Proposes DNN for enhancing sound quality scores.
problem Improving sound quality assessment scores.
method Develops a DNN optimization scheme based on black-box optimization and policy gradient method.
result Significant increase in OSQA scores without minimizing MSE.
Stabilizes training of DNN for speech enhancement using PESQ scores.
problem Stability issues in training DNNs using non-differentiable OSQA scores.
method Approximate OSQA scores with a differentiable auxiliary DNN and stabilize training with reinforcement learning techniques.
result Stable training of DNN to achieve state-of-the-art PESQ scores and better sound quality.
To improve the efficiency of Monte Carlo estimation, practitioners are turning to biased Markov chain Monte Carlo procedures that trade off asymptotic exactness for computational speed. The reasoning is sound: a reduction in variance due to more rapid sampling can outweigh the bias introduced. However, the inexactness …
Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, th…
Protein structure prediction has been a grand challenge problem in the structure biology over the last few decades. Protein quality assessment plays a very important role in protein structure prediction. In the paper, we propose a new protein quality assessment method which can predict both local and global quality of …
Neural network synthesizes percussive sounds with adjustable timbral features.
problem Control over high-level timbral characteristics of percussive sounds.
method Feedforward convolutional neural network mapping input parameters to waveform.
result Changing input parameters produces a waveform congruent with desired characteristics.
We augment the nonnegative matrix factorization method for audio source separation with cues about directionality of sound propagation. This improves separation quality greatly and removes the need for training data, with only a twofold increase in run time. This is the first method which can exploit directional inform…
The paper assesses quality measures for machine learning models using cross-validation.
problem Evaluating the accuracy and robustness of quality measures for machine learning models.
method Cross-validation approach to estimate prediction error and quantify explained variation. Confidence bounds and local quality measures derived from residuals.
result The reliability and robustness of quality measures are assessed through numerical examples and confidence bounds.
Automatically assesses the quality of online health articles.
problem Lack of automated tools to evaluate the quality of online health information.
method Data mining approach using 10 quality criteria and feature selection.
result Classifier achieved 84%-90% accuracy on 10 criteria.
Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating fr…
Deep learning models generate music with arbitrary control strategies.
problem Lack of efficient methods for generating music with arbitrary control.
method Deep generative models learn to navigate arbitrary sound spaces.
result Deep learning enables high-quality, arbitrary sound synthesis.
Study improves data quality assessment for structural monitoring data.
problem Ensuring reliability of structural health monitoring data.
method Probabilistic data quality assessment using a conditional diffusion model.
result Significantly improves accuracy of data quality assessment.
Neural Information Processing Systems (NIPS) is a top-tier annual conference in machine learning. The 2016 edition of the conference comprised more than 2,400 paper submissions, 3,000 reviewers, and 8,000 attendees. This represents a growth of nearly 40% in terms of submissions, 96% in terms of reviewers, and over 100%…
A framework assesses the quality of crowdsourced weather data.
problem Quality control and assessment of crowdsourced weather data from third-party stations.
method Proposes a simple, scalable, and interpretable AI/Stats/ML framework to assess TPAWS data.
result Demonstrates the performance of the framework using synthetic and real data.
Paper proposes a method to estimate intra-observer variability in echocardiography quality assessment.
problem Intra-observer variability in echocardiography quality assessment impacts deep neural network reliability.
method Modeling intra-observer variability as aleatoric uncertainty in a regression problem.
result The proposed method reduces error from 0.11 to 0.09, improving test accuracy by 5.7%.
End-to-end CNN classifies environmental sounds from audio signals.
problem Classifying environmental sounds from audio signals.
method 1D Convolutional Neural Network (CNN) with overlapped frames and Gammatone filterbank initialization.
result 89% mean accuracy on UrbanSound8k dataset.
SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.
problem Improving neural vocoder sound quality, especially in high-frequency bands.
method Adapting the diffusion noise distribution to the conditioning log-mel spectrogram through time-varying filtering.
result SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders.
Improved representations from multiple video views.
problem Learning reliable representations across unaligned video modalities.
method Correlation-based representation learning on a 4-way parallel multimodal dataset.
result Best models achieve retrieval rates up to 96.9% on open-domain instructional videos.
Generative models assess quality on time-series data using ITS and FITD.
problem Lack of consensus for quality assessment of class-conditional generative models on time-series data.
method Introduced InceptionTime Score (ITS) and Frechet InceptionTime Distance (FITD) to evaluate generative models.
result ITS and FITD combined with TSTR can accurately assess generative model performance on time-series data.
The paper defines and assesses the quality of datasets using a novel expected diameter metric.
problem Lack of rigorous methods to assess data quality.
method Formal definition of data quality, expected diameter metric, Fourier analysis, algebraic methods, probabilistic analysis.
result The expected diameter metric provides theoretical guarantees and practical solutions for data quality assessment.
Risk, including economic risk, is increasingly a concern for public policy and management. The possibility of dealing effectively with risk is hampered, however, by lack of a sound empirical basis for risk assessment and management. The paper demonstrates the general point for cost and demand risks in urban rail projec…
Framework for automatically assessing and correcting data quality issues without domain knowledge.
problem Ensuring data quality in datasets across various domains.
method Hybrid approach combining statistical and machine learning methods.
result Effective detection and correction of missing values, duplicates, and typographical errors.
The paper introduces a method to assess machine translation quality with confidence intervals.
problem Evaluating the uncertainty and quality of machine translation.
method Utilizes conformal predictive distributions to produce prediction intervals with guaranteed coverage.
result The method outperforms a baseline on six language pairs in terms of coverage and sharpness.
Developed a new method to generate synthetic data while protecting privacy.
problem Protecting privacy of human participant data while making it publicly accessible.
method A multi-step framework based on Classification and Regression Trees and an original distance-based filtering.
result Satisfactory protection against attribute disclosure attacks and formal prevention of membership disclosure attacks.
PQMass assesses generative model quality using chi-squared tests.
problem Assessing the quality of generative models without density assumptions.
method Divides sample space into regions, applies chi-squared tests to p-values.
result Effectively assesses generative model quality, novelty, and diversity.
Dual quality assessment method tackles adversarial robustness issues across various metrics.
problem Varying robustness levels and bias in adversarial attacks and defenses.
method Model agnostic dual quality assessment method, including robustness levels.
result Current networks and defenses are vulnerable at all robustness levels, highlighting the need for a dual approach.
A popular tool for unsupervised modelling and mining multi-aspect data is tensor decomposition. In an exploratory setting, where and no labels or ground truth are available how can we automatically decide how many components to extract? How can we assess the quality of our results, so that a domain expert can factor th…
Re-speaking is a mechanism for obtaining high quality subtitles for use in live broadcast and other public events. Because it relies on humans performing the actual re-speaking, the task of estimating the quality of the results is non-trivial. Most organisations rely on humans to perform the actual quality assessment, …
CALLISTO generates tests and assesses ML data quality using prediction entropy.
problem Validating ML systems for accuracy and data quality.
method Entropy-based test generation and data quality assessment framework.
result CALLISTO detects up to 20x more errors than traditional methods.
This paper uses Monte Carlo simulation to value quality options in agricultural futures contracts.
problem Valuation of quality options in agricultural futures to prevent manipulation and improve hedging performance.
method Monte Carlo simulation with antithetic variables for efficiency.
result Demonstrates a method to estimate the value of quality options in agricultural futures contracts.
Optimizes audio codec selection with statistical guarantees.
problem Selecting the best audio encoding scheme for various data types.
method Supervised learning with uniform convergence theory.
result Rigorous statistical guarantees for codec selection.
A deep learning framework assesses physical rehabilitation exercises.
problem Lack of versatile, robust, and practical assessment methods for rehabilitation exercises.
method Deep learning framework with metrics, scoring functions, and neural networks.
result First implementation of deep neural networks for rehabilitation performance assessment.
A system is presented that segments, clusters and predicts musical audio in an unsupervised manner, adjusting the number of (timbre) clusters instantaneously to the audio input. A sequence learning algorithm adapts its structure to a dynamically changing clustering tree. The flow of the system is as follows: 1) segment…
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.
Paper proposes a method to protect DCNNs from adversarial attacks and poor quality images.
problem DCNNs are vulnerable to adversarial examples and perceptual quality issues.
method Combines image quality assessment with knowledge distillation.
result Detector effectively identifies poor quality and adversarial images.
Study subjective perception of low light restored images and develop an unsupervised QA model.
problem Lack of subjective QA for low light restored images and challenges in collecting human opinion scores.
method Create a dataset, conduct subjective QA study, develop self-supervised contrastive learning technique to extract features.
result Unsupervised NR QA model achieves state-of-the-art performance for low light restored images.
The study improves life insurance surrender risk modeling using various machine learning techniques.
problem Accurate modeling of surrender risk in life insurance to meet Solvency II directive requirements.
method Extensive experiments with XGBoost, random forest, GLM, and neural networks; resampling analysis; time-dependent confidence bands.
result Models trained on resampled data predict significantly biased event probabilities, highlighting the need for complementary assessments.
This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN. Our method, which we call StarGAN-VC, is noteworthy in that it (1) requires no parallel utterances, transcriptions, or time alignment procedures for speec…
New β3-IRT model improves test performance and assesses classifier quality.
problem Improving test performance and assessing classifier quality.
method Proposes β3-IRT model to model continuous responses and assess latent abilities. result The β3-IRT model outperforms standard models on various datasets and provides a new metric for classifier evaluation. We introduce a fully probabilistic framework of consumer product choice based on quality assessment. It allows us to capture many aspects of marketing such as partial information asymmetry, quality differentiation, and product placement in a supermarket.
This paper summarizes some recent advances on a set of tasks related to the processing of singing using state-of-the-art deep learning techniques. We discuss their achievements in terms of accuracy and sound quality, and the current challenges, such as availability of data and computing resources. We also discuss the i…
A novel ML verification technique using manifold learning.
problem Ensuring trust in machine learning systems.
method Variational autoencoder for extracting a low-dimensional manifold from high-dimensional training data.
result The manifold provides diverse test data, fault-revealing test cases, and independent runtime trust assessment.
Study investigates how simple speech sounds can form abstract categories.
problem How do abstract categories like phonemes emerge from speech exposure?
method Used modeling techniques to test Memory-Based Learning and Error-Correction Learning.
result Error-Correction Learning models can learn abstractions, identifying phone inventory and grouping.
rMCL improves on MCL by preserving diversity in predictions for regression problems.
problem Multimodal density estimation in regression settings with multiple targets.
method rMCL uses a learned scoring scheme based on Voronoi tessellations to maintain diversity among predictions.
result rMCL outperforms existing MCL variants in sound source localization tasks.
Algorithm selects optimal segment for physiological signal analysis.
problem Physiological signals are often corrupted by noise, requiring selective analysis.
method Combines deep neural networks for signal analysis and combinatorial optimization for segment selection.
result Significant improvement in system performance, e.g. 2.4% increase in sensitivity for heart sound segmentation.
Paper analyzes GP derivatives for error propagation in geoscience.
problem Error estimation in Gaussian Process models for geoscience applications.
method Derivative of GP model for error propagation analysis.
result Analytical error propagation formula derived from GP derivatives.
This paper improves universal sound separation using sound classification.
problem Separating acoustic sources from an open domain, regardless of their class.
method Utilizing semantic embeddings from a sound classifier to condition a separation network.
result Classifier embeddings provide nearly one dB of SNR gain, and iterative models achieve significant performance.
End-to-end Sanskrit TTS developed with limited data, achieving good quality.
problem Developing natural-sounding speech for Sanskrit with scarce data.
method Fine-tuning Tacotron2 model with WaveGlow and transfer learning.
result Achieved an overall MOS of 3.38 from 37 evaluators.