Search

Previous approaches on accent conversion (AC) mainly aimed at making non-native speech sound more native while maintaining the original content and speaker identity. However, non-native speakers sometimes have pronunciation issues, which can make it difficult for listeners to understand them. Hence, we developed a new AC approach that not only focuses on accent conversion but also improves pronunciation of non-native accented speaker. By providing the non-native audio and the corresponding transcript, we generate the ideal ground-truth audio with native-like pronunciation with original duration and prosody. This ground-truth data aids the model in learning a direct mapping between accented and native speech. We utilize the end-to-end VITS framework to achieve high-quality waveform reconstruction for the AC task. As a result, our system not only produces audio that closely resembles native accents and while retaining the original speaker's identity but also improve pronunciation, as demonstrated by evaluation results., Comment: Submitted to ICASSP 2025

In this paper, we report on communication experiments conducted in the summer of 2022 during a deep dive to the wreck of the Titanic. Radio transmission is not possible in deep sea water, and communication links rely on sonar signals. Due to the low bandwidth of sonar signals and the need to communicate readable data, text messaging is used in deep-sea missions. In this paper, we report results and experiences from a messaging system that converts speech to text in a submarine, sends text messages to the surface, and reconstructs those messages as synthetic lip-synchronous videos of the speakers. The resulting system was tested during an actual dive to Titanic in the summer of 2022. We achieved an acceptable latency for a system of such complexity as well as good quality. The system demonstration video can be found at the following link: https://youtu.be/C4lyM86-5Ig

With the rise of SSL and ASR technologies, the Wav2Vec2 ASR-based model has been fine-tuned for automated speech disorder quality assessment tasks, yielding impressive results and setting a new baseline for Head and Neck Cancer speech contexts. This demonstrates that the ASR dimension from Wav2Vec2 closely aligns with assessment dimensions. Despite its effectiveness, this system remains a black box with no clear interpretation of the connection between the model ASR dimension and clinical assessments. This paper presents the first analysis of this baseline model for speech quality assessment, focusing on intelligibility and severity tasks. We conduct a layer-wise analysis to identify key layers and compare different SSL and ASR Wav2Vec2 models based on pre-trained data. Additionally, post-hoc XAI methods, including Canonical Correlation Analysis (CCA) and visualization techniques, are used to track model evolution and visualize embeddings for enhanced interpretability., Comment: Accepted at the Spoken Language Technology (SLT) Conference 2024

DNA-based data storage has been attracting significant attention due to its extremely high density, low power consumption, and long duration compared to traditional data storage mediums. Despite the recent advancements in DNA data storage technology, significant challenges remain. In particular, various types of errors can occur during the processes of DNA synthesis, storage, and sequencing, including substitution errors, insertion errors, and deletion errors. Furthermore, the entire oligo may be lost. In this work, we report a DNA-based data storage architecture that incorporates efficient channel coding schemes, including different types of error-correcting codes (ECCs) and constrained codes, for both the inner coding and outer coding for the DNA data storage channel. We also carry out large scale experiments to validate our proposed DNA data storage architecture. Specifically, 1.61 and 1.69 MB data are encoded into 30,000 oligos each, with information densities of 1.731 and 1.815, respectively. It has been found that the stored information can be fully recovered without any error at average coverages 4.5 and 6.0, respectively. Compared to previous experimental studies, our architecture achieves higher information density and lower coverage, demonstrating the efficiency of the proposed channel coding schemes.

The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues. Our approach utilizes discrete units, derived from clustering self-supervised representations of native speech, as an intermediary target for accent conversion. Leveraging multi-speaker text-to-speech synthesis, it transforms these discrete representations back into native speech while retaining the speaker identity. Additionally, we develop an efficient data augmentation method to train the system without demanding a lot of non-native resources. Our system is proved to improve non-native speaker fluency, sound like a native accent, and preserve original speaker identity well., Comment: Accepted at Syndata4genAI

We prove that multilevel Picard approximations are capable of approximating solutions of semilinear heat equations in $L^{p}$-sense, ${p}\in [2,\infty)$, in the case of gradient-dependent, Lipschitz-continuous nonlinearities, in the sense that the computational effort of the multilevel Picard approximations grow at most polynomially in both the dimension $d$ and the reciprocal $1/\epsilon$ of the prescribed accuracy $\epsilon$., Comment: 23 pages, 2 figures

We prove that multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation are capable of approximating solutions of semilinear Kolmogorov PDEs in $L^\mathfrak{p}$-sense, $\mathfrak{p}\in [2,\infty)$, in the case of gradient-independent, Lipschitz-continuous nonlinearities, while the computational effort of the multilevel Picard approximations and the required number of parameters in the neural networks grow at most polynomially in both dimension $d\in \mathbb{N}$ and reciprocal of the prescribed accuracy $\epsilon$.

Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objective evaluation of these specialized LLM models. Leveraging a recent initiative to curate high-quality astronomical MCQs, this study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. We demonstrate that this performance degradation can be partially mitigated by utilizing high-quality data for continual pretraining, such as summarized text from arXiv. Despite the observed catastrophic forgetting in smaller models, our results indicate that continual pretraining on the 70B model can yield significant improvements. However, the current supervised fine-tuning dataset still constrains the performance of instruct models. In conjunction with this study, we introduce a new set of models, AstroLLaMA-3-8B and AstroLLaMA-2-70B, building upon the previous AstroLLaMA series., Comment: 10 pages, 1 figure, 1 table, accepted to AI4S: The 5th Workshop on Artificial Intelligence and Machine Learning for Scientific Applications at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC24). Models will be released at https://huggingface.co/AstroMLab. AstroMLab homepage: https://astromlab.org/

Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.

We consider a novel active learning problem motivated by the need of learning machine learning models for health monitoring in wireless body area network (WBAN). Due to the limited resources at body sensors, collecting each unlabeled sample in WBAN incurs a nontrivial cost. Moreover, training health monitoring models typically requires labels indicating the patient's health state that need to be generated by healthcare professionals, which cannot be obtained at the same pace as data collection. These challenges make our problem fundamentally different from classical active learning, where unlabeled samples are free and labels can be queried in real time. To handle these challenges, we propose a two-phased active learning method, consisting of an online phase where a coreset construction algorithm is proposed to select a subset of unlabeled samples based on their noisy predictions, and an offline phase where the selected samples are labeled to train the target model. The samples selected by our algorithm are proved to yield a guaranteed error in approximating the full dataset in evaluating the loss function. Our evaluation based on real health monitoring data and our own experimentation demonstrates that our solution can drastically save the data curation cost without sacrificing the quality of the target model.

This paper introduces SHANGUS, an advanced framework combining Deep Reinforcement Learning (DRL) with heuristic optimization to improve frontier-based exploration efficiency in unknown environments, particularly for intelligent vehicles in autonomous air services, search and rescue operations, and space exploration robotics. SHANGUS harnesses DRL's adaptability and heuristic prioritization, markedly enhancing exploration efficiency, reducing completion time, and minimizing travel distance. The strategy involves a frontier selection node to identify unexplored areas and a DRL navigation node using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm for robust path planning and dynamic obstacle avoidance. Extensive experiments in ROS2 and Gazebo simulation environments show SHANGUS surpasses representative traditional methods like the Nearest Frontier (NF), Novel Frontier-Based Exploration Algorithm (CFE), and Goal-Driven Autonomous Exploration (GDAE) algorithms, especially in complex scenarios, excelling in completion time, travel distance, and exploration rate. This scalable solution is suitable for real-time autonomous navigation in fields such as industrial automation, autonomous driving, household robotics, and space exploration. Future research will integrate additional sensory inputs and refine heuristic functions to further boost SHANGUS's efficiency and robustness.

We present a comprehensive evaluation of proprietary and open-weights large language models using the first astronomy-specific benchmarking dataset. This dataset comprises 4,425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics, covering a broad range of astrophysical topics. Our analysis examines model performance across various astronomical subfields and assesses response calibration, crucial for potential deployment in research environments. Claude-3.5-Sonnet outperforms competitors by up to 4.6 percentage points, achieving 85.0% accuracy. For proprietary models, we observed a universal reduction in cost every 3-to-12 months to achieve similar score in this particular astronomy benchmark. Open-source models have rapidly improved, with LLaMA-3-70b (80.6%) and Qwen-2-72b (77.7%) now competing with some of the best proprietary models. We identify performance variations across topics, with non-English-focused models generally struggling more in exoplanet-related fields, stellar astrophysics, and instrumentation related questions. These challenges likely stem from less abundant training data, limited historical context, and rapid recent developments in these areas. This pattern is observed across both open-weights and proprietary models, with regional dependencies evident, highlighting the impact of training data diversity on model performance in specialized scientific domains. Top-performing models demonstrate well-calibrated confidence, with correlations above 0.9 between confidence and correctness, though they tend to be slightly underconfident. The development for fast, low-cost inference of open-weights models presents new opportunities for affordable deployment in astronomy. The rapid progress observed suggests that LLM-driven research in astronomy may become feasible in the near future., Comment: 45 pages, 12 figures, 7 tables. Submitted to ApJ. Comments welcome. AstroMLab homepage: https://astromlab.org/

With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with high dimensionality. Recent unsupervised ML-IDS approaches such as AutoEncoders and Generative Adversarial Networks (GAN) offer alternative solutions but pose challenges in deployment onto resource-constrained IoT devices and in interpretability. To address these concerns, this paper proposes a novel federated unsupervised anomaly detection framework, FedPCA, that leverages Principal Component Analysis (PCA) and the Alternating Directions Method Multipliers (ADMM) to learn common representations of distributed non-i.i.d. datasets. Building on the FedPCA framework, we propose two algorithms, FEDPE in Euclidean space and FEDPG on Grassmann manifolds. Our approach enables real-time threat detection and mitigation at the device level, enhancing network resilience while ensuring privacy. Moreover, the proposed algorithms are accompanied by theoretical convergence rates even under a subsampling scheme, a novel result. Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to nonlinear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks., Comment: Accepted for publication at IEEE/ACM Transactions on Networking

Given the rising urban population and the consequential rise in traffic congestion, the implementation of smart parking systems has emerged as a critical matter of concern. Smart parking solutions use cameras, sensors, and algorithms like computer vision to find available parking spaces. This method improves parking place recognition, reduces traffic and pollution, and optimizes travel time. In recent years, computer vision-based approaches have been widely used. However, most existing studies rely on manually labeled parking spots, which has implications for the cost and practicality of implementation. To solve this problem, we propose a novel approach PakLoc, which automatically localize parking spots. Furthermore, we present the PakSke module, which automatically adjust the rotation and the size of detected bounding box. The efficacy of our proposed methodology on the PKLot dataset results in a significant reduction in human labor of 94.25\%. Another fundamental aspect of a smart parking system is its capacity to accurately determine and indicate the state of parking spots within a parking lot. The conventional approach involves employing classification techniques to forecast the condition of parking spots based on the bounding boxes derived from manually labeled grids. In this study, we provide a novel approach called PakSta for identifying the state of parking spots automatically. Our method utilizes object detector from PakLoc to simultaneously determine the occupancy status of all parking lots within a video frame. Our proposed method PakSta exhibits a competitive performance on the PKLot dataset when compared to other classification methods.

In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s forward-facing camera. We concentrate in building a robust model which performs well across various domains of different outdoor situations such as sunny, snowy, rainy, etc. In particular, our method is developed with two main directions: model development and domain adaptation. In model development, we use the High Resolution Network (HRNet) as the baseline. Then, this baseline s result is processed by two coarse-to-fine models: Object-Contextual Representations (OCR) and Hierarchical Multi-scale Attention (HMA) to get the better robust feature. For domain adaption, we implement the Domain-Based Batch Normalization (DNB) to reduce the distribution shift from diverse domains. Our proposed method yield 81.259 mean intersection-over-union (mIoU) in validation set. This paper studies the effectiveness of employing real-world and synthetic data to handle the domain adaptation in semantic segmentation problem., Comment: 13 pages

Despite the promise of Federated Learning (FL) for privacy-preserving model training on distributed data, it remains susceptible to backdoor attacks. These attacks manipulate models by embedding triggers (specific input patterns) in the training data, forcing misclassification as predefined classes during deployment. Traditional single-trigger attacks and recent work on cooperative multiple-trigger attacks, where clients collaborate, highlight limitations in attack realism due to coordination requirements. We investigate a more alarming scenario: non-cooperative multiple-trigger attacks. Here, independent adversaries introduce distinct triggers targeting unique classes. These parallel attacks exploit FL's decentralized nature, making detection difficult. Our experiments demonstrate the alarming vulnerability of FL to such attacks, where individual backdoors can be successfully learned without impacting the main task. This research emphasizes the critical need for robust defenses against diverse backdoor attacks in the evolving FL landscape. While our focus is on empirical analysis, we believe it can guide backdoor research toward more realistic settings, highlighting the crucial role of FL in building robust defenses against diverse backdoor threats. The code is available at \url{https://anonymous.4open.science/r/nba-980F/}.

Billions of organic molecules are known, but only a tiny fraction of the functional inorganic materials have been discovered, a particularly relevant problem to the community searching for new quantum materials. Recent advancements in machine-learning-based generative models, particularly diffusion models, show great promise for generating new, stable materials. However, integrating geometric patterns into materials generation remains a challenge. Here, we introduce Structural Constraint Integration in the GENerative model (SCIGEN). Our approach can modify any trained generative diffusion model by strategic masking of the denoised structure with a diffused constrained structure prior to each diffusion step to steer the generation toward constrained outputs. Furthermore, we mathematically prove that SCIGEN effectively performs conditional sampling from the original distribution, which is crucial for generating stable constrained materials. We generate eight million compounds using Archimedean lattices as prototype constraints, with over 10% surviving a multi-staged stability pre-screening. High-throughput density functional theory (DFT) on 26,000 survived compounds shows that over 50% passed structural optimization at the DFT level. Since the properties of quantum materials are closely related to geometric patterns, our results indicate that SCIGEN provides a general framework for generating quantum materials candidates., Comment: 512 pages total, 4 main figures + 218 supplementary figures

We argue that the long-standing issues of neutrino mass and dark matter can be manifestly solved in a dark gauge symmetry $U(1)_D$ that transforms nontrivially only for three right-handed neutrinos $\nu_{1,2,3R}$ -- the counterparts of known left-handed neutrinos. This theory assigns $\nu_{1,2,3R}$ dark charge to be $D=0$, $-1$, and $+1$, respectively, in order for anomaly cancelation. Additionally, it imposes an inert Higgs doublet $\eta$ and two Higgs singlets $\xi,\phi$ with dark charge $D=+1$, $-1$, and $+2$, respectively. That said, the dark symmetry is broken by $\phi$ (by two units) down to a dark parity $P_D=(-1)^D$, for which $\nu_{2,3R}$ and $\eta,\xi$ are odd, whereas all other fields are even due to $D=0$. The lightest of these odd fields is stabilized by $P_D$, responsible for dark matter. Neutrino masses are generated by a scotoseesaw scheme, in which the seesaw part is mediated by $\nu_{1R}$, while the scotogenic part is mediated by $\nu_{2,3R}$, for which the hierarchy of atmospheric and solar neutrino mass splittings is explained., Comment: 14 pages, 2 figures, 1 table

Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head self-attention (MHSA) in the Transformer model, which learns the temporal relationship of each input token. However, artifacts of synthetic speech can be located in specific regions of both frequency channels and temporal segments, while MHSA neglects this temporal-channel dependency of the input sequence. In this work, we proposed a Temporal-Channel Modeling (TCM) module to enhance MHSA's capability for capturing temporal-channel dependencies. Experimental results on the ASVspoof 2021 show that with only 0.03M additional parameters, the TCM module can outperform the state-of-the-art system by 9.25% in EER. Further ablation study reveals that utilizing both temporal and channel information yields the most improvement for detecting synthetic speech., Comment: Accepted by INTERSPEECH 2024

Optical properties in solids, such as refractive index and absorption, hold vast applications ranging from solar panels to sensors, photodetectors, and transparent displays. However, first-principles computation of optical properties from crystal structures is a complex task due to the high convergence criteria and computational cost. Recent progress in machine learning shows promise in predicting material properties, yet predicting optical properties from crystal structures remains challenging due to the lack of efficient atomic embeddings. Here, we introduce GNNOpt, an equivariance graph-neural-network architecture featuring automatic embedding optimization. This enables high-quality optical predictions with a dataset of only 944 materials. GNNOpt predicts all optical properties based on the Kramers-Kr{\"o}nig relations, including absorption coefficient, complex dielectric function, complex refractive index, and reflectance. We apply the trained model to screen photovoltaic materials based on spectroscopic limited maximum efficiency and search for quantum materials based on quantum weight. First-principles calculations validate the efficacy of the GNNOpt model, demonstrating excellent agreement in predicting the optical spectra of unseen materials. The discovery of new quantum materials with high predicted quantum weight, such as SiOs which hosts exotic quasiparticles, demonstrates GNNOpt's potential in predicting optical properties across a broad range of materials and applications., Comment: (i) Completely Rewritten Manuscript, including 5 main figures and 1 table. (ii) Supplementary Information, including 15 supplementary figures and 2 tables

Unlocking the vast potential of optical sensing technology has long been hindered by the challenges of achieving fast, sensitive, and broadband photodetection at ambient temperatures. In this review, we summarize recent progress in the study of nonlinear photocurrent in topological quantum materials, and its application in broadband photodetection without the use of p-n junction based semiconductor diodes. The intrinsic quadratic transverse current-input voltage relation is used to rectify the alternating electric field from incident radio, terahertz or infrared waves into a direct current, without a bias voltage and at zero magnetic field. We review novel photocurrents in several material systems, including topological Weyl semimetals, chiral crystals, ferroelectric materials, and low dimensional topological insulators. These quantum materials hold tremendous promise for broadband high-frequency rectification and photodetection, featuring substantial responsivity and detectivity., Comment: Review article, 24 pages + 19 figures

Best Response Dynamics (BRD) is a class of strategy updating rules to find Pure Nash Equilibria (PNE) in a game. At each step, a player is randomly picked, and the player switches to a "best response" strategy based on the strategies chosen by others, so that the new strategy profile maximises their payoff. If no such strategy exists, a different player will be chosen randomly. When no player wants to change their strategy anymore, the process reaches a PNE and will not deviate from it. On the other hand, either PNE may not exist, or BRD could be "trapped" within a subgame that has no PNE. We consider a random game with $N$ players, each with two actions available, and i.i.d. payoffs, in which the payoff distribution may have an atom, i.e. ties are allowed. We study a class of random walks in a random medium on the $N$-dimensional hypercube induced by the random game. The medium contains two types of obstacles corresponding to PNE and traps. The class of processes we analyze includes BRD, simple random walks on the hypercube, and many other nearest neighbour processes. We prove that, with high probability, these processes reach a PNE before hitting any trap., Comment: 20 pages, 4 figures, 1 table

Federated Learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effectiveness of client updates by dividing the network into smaller partitions, or cohorts. We introduce Cohort-Parallel Federated Learning (CPFL): a novel learning approach where each cohort independently trains a global model using FL, until convergence, and the produced models by each cohort are then unified using one-shot Knowledge Distillation (KD) and a cross-domain, unlabeled dataset. The insight behind CPFL is that smaller, isolated networks converge quicker than in a one-network setting where all nodes participate. Through exhaustive experiments involving realistic traces and non-IID data distributions on the CIFAR-10 and FEMNIST image classification tasks, we investigate the balance between the number of cohorts, model accuracy, training time, and compute and communication resources. Compared to traditional FL, CPFL with four cohorts, non-IID data distribution, and CIFAR-10 yields a 1.9$\times$ reduction in train time and a 1.3$\times$ reduction in resource usage, with a minimal drop in test accuracy.

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that achieve full accuracy recovery for fine-tuning tasks at up to 70% sparsity. We achieve this for the LLaMA-2 7B model by combining the SparseGPT one-shot pruning method and sparse pretraining of those models on a subset of the SlimPajama dataset mixed with a Python subset of The Stack dataset. We exhibit training acceleration due to sparsity on Cerebras CS-3 chips that closely matches theoretical scaling. In addition, we establish inference acceleration of up to 3x on CPUs by utilizing Neural Magic's DeepSparse engine and 1.7x on GPUs through Neural Magic's nm-vllm engine. The above gains are realized via sparsity alone, thus enabling further gains through additional use of quantization. Specifically, we show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x. We demonstrate these results across diverse, challenging tasks, including chat, instruction following, code generation, arithmetic reasoning, and summarization to prove their generality. This work paves the way for rapidly creating smaller and faster LLMs without sacrificing accuracy.

Federated Recommendation (FedRec) systems have emerged as a solution to safeguard users' data in response to growing regulatory concerns. However, one of the major challenges in these systems lies in the communication costs that arise from the need to transmit neural network models between user devices and a central server. Prior approaches to these challenges often lead to issues such as computational overheads, model specificity constraints, and compatibility issues with secure aggregation protocols. In response, we propose a novel framework, called Correlated Low-rank Structure (CoLR), which leverages the concept of adjusting lightweight trainable parameters while keeping most parameters frozen. Our approach substantially reduces communication overheads without introducing additional computational burdens. Critically, our framework remains fully compatible with secure aggregation protocols, including the robust use of Homomorphic Encryption. The approach resulted in a reduction of up to 93.75% in payload size, with only an approximate 8% decrease in recommendation performance across datasets. Code for reproducing our experiments can be found at https://github.com/NNHieu/CoLR-FedRec., Comment: 12 pages, 6 figures, 4 tables

This study advanced tele-operations in Advanced Air Mobility (AAM) through the creation of a Vehicle Digital Twin (VDT) system for eVTOL aircraft, tailored to enhance remote control safety and efficiency, especially for Beyond Visual Line of Sight (BVLOS) operations. By synergizing digital twin technology with immersive Virtual Reality (VR) interfaces, we notably elevate situational awareness and control precision for remote operators. Our VDT framework integrates immersive tele-operation with a high-fidelity aerodynamic database, essential for authentically simulating flight dynamics and control tactics. At the heart of our methodology lies an eVTOL's high-fidelity digital replica, placed within a simulated reality that accurately reflects physical laws, enabling operators to manage the aircraft via a master-slave dynamic, substantially outperforming traditional 2D interfaces. The architecture of the designed system ensures seamless interaction between the operator, the digital twin, and the actual aircraft, facilitating exact, instantaneous feedback. Experimental assessments, involving propulsion data gathering, simulation database fidelity verification, and tele-operation testing, verify the system's capability in precise control command transmission and maintaining the digital-physical eVTOL synchronization. Our findings underscore the VDT system's potential in augmenting AAM efficiency and safety, paving the way for broader digital twin application in autonomous aerial vehicles.

Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification, largely due to data scarcity. To deal with this challenge, current works tend to segment patients' audio files into many samples to augment the datasets. Nevertheless, this approach has limitations, as it indirectly relates overall audio scores to individual segments. This paper introduces a novel approach where the system learns at the audio level instead of segments despite data scarcity. This paper proposes to use the pre-trained Wav2Vec2 architecture for both SSL, and ASR as feature extractor in speech assessment. Carried out on the HNC dataset, our ASR-driven approach established a new baseline compared with other approaches, obtaining average $MSE=0.73$ and $MSE=1.15$ for the prediction of intelligibility and severity scores respectively, using only 95 training samples. It shows that the ASR based Wav2Vec2 model brings the best results and may indicate a strong correlation between ASR and speech quality assessment. We also measure its ability on variable segment durations and speech content, exploring factors influencing its decision., Comment: Accepted at LREC-COLING 2024

Most domain adaptation (DA) methods are based on either a convolutional neural networks (CNNs) or a vision transformers (ViTs). They align the distribution differences between domains as encoders without considering their unique characteristics. For instance, ViT excels in accuracy due to its superior ability to capture global representations, while CNN has an advantage in capturing local representations. This fact has led us to design a hybrid method to fully take advantage of both ViT and CNN, called Explicitly Class-specific Boundaries (ECB). ECB learns CNN on ViT to combine their distinct strengths. In particular, we leverage ViT's properties to explicitly find class-specific decision boundaries by maximizing the discrepancy between the outputs of the two classifiers to detect target samples far from the source support. In contrast, the CNN encoder clusters target features based on the previously defined class-specific boundaries by minimizing the discrepancy between the probabilities of the two classifiers. Finally, ViT and CNN mutually exchange knowledge to improve the quality of pseudo labels and reduce the knowledge discrepancies of these models. Compared to conventional DA methods, our ECB achieves superior performance, which verifies its effectiveness in this hybrid model. The project website can be found https://dotrannhattuong.github.io/ECB/website., Comment: Project page: https://dotrannhattuong.github.io/ECB/website, Accepted to CVPR 2024

Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. To address the opaqueness often associated with deep learning (DL) models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax diagnoses made by DL models. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. Method: We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of these explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods with and without our template guidance when explaining two DL models in two real-world datasets. Results: The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. Conclusions: In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving AI explanations. We anticipate that our template guidance will forge a fresh approach to elucidating AI models by integrating clinical domain expertise.

Panoptic segmentation unifies semantic and instance segmentation and thus delivers a semantic class label and, for so-called thing classes, also an instance label per pixel. The differentiation of distinct objects of the same class with a similar appearance is particularly challenging and frequently causes such objects to be incorrectly assigned to a single instance. In the present work, we demonstrate that information on the 3D geometry of the observed scene can be used to mitigate this issue: We present a novel CNN-based method for panoptic segmentation which processes RGB images and depth maps given as input in separate network branches and fuses the resulting feature maps in a late fusion manner. Moreover, we propose a new depth-aware dice loss term which penalises the assignment of pixels to the same thing instance based on the difference between their associated distances to the camera. Experiments carried out on the Cityscapes dataset show that the proposed method reduces the number of objects that are erroneously merged into one thing instance and outperforms the method used as basis by 2.2% in terms of panoptic quality.

Numerical experiments indicate that deep learning algorithms overcome the curse of dimensionality when approximating solutions of semilinear PDEs. For certain linear PDEs and semilinear PDEs with gradient-independent nonlinearities this has also been proved mathematically, i.e., it has been shown that the number of parameters of the approximating DNN increases at most polynomially in both the PDE dimension $d\in \mathbb{N}$ and the reciprocal of the prescribed accuracy $\epsilon\in (0,1)$. The main contribution of this paper is to rigorously prove for the first time that deep neural networks can also overcome the curse dimensionality in the approximation of a certain class of nonlinear PDEs with gradient-dependent nonlinearities.

In this research, the ambient cured one part alkali activated material (AAM) containing graphene nanoplatelets (GNPs), fly ash, slag and silica fume has been investigated after high temperature exposure to 200 to 800oC. Their compressive strength, thermal properties, microstructure, pore structure were characterised through visual observation, isothermal calorimetry, TGA, XRD, SEM-EDS and X-ray CT. The research findings indicated high strength characteristics of the developed AAM (80 MPa) at ambient condition, which could further reach to approx. 100 MPa after being heated up to 400oC. GNPs provided nucleation effects for promoting geopolymerisation and crystallisation. As observed from X-ray CT, a high extent of severe cracks initiated from the core and propagated towards the surface. From SEM-EDS analysis, high Na-Al and Na-Si ratios or low Si-Al and Ca-Si ratios highly correlated to thermal stability. Overall, the research outcomes implied the promising use of the nano-engineered AAMs for thermal energy storage (TES) at 400 to 600oC.

Despite recent progress, large language models (LLMs) still face the challenge of appropriately reacting to the intricacies of social and cultural conventions. This paper presents MANGO, a methodology for distilling high-accuracy, high-recall assertions of cultural knowledge. We judiciously and iteratively prompt LLMs for this purpose from two entry points, concepts and cultures. Outputs are consolidated via clustering and generative summarization. Running the MANGO method with GPT-3.5 as underlying LLM yields 167K high-accuracy assertions for 30K concepts and 11K cultures, surpassing prior resources by a large margin in quality and size. In an extrinsic evaluation for intercultural dialogues, we explore augmenting dialogue systems with cultural knowledge assertions. Notably, despite LLMs inherently possessing cultural knowledge, we find that adding knowledge from MANGO improves the overall quality, specificity, and cultural sensitivity of dialogue responses, as judged by human annotators. Data and code are available for download., Comment: 11 pages, 2 figures, 10 tables, accepted at CIKM '24

Learning at the edges has become increasingly important as large quantities of data are continually generated locally. Among others, this paradigm requires algorithms that are simple (so that they can be executed by local devices), robust (again uncertainty as data are continually generated), and reliable in a distributed manner under network issues, especially delays. In this study, we investigate the problem of online convex optimization under adversarial delayed feedback. We propose two projection-free algorithms for centralised and distributed settings in which they are carefully designed to achieve a regret bound of O(\sqrt{B}) where B is the sum of delay, which is optimal for the OCO problem in the delay setting while still being projection-free. We provide an extensive theoretical study and experimentally validate the performance of our algorithms by comparing them with existing ones on real-world problems.

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which measures the OT distance between a distribution over the source class-conditional distributions and a mixture of source and target data distribution. Our class-aware OT leverages a cost function that determines the matching extent between a given data example and a source class-conditional distribution. By optimizing this cost function, we find the optimal matching between target examples and source class-conditional distributions, effectively addressing the data and label shifts that occur between the two domains. To handle the class-aware OT efficiently, we propose an amortization solution that employs deep neural networks to formulate the transportation probabilities and the cost function. Additionally, we propose minimizing class-aware Higher-order Moment Matching (HMM) to align the corresponding class regions on the source and target domains. The class-aware HMM component offers an economical computational approach for accurately evaluating the HMM distance between the two distributions. Extensive experiments on benchmark datasets demonstrate that our proposed method significantly outperforms existing state-of-the-art baselines., Comment: 18 pages