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.
Speech data from multiple tasks improves AD detection models.
problem Limited AD detection models trained on single-task speech datasets.
method Augmented AD-specific dataset with multi-task healthy data.
result AD detection improved by up to 9% with heterogeneous data.
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.
Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the sa…
Study improves infant cry-based asphyxia diagnosis using transfer learning.
problem Improving accuracy of diagnosing perinatal asphyxia in newborns.
method Neural transfer learning from adult speech to infant cries.
result Transfer learning models are resilient to noise and signal loss.
Localization of chest pathologies in chest X-ray images is a challenging task because of their varying sizes and appearances. We propose a novel weakly supervised method to localize chest pathologies using class aware deep multiscale feature learning. Our method leverages intermediate feature maps from CNN layers at di…
We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach (as opposed to LDA) for intersession variability compensation in the i-…
This study investigates how much knowledge from natural images can be transferred to pathology images.
problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.
Study classifies pathology reports using TF-IDF features and machine learning.
problem Classifying pathology reports for cancer surveillance and diagnostic workflow.
method Extracted TF-IDF features from pathology reports and classified them using SVM, XGBoost, and Logistic Regression.
result XGBoost achieved 92% accuracy in classifying pathology reports.
This paper characterizes VAE training pathologies and their effects on tasks.
problem Characterizing VAE training pathologies and their impact on downstream tasks.
method Concretely characterizing conditions for VAE training pathologies and their connection to specific downstream tasks.
result Connects VAE training pathologies to specific downstream tasks like learning compressed and disentangled representations, adversarial robustness, and semi-supervised learning.
Batch normalization in the last layer reduces sharpness in wide neural networks.
problem Pathological sharpness in wide neural networks.
method Quantifying the geometry of the parameter space using Fisher information matrix and analyzing deep neural networks with random initialization.
result Batch normalization in the last layer significantly decreases pathological sharpness under specific conditions.
The paper identifies conditions for trend reversal in classification tasks.
problem Trend reversal in classification scores and dataset values.
method Algebraic conditions and numerical results for ridge regression.
result Existence of pathological regularization regimes for certain dataset conditions.
SAPSAM trains CNNs on lung CTs with binary labels, improving CPA detection and localization.
problem Chronic Pulmonary Aspergillosis (CPA) detection and localization on CT scans using binary labels.
method Binary labels, average intensity projections, 2D RGB-like images, hierarchical CNN architectures.
result High classification accuracy, precise localization, predictive power of 2-year survival.
KL-regularized RL from expert demos can lead to slow, unstable learning.
problem Pathological training dynamics in KL-regularized RL from expert demonstrations.
method Empirical analysis and non-parametric behavioral reference policies.
result KL-regularized RL can be significantly improved by using non-parametric behavioral policies.
This work examines robust MCMC for pathological distributions.
problem Pathological behavior in target distributions affects MCMC efficiency.
method Reviewing and proposing remedies for roughness and flatness in MCMC.
result Robust MCMC algorithms can perform well even in challenging conditions.
Paper develops a BERT-based classifier to reduce pathology report annotation workload.
problem Manual annotation of pathology reports is labor-intensive and time-consuming.
method Developed an automatic text classifier using BERT and introduced a human-centric metric to identify low-confidence cases.
result The model reduces manual annotation workload by 80% to 98%.
Generative model for morphological continuum of normal and pathological states.
problem Identifying trends and features that separate normality and pathology in biomedical images.
method Wasserstein Auto-encoder with HSIC regularization for latent features.
result Model generates a continuum of morphological changes corresponding to side information.
We introduce a novel approach, requiring only mild assumptions, for the characterization of deep neural networks at initialization. Our approach applies both to fully-connected and convolutional networks and easily incorporates batch normalization and skip-connections. Our key insight is to consider the evolution with …
The paper presents algorithms for diagnosing Pathological Myopia and detecting retinal structures.
problem Diagnosing Pathological Myopia and detecting retinal structures in fundus images.
method The approach uses Deep Learning techniques, including transfer learning with Xception and YOLO architecture.
result The method has shown satisfactory results in the Pathologic Myopia Challenge.
New analysis explains pathology of deep Gaussian processes.
problem Pathology of deep Gaussian processes reduces learning capacities with increased layers.
method Study nonlinear dynamic systems corresponding to DGPs, derive recurrence relations.
result Provide tighter bounds and rate of convergence for dynamic systems.
Machine learning improves EEG pathology classification.
problem Automating clinical EEG analysis using machine learning.
method Developed a comprehensive feature-based framework and compared it to deep neural networks.
result Feature-based framework achieves accuracies similar to deep neural networks.
Causal methods for GRN inference from single-cell data often fail in real-world benchmarks.
problem Understanding when and why causal methods for GRN inference from single-cell data fail in real-world benchmarks.
method Introduced a controlled diagnostic framework to isolate and measure seven pathologies.
result Causal methods dominate in clean and structurally favorable regimes but fail in specific pathologies.
Regularized Stein thinning improves MCMC output approximations.
problem Pathologies in Stein thinning leading to poor approximations.
method Theoretical analysis and regularization to improve KSD.
result Regularized Stein thinning alleviates pathologies and improves efficiency.
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
New method prevents entropy collapse in Transformer training, leading to more stable and robust models.
problem Training instability in Transformers, especially in attention layers.
method Spectral normalization with a learned scalar to prevent entropy collapse.
result Prevents entropy collapse, leading to more stable training.
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manu…
Paper shows EEG can improve ASR in noisy speech.
problem ASR performance drops in noisy conditions.
method Used EEG to train ASR models and improve performance.
result ASR accuracy improved with EEG features and distillation.
For test configurations, the Donaldson-Futaki invariant F_1 is well-known. In this note, its refinement will be discussed. Then we see that Li-Xu's pathology doesn't occur, since their example of a non-normal test configuration, with trivial normalization, actually has non-vanishing F_1 in this refined sense.
Paper shows continuous speech recognition with EEG features, no speech input.
problem Continuous speech recognition with limited vocabulary and noisy/no speech input.
method Connectionist temporal classification (CTC) model, EEG features, new deep learning architecture.
result Continuous speech recognition achieved on limited vocabulary with noisy/no speech input.
New test identifies specific biological parameters for personalized CVD detection.
problem Ineffectual pathology tests fail to consider platelet activation and inter-individual variability.
method Stochastic platelet deposition model and approximate Bayesian computation with discriminative summary statistics.
result Inferred parameters help identify specific biological parameters for personalized CVD detection.
This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis pr…
RUSLAN is a large Russian speech corpus for text-to-speech.
problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.
Method treats pseudo healthy synthesis as a factor decomposition problem.
problem Creating a healthy-looking image from a pathological one.
method Adversarial training with paired or unpaired settings, combining two factors (healthy and disease) to reconstruct the input.
result Method outperforms conditional GAN and CycleGAN in generating pseudo healthy images.
This paper proposes synthetic augmentation for nuclei image segmentation in medical pathology.
problem Rare and time-consuming labeling of tumor nuclei images for semantic segmentation.
method Label-to-image translation to generate synthetic images.
result Synthetic augmentation improves segmentation accuracy.
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.
Detects AI-synthesized speech using cepstral and bispectral analysis.
problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.
problem Human ear can still distinguish synthesized speech from natural speech.
method WaveCycleGAN2 uses generators without down/up-sampling modules and combines discriminators from waveform and acoustic parameter domains.
result WaveCycleGAN2 achieves high-quality speech synthesis with comparable mean opinion scores to natural speech.
AudioPaLM combines text and speech models to improve speech processing and translation.
problem Improving speech understanding and generation models.
method Unified multimodal architecture combining text and speech models.
result AudioPaLM significantly outperforms existing speech translation systems.
Study reveals pathological eigenvalue spectra in FIM and its variants of DNNs.
problem Understanding sharp local shapes in DNN loss landscapes.
method Analysis of FIM and its variants in regression and classification DNNs.
result Pathological eigenvalue spectra appear in FIM and its variants, indicating sharp local shapes in specific directions.
Enhances spoken speech quality using EEG signals.
problem Improves speech clarity in noisy environments.
method Generative adversarial network (GAN), gated recurrent unit (GRU), temporal convolutional network (TCN) regression models.
result Significant improvement in speech enhancement quality compared to traditional methods.
Improved speech enhancement using diffusion models with MSE loss.
problem Efficient incorporation of noisy speech in generative speech enhancement.
method Augmented diffusion-based generative model with a MSE loss for enhanced speech.
result Proposed method improves speech enhancement performance compared to original diffusion model.
Automatic Chemical Design is a framework for generating novel molecules with optimized properties. The original scheme, featuring Bayesian optimization over the latent space of a variational autoencoder, suffers from the pathology that it tends to produce invalid molecular structures. First, we demonstrate empirically …
This work disentangles speech and non-speech components from found data.
problem Building robust acoustic models from found data with non-standard variations.
method Latent Stochastic Models and Multinode Latent Space Variational Autoencoders (VAE).
result Speech and music can be separated in the latent space of a VAE, independent of the language.
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
Speech emotion recognition system using features and text.
problem Improving accuracy in emotion recognition from speech.
method Used speech features (Spectrogram, MFCC) and text, trained Deep Neural Networks.
result Combined MFCC-Text CNN model achieved highest accuracy.
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.