Search Results for author:
Found 23 papers, 9 papers with code
Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era
The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation.
Investigating Effective Speaker Property Privacy Protection in Federated Learning for Speech Emotion Recognition
To this end, this paper focuses on investigating the security of FL for SER concerning property inference attacks.
Optimizing Cox Models with Stochastic Gradient Descent: Theoretical Foundations and Practical Guidances
We establish that the SGD estimator for the Cox neural network (Cox-NN) is consistent and achieves the optimal minimax convergence rate up to a polylogarithmic factor.
Speech Emotion Recognition under Resource Constraints with Data Distillation
Speech emotion recognition (SER) plays a crucial role in human-computer interaction.
A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures
As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies.
STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition
Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction.
A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era
This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis.
Cutting Through the Noise: An Empirical Comparison of Psychoacoustic and Envelope-based Features for Machinery Fault Detection
We train a state-of-the-art one-class-classifier, on samples from healthy motors and separate the faulty ones for fault detection using a threshold.
Efficient ECG-based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks
Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke.
Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning
Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance compared to models with speech samples only and those using classic transfer learning strategies.
A Survey of Machine Unlearning
Specifically, as a category collection of cutting-edge studies, the intention behind this article is to serve as a comprehensive resource for researchers and practitioners seeking an introduction to machine unlearning and its formulations, design criteria, removal requests, algorithms, and applications.
Towards KAB2S: Learning Key Knowledge from Single-Objective Problems to Multi-Objective Problem
As "a new frontier in evolutionary computation research", evolutionary transfer optimization(ETO) will overcome the traditional paradigm of zero reuse of related experience and knowledge from solved past problems in researches of evolutionary computation.
Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19.
Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition
The proposed framework consists of i) federated learning for data privacy, and ii) adversarial training at the training stage and randomisation at the testing stage for model robustness.
Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
High-dimensional neural recordings across multiple brain regions can be used to establish functional connectivity with good spatial and temporal resolution.
Covariance-engaged Classification of Sets via Linear Programming
The convergence rates of estimation errors and risk of the CLIPS classifier are established to show that having multiple observations in a set leads to faster convergence rates, compared to the standard classification situation in which there is only one observation in the set.
An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety.
EmoBed: Strengthening Monomodal Emotion Recognition via Training with Crossmodal Emotion Embeddings
Motivated by this, we propose a novel crossmodal emotion embedding framework called EmoBed, which aims to leverage the knowledge from other auxiliary modalities to improve the performance of an emotion recognition system at hand.
AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition
The Audio/Visual Emotion Challenge and Workshop (AVEC 2019) "State-of-Mind, Detecting Depression with AI, and Cross-cultural Affect Recognition" is the ninth competition event aimed at the comparison of multimedia processing and machine learning methods for automatic audiovisual health and emotion analysis, with all participants competing strictly under the same conditions.
User-Friendly Covariance Estimation for Heavy-Tailed Distributions
We offer a survey of recent results on covariance estimation for heavy-tailed distributions.
Methodology Statistics Theory Statistics Theory
Tuning-Free Heterogeneity Pursuit in Massive Networks
Heterogeneity is often natural in many contemporary applications involving massive data.
Sparse CCA via Precision Adjusted Iterative Thresholding
Sparse Canonical Correlation Analysis (CCA) has received considerable attention in high-dimensional data analysis to study the relationship between two sets of random variables.
Asymptotic normality and optimalities in estimation of large Gaussian graphical models
This paper considers a fundamental question: When is it possible to estimate low-dimensional parameters at parametric square-root rate in a large Gaussian graphical model?
