This paper improves monaural source enhancement using SDR as an objective function.
problem Maximizing signal-to-distortion ratio (SDR) for better monaural source enhancement.
method Uses signal-to-distortion ratio (SDR) as an objective function to improve monaural source enhancement.
result The proposed method achieved better performance than conventional methods.
Proposes a self-supervised method for generating spatial audio from monaural audio and video.
problem Generating spatial audio from monaural audio and video recordings is challenging and expensive.
method Uses a self-supervised network with an auxiliary classifier to classify video channels and generate spatial audio.
result The proposed method effectively generates spatial audio from monaural audio and video.
A new unsupervised method separates speech sources without requiring labeled data.
problem Lack of supervised data for effective neural source separation.
method Uses a complex Gaussian mixture model (cGMM) for joint training of separation and localization networks.
result The method outperforms conventional initialization methods in monaural and multichannel separation.
This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on mon…
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive of independent speakers. Such a vector space can embed empirically determi…
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.
Enhances source domain knowledge with target data for transfer learning.
problem Limited data in target domains and rigid model assumptions in transfer learning.
method Transfer learning through Enhanced Sufficient Representation (TESR).
result TESR enhances source domain knowledge with target data, improving transfer learning performance.
A fast method for multichannel source separation using jointly diagonalizable SCMs.
problem Computational inefficiency and poor performance in multichannel source separation.
method Restricts SCMs to jointly-diagonalizable but full-rank matrices, proposing efficient algorithms.
result Significant speedup and improved performance compared to original methods.
Enhances stock market prediction using multi-sourced data.
problem Improving stock market prediction by considering multiple data sources.
method Extended Coupled Hidden Markov Model incorporating historical trading data and news events, with correlations between stocks incorporated.
result Superior performance on China A-share market data in 2016 compared to previous methods.
Enhances generative model accuracy through knowledge transfer.
problem Improving generative model precision across different tasks.
method Introduces a novel framework for transfer learning using shared structures.
result Demonstrates enhanced performance in diffusion and normalizing flows models.
Enhances construction input modeling with Bayesian deep neural networks.
problem Deriving reliable simulation input models from construction data.
method Bayesian deep neural networks integrated with multi-source construction data.
result Derives detailed input models for construction operations.
Enhances optimization in multi-source settings with causal principles.
problem Optimizing functions with multiple sources of data and causal dependencies.
method Integrates Multi-Source Bayesian Optimization with Causal Bayesian Optimization principles.
result Improves optimization efficiency and reduces computational complexity.
Enhances adversarial examples for better transferability across models.
problem Adversarial examples often have limited black-box transferability.
method Fine-tunes existing adversarial examples by increasing perturbation on a pre-specified layer of the source model.
result Our method achieves greater black-box transferability of adversarial examples.
Efficient trainable front-end for neural speech enhancement.
problem Inefficient STFT front-ends in neural speech enhancement models.
method Butterfly mechanism for Fast Fourier Transform, trainable STFT window.
result Accuracy and efficiency improvements for low-compute systems.
Semi-supervised singing voice separation using synthetic mixtures.
problem Singing voice separation with limited labeled data.
method Trains a single mapping function g on synthetic mixtures of singing and instrumental music.
result Performance comparable to fully supervised methods, better than semi-supervised alternatives.
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not…
Enhances interpretability of linear latent spaces through automated clustering and ranking.
problem Severe interpretability issues in latent directions of PCA, ICA, CCA, and FA.
method LS-PIE framework automates clustering and ranking of latent vectors.
result Enhanced interpretability of latent vectors through LR, LS, LC, and LCON.
This work improves speech enhancement using multiple GAN generators in stages.
problem Efficient speech enhancement using GANs with multiple stages.
method Multiple GAN generators in a chained multi-stage approach, with two scenarios: shared or independent parameters.
result Multi-stage SEGAN outperforms one-stage SEGAN, with independent generators yielding better results.
Enhanced FastMNMF for better speech separation.
problem Improving blind source separation for speech.
method Gaussian scale mixture (GSM) for heavy-tailed distributions.
result GSM-FastMNMF outperforms existing methods in speech enhancement.
We study a generalization of the Heston model, which consists of two coupled stochastic differential equations, one for the stock price and the other one for the volatility. We consider a cubic nonlinearity in the first equation and a correlation between the two Wiener processes, which model the two white noise sources…
SETrLUSI combines diverse knowledge from multiple domains for faster convergence.
problem Handling diverse knowledge from multiple domains in transfer learning.
method Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invariant (SETrLUSI).
result SETrLUSI accelerates convergence and outperforms related methods.
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.
Enhances adversarial example transferability by fine-tuning existing examples.
problem Adversarial examples are often overfit to a source model, limiting black-box transferability.
method Intermediate Level Attack (ILA) fine-tunes adversarial examples on a pre-specified layer of the source model.
result ILAs achieve high transferability to target models without knowledge of their architecture.
A decentralized approach for multi-source domain adaptation.
problem Transfer knowledge from multiple related domains to an unlabeled target domain.
method Federated Dataset Dictionary Learning (FedDaDiL) framework, eliminating central server, using Wasserstein barycenters.
result Our decentralized approach effectively adapts source domains to an unlabeled target domain.
Enhances RL in target domains with limited data using augmented return.
problem Utilize data from an accessible source domain to improve policy learning in a target domain with scarce data.
method Return Augmented Decision Transformer (REAG) method, which augments the return in the source domain to align with the target domain's optimal trajectory distribution.
result The proposed REAG method achieves the same level of suboptimality as without a dynamics shift, enhancing DT type frameworks' performance in off-dynamics RL.
AR-Flow VAE improves blind source separation with flexible autoregressive priors.
problem Unsupervised blind source separation of latent signals from mixtures.
method AR-Flow VAE uses autoregressive flows to model latent sources, enhancing flexibility and capturing complex dependencies.
result AR-Flow VAE effectively separates latent sources, demonstrating improved performance over conventional methods.
Proposes Textual Echo Cancellation to improve speech recognition.
problem Improving speech recognition performance and user experience for smart devices.
method A novel sequence-to-sequence model with multi-source attention that processes both the microphone mixture signal and source text of TTS playback.
result Demonstrates enhanced speech recognition performance and reduced latency.
Neural networks enhance relation extraction from biomedical literature.
problem Automated extraction of relations between biomedical concepts.
method Use of multichannel architectures in deep neural networks with biomedical ontologies.
result State-of-the-art results in relation extraction tasks.
Enhances KWS in vehicles with multi-source fusion.
problem Improving precision and recall rates in vehicle keyword spotting.
method Integrates vehicle information into a DNN for speech classification and selects optimal sensitivity parameters.
result Significantly improved performance metrics (precision, recall, MSE) compared to baseline.
Paper proposes a method to enhance low-quality retinal images using optimal transport.
problem Artifacts and imperfections in retinal images lead to diagnostic inaccuracies.
method Leveraging optimal transport theory, an unpaired image-to-image translation scheme is proposed.
result The method improves perceptually and quantitatively the quality of low-quality retinal images.
Study shows diverse data sources improve cryptocurrency forecasting models.
problem Improving cryptocurrency market forecasting accuracy.
method Integrating various data types, including on-chain metrics, traditional indices, and macroeconomic indicators.
result Data source diversity significantly enhances forecasting model performance.
Paper proposes a transfer learning method for improving matrix completion.
problem Improving estimation of a low-rank target matrix using auxiliary data.
method Transfer learning procedure leveraging prior information on favorable source datasets.
result Method outperforms traditional methods when source datasets are close to the target matrix.
Gradient-enhanced deep GPs improve multifidelity model accuracy.
problem Improving accuracy in multifidelity models using gradient data.
method Extending deep Gaussian processes to incorporate gradient data.
result Gradient-enhanced deep GP outperforms other models in predicting aerodynamic coefficients.
This study predicts parking availability using multi-source data and a self-supervised learning enhanced transformer.
problem Accurate parking availability prediction to support urban planning and management.
method Proposes SST-iTransformer, a self-supervised learning enhanced spatio-temporal inverted transformer, integrating multi-source data.
result SST-iTransformer achieves state-of-the-art performance in parking availability prediction.
Study uses open data to improve traffic emissions estimation.
problem Estimating accurate link level traffic emissions.
method Data-driven framework integrating MOVES, GPS, OSM, and satellite imagery.
result Neural network reduces RMSE by over 50% for key pollutants.
A new framework enhances binaural audio for moving talkers.
problem Real-time binaural audio enhancement for moving sound sources.
method Mixture-of-experts framework combining multiple binaural filters.
result Dynamic spatial audio rendering adapts to moving talkers.
Proposes robust ITRs integrating multiple datasets to handle posterior shift.
problem Posterior shift in conditional outcome distributions between source and target populations.
method Distributionally robust approach with closed-form solution and adaptive uncertainty tuning.
result Achieves superior performance compared to existing methods in simulations and real-data applications.
Unsupervised method constructs knowledge graph from text and code.
problem Lack of structured knowledge in scientific literature and code.
method Word embedding, clustering, and dimensionality reduction techniques.
result Enhanced understanding of scientific literature and code.
New layers estimate complex time-frequency masks without phase wrapping issues.
problem Lack of phase estimation in deep learning-based speech enhancement and source separation.
method Proposes magbook, phasebook, and combook layers for complex mask estimation.
result Match state-of-the-art performance on speaker separation datasets.
SAGDA generates synthetic agricultural datasets to improve ML in African farming.
problem Data scarcity in African agriculture limits machine learning innovations.
method SAGDA is an open-source Python toolkit that generates, augments, and validates synthetic agricultural datasets.
result SAGDA enhances ML applications in agriculture, such as yield prediction and fertilizer recommendation.
Advanced deep learning model improves speech enhancement by estimating phase accurately.
problem Difficulty in estimating the phase of clean speech in speech enhancement.
method Proposes Deep Complex U-Net, polar coordinate-wise complex-valued masking, and wSDR loss function.
result Achieves state-of-the-art performance in all metrics, outperforming previous approaches.
Enhances insurance loss models using InsurTech data and machine learning.
problem Traditional insurance loss models lack predictive accuracy due to limited data sources.
method Combining proprietary claims data with InsurTech data and applying machine learning techniques.
result Improved predictive accuracy of the loss model through machine learning.
A new speech enhancement method using variational autoencoders.
problem Improving speech quality in noisy environments.
method Using a variational autoencoder as a speech model, trained with unsupervised noise modeling.
result The method outperforms existing techniques in speech enhancement.
Paper introduces RiskEmbed, a finetuned model for financial risk management.
problem Improving retrieval accuracy in financial question-answering systems.
method Curated dataset and finetuned BERT model for financial domain.
result RiskEmbed significantly outperforms general-purpose and financial embedding models.
This paper examines risks and uncertainties of changing data sources in machine learning for official statistics.
problem Risks and uncertainties associated with changing data sources in machine learning for official statistics.
method An overview of risks, causes, and repercussions of changing data sources, with a checklist of measures.
result Maintaining integrity, reliability, consistency, and relevance in official statistics.
FinRobot opens-source AI for financial tasks, breaking down complex problems.
problem Barriers to AI adoption in finance due to proprietary data and specialized knowledge.
method Develops open-source AI agent platform with four layers: Financial AI Agents, LLM Algorithms, LLMOps/DataOps, and Foundation Models.
result FinRobot democratizes AI access for financial analysis.
This paper benchmarks FinGPT for financial datasets using open-source large language models.
problem Challenges in integrating GPT-based models with financial datasets.
method Instruction Tuning paradigm for open-source large language models adapted for financial contexts.
result Demonstrates the effectiveness and adaptability of FinGPT in financial tasks.
Develops techniques to align word embeddings from different sources.
problem Aligning word embeddings from diverse datasets or methods.
method Simple closed-form techniques for optimal rotation, translation, and scaling.
result Maximizes cosine similarity and minimizes root mean squared errors.