Abstract

Automatic syllable stress detection is a crucial component in Computer-Assisted Language Learning (CALL) systems for language learners. Current stress detection models are typically trained on clean speech, which may not be robust in real-world scenarios where background noise is prevalent. To address this, speech enhancement (SE) models, designed to enhance speech by removing noise, might be employed, but their impact on preserving syllable stress patterns is not well studied. This study examines how different SE models, representing discriminative and generative modeling approaches, affect syllable stress detection under noisy conditions. We assess these models by applying them to speech data with varying signal-to-noise ratios (SNRs) from 0 to 20 dB, and evaluating their effectiveness in maintaining stress patterns. Additionally, we explore different feature sets to determine which ones are most effective for capturing stress patterns amidst noise. To further understand the impact of SE models, a human-based perceptual study is conducted to compare the perceived stress patterns in SE-enhanced speech with those in clean speech, providing insights into how well these models preserve syllable stress as perceived by listeners. Experiments are performed on English speech data from non-native speakers of German and Italian. And the results reveal that the stress detection performance is robust with the generative SE models when heuristic features are used. Also, the observations from the perceptual study are consistent with the stress detection outcomes under all SE models.

Abstract

This paper presents a novel approach to the design of Delta-Sigma Modulators (DSMs) for Fractional-N Phase Locked Loop (PLL) Frequency Synthesizers by incorporating an approximate adder characterized by near-normal error distribution. Traditional Frequency Synthesizers utilize DSMs that rely on precise adders and Pseudo-Random Binary Sequence (PRBS) generators to provide modulus inputs to multi-modulus frequency dividers for achieving Fractional-N Frequency Synthesis. The inclusion of PRBS is critical in introducing randomness in the DSM's output, thereby mitigating frequency spurs in the output of the synthesizer. In contrast, the proposed DSM design leverages an approximate adder with near-normal error distribution to introduce the required randomness, eliminating the dependency on PRBS. This innovative design leads to substantial improvements in power efficiency, area, processing speed and improves the performance of the synthesizer. The proposed design demonstrates a reduction of approximately 44.7% in power consumption and 39.73% in area compared to conventional DSMs combined with PRBS generators when implemented in 65nm TSMC technology. The proposed design achieves comparable accuracy in output frequency, maintains similar Signal-to-Noise Ratio (SNR) and Effective Number of Bits (ENOB), and shows improvement in Spurious-Free Dynamic Range (SFDR).

Abstract

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results.

Abstract

We propose a data-driven method for direction-of-arrival (DOA) trajectory estimation. We use a deep complex architecture which leverages complex-valued representations to capture both magnitude and phase information in the received sensor array data. The network is designed to output the DOA trajectory parameters and amplitudes of the strongest source. Deviating from conventional methods, which attempt to estimate parameters for all sources simultaneously -- leading to assignment ambiguity and the problem of uncertain output dimensions, we adopt a sequential approach. The estimated source signal contribution is subtracted from the input to obtain a residual signal. This residual signal is then fed back into the network to identify the next strongest source and so on, making the proposed network reusable. We evaluate our network on simulated data of varying complexity. Results demonstrate the feasibility of such a reusable network and potential improvements can be explored in future.

Abstract

Time series data related to traffic and air quality are useful indicators for urban planning but they frequently have missing values. Imputation of multi-sensor time series data is thus a vital pre-processing step for forecasting, anomaly detection and other downstream tasks. We develop an efficient architecture – Sparse Attention-based Imputation Network for Time series (SAINT) – which outperforms the state-of- the-art imputation networks. Efficiency is achieved by separating the computations on the space-time product graph sequentially into channel independent temporal attention and sparse space-time transformer. This channel independent network can reduce overfitting to effectively repre- sent general temporal patterns. Sparse space-time transformer performs message passing on the spatial graph conditioned on time. We consider real-world datasets for evaluation – PEMS-BAY, METR-LA and AQI – which are gathered from sensor networks in major cities. We demonstrate the effectiveness and robustness of SAINT across complex missing data scenarios. Additionally, SAINT generalizes well to short-term forecasting and is practical for long-term forecasting with limited resources.

Abstract

Besides global attention on extreme precipitation, a limited research has been done in the Arctic due to constraints of data availability. In this backdrop, we attempt to analyze extreme precipitation events at three Arctic stations (Bjørnøya, Ny-Ålesund, and Svalbard Lufthavn) in Svalbard using extreme value theory. The analysis revealed that these high-latitudinal Arctic stations were characterized by heavy-tailed distributions for the exceedances, suggesting a higher probability of the occurrence of extreme precipitation events. Ny-Ålesund and Bjørnøya have exhibited a significant increase in return values over the last three decades. Among the three stations, Ny-Ålesund displayed the strongest return values, especially in winter post-1994 when the atmospheric temperature was characterized by an enhanced positive trend. Significant seasonal variability in return values has also been observed; the fall in Ny-Ålesund was characterized by a low-intensity regime as indicated by the shape parameter. Ny-Ålesund precipitation had shifted from heavy-tailed distribution in pre-1994 to bounded tail distribution post-1994 during spring. Bjørnøya’s extremes are driven by cyclonic circulation, while southerly winds drive extremes in Ny-Ålesund and Svalbard Lufthavn. Even though, Svalbard Lufthavn, displayed regime changes, showed low variability, likely due to its position in a rain shadow region. This research highlights the nuanced responses of Arctic hydrology to warming, emphasizing the need for localized studies and active collaboration with policymakers to translate these insights into effective climate adaptation and mitigation strategies.

Abstract

We present the emergence of topological phase transition in the minimal model of two-dimensional rockpaper- scissors cycle in the form of a doublet chain. The evolutionary dynamics of the doublet chain is obtained by solving the anti-symmetric Lotka-Volterra equation. We show that the mass decays exponentially towards edges and robust against small perturbation in the rate of change of mass transfer, a signature of a topological phase. For one of the configuration of our doublet chain, the mass is transferred towards both edges and the bulk is gaped. Further, we confirm this phase transition within the framework of topological band theory. For this, we calculate the winding number, which change from zero to one for trivial and nontrivial topological phases, respectively.

Abstract

Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing these challenges requires intelligent solutions capable of real-time monitoring, predictive analytics, and adaptive control. This paper proposes an architecture for DigIT, a Digital Twin (DT) platform for Intelligent Transportation Systems (ITS), designed to overcome the limitations of existing frameworks by offering a modular and scalable solution for traffic management. Built on a Domain Concept Model (DCM), the architecture systematically models key ITS components enabling seamless integration of predictive modeling and simulations. The architecture leverages machine learning models to forecast traffic patterns based on historical and real-time data. To adapt to evolving traffic patterns, the architecture incorporates adaptive Machine Learning Operations (MLOps), automating the deployment and lifecycle management of predictive models. Evaluation results highlight the effectiveness of the architecture in delivering accurate predictions and computational efficiency.

Abstract

We introduce a new information-theoretic measure to characterize non-Markovianity in a tripartite quantum state of genuine quantum origin. This measure reveals a novel tripartite quantum correlation and may be interpreted as entanglement between two systems when conditioned on the third (memory) system. We formulate a convex resource-theoretic framework to characterize genuine quantum non-Markovianity in states as a quantum resource and provide operational meaning to this resource in various information processing tasks.

Abstract

The widespread adoption of machine learning on edge devices, such as mobile phones, laptops, IoT devices, etc., has enabled real-time AI applications in resource-constrained environments. Existing solutions for managing computational resources often focus narrowly on accuracy or energy efficiency, failing to adapt dynamically to varying workloads. Furthermore, the existing system lack robust mechanisms to adaptively balance CPU utilization, leading to inefficiencies in resource-constrained scenarios like real-time traffic monitoring. To address these limitations, we propose a self-adaptive approach that optimizes CPU utilization and resource management on edge devices. Our approach, EdgeMLBalancer balances between models through dynamic switching, guided by real-time CPU usage monitoring across processor cores. Tested on real-time traffic data, the approach adapts object detection models based on CPU usage, ensuring efficient resource utilization. The approach leverages epsilon-greedy strategy which promotes fairness and prevents resource starvation, maintaining system robustness. The results of our evaluation demonstrate significant improvements by balancing computational efficiency and accuracy, highlighting the approach's ability to adapt seamlessly to varying workloads. This work lays the groundwork for further advancements in self-adaptation for resource-constrained environments.