigenvalues and resonances.
problem Determining the rotation radius of a manifold from its eigenvalues and resonances.
method Unitary equivalence to one-dimensional Schrödinger operators, non-linear real analytic isomorphism between Hilbert spaces.
result The rotation radius is uniquely determined by its eigenvalues and resonances.
Resonator Networks solve high-dimensional vector factorization better than optimization methods.
problem High-dimensional vector factorization problem in Vector Symbolic Architectures.
method Recurrent neural network (Resonator Networks) that combines nonlinear dynamics and superposition search.
result Resonator Networks outperform optimization methods in solving high-dimensional vector factorization.
New method separates music vocals from accompaniment without labeled data.
problem Separating music sources without isolated recordings.
method Bootstrapping deep model using primitive auditory cues.
result Trained deep model separates vocals from accompaniment in unlabeled music.
Paper proposes efficient multivariate spatial Fay-Herriot models using variational autoencoders.
problem Estimating population characteristics in small areas with limited data.
method Integrates multivariate spatial Fay-Herriot model with variational autoencoders to leverage spatial structure efficiently.
result Significant computational efficiency improvements for high-dimensional datasets.
Study reveals a link between Ruelle-Pollicott resonances and cohomology eigenvalues for Anosov diffeomorphisms.
problem Understanding the speed of mixing in Anosov diffeomorphisms.
method Investigates Ruelle-Pollicott resonances on manifolds of any dimension, connecting them to cohomology eigenvalues of a quasi-compact transfer operator.
result Established a cohomological bound for the speed of mixing of Anosov diffeomorphisms.
For compact and for convex co-compact oriented hyperbolic surfaces, we prove an explicit correspondence between classical Ruelle resonant states and quantum resonant states, except at negative integers where the correspondence involves holomorphic sections of line bundles.
A new neural network separates vocals from music accompaniment.
problem Separating vocals from music accompaniment in recordings.
method Self-attention convolutional neural network (CNN) with densely-connected blocks.
result 19.5% relative improvement in vocals separation.
New method provides reliable probabilistic bounds for VUR detection.
problem Detect VUR in children without radiation exposure.
method Machine learning with probabilistic bounds for conditional probability.
result Guaranteed bounds contain well-calibrated probabilities.
Proves new fixed point formulae for complex manifolds with boundary.
problem Fixed points on complex manifolds with boundary conditions.
method Logarithmic Lefschetz fixed point formulae, normal rescaling, relative duality.
result Resonant boundary terms record normal contact and tangential multiplicity.
The study finds resonance points in polarised curves with polynomial conserved quantities.
problem Finding resonance points in polarised curves with polynomial conserved quantities.
method Using the non-orthogonality assumption on the conserved quantity, the study deduces the existence of resonance points.
result Every finite type polarised curve in the conformal 2-sphere with a polynomial conserved quantity admits a resonance point.
Study of spectral properties of Lorentzian quasi-Fuchsian manifolds.
problem Understanding the spectral properties of Lorentzian quasi-Fuchsian manifolds.
method Analyzing the geodesic flow, Ruelle resonances, and pseudo-Riemannian Laplacian.
result Meromorphic extension of the resolvent of the pseudo-Riemannian Laplacian with poles of finite rank.
The resonant band is a useful notion for the computation of the nontrivial monodromy eigenspaces of the Milnor fiber of a real line arrangement. In this article, we develop the resonant band description for the cohomology of the Aomoto complex. As an application, we prove that real 4-nets do not exist.
We show that the resolvent of the Laplacian on SL(3,R)/SO(3) can be lifted to a meromorphic function on a Riemann surface which is a branched covering of C. The poles of this function are called the resonances of the Laplacian. We determine all resonances and show that the corresponding residue op…
We find a resonance free region polynomially close to the critical line on Conformally compact manifolds with polyhomogeneous metric.
Uniform spectral gap for convex cocompact hyperbolic surfaces and expanders.
problem Spectral gap for convex cocompact hyperbolic surfaces and their covers.
method Using thermodynamic formalism for twisted Selberg zeta functions.
result Uniform resonance-free regions for convex cocompact hyperbolic surfaces and expanders.
We investigate the resonance varieties, lower central series ranks, and Chen ranks of the pure virtual braid groups and their upper-triangular subgroups. As an application, we give a complete answer to the 1-formality question for this class of groups. In the process, we explore various connections between the Alexande…
A faster Bayesian method for estimating spatial count data models.
problem Bayesian estimation of spatial count data models is computationally expensive and slow.
method Derive a Variational Bayes (VB) method for posterior inference in negative binomial models with spatial dependence.
result The VB method is up to 50 times faster than MCMC and offers similar accuracy.
Hierarchical CNNs improve diagnosis of GI diseases from histopathological images.
problem Diagnosing GI diseases from histopathological images is challenging due to heterogeneity and shared features.
method Embedded a class hierarchy into a VGGNet to address the hierarchical structure of GI diseases.
result The hierarchical model achieved better results than a flat model for multi-category diagnosis of GI disorders.
For a conformally compact manifold that is hyperbolic near infinity and of dimension n+1, we complete the proof of the optimal O(rn+1) upper bound on the resonance counting function, correcting a mistake in the existing literature. In the case of a compactly supported perturbation of a hyperbolic manifold, we es…