Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

5099149198 · Jun 202019922001200920182026
48 results for sound quality assessment

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 …

2015-06-09abs ↗pdf ↗

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…

2018-02-09abs ↗pdf ↗

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 …

2016-02-13abs ↗pdf ↗

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.

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.

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%…

2017-08-31abs ↗pdf ↗

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%.

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.

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.

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…

2015-03-11abs ↗pdf ↗

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.

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…

2015-02-02abs ↗pdf ↗

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.

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.

New β3β^3-IRT model improves test performance and assesses classifier quality.

problem Improving test performance and assessing classifier quality.
method Proposes β3β^3-IRT model to model continuous responses and assess latent abilities.
result The β3β^3-IRT model outperforms standard models on various datasets and provides a new metric for classifier evaluation.

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.

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.