In recent decades, researchers have been focused on developing noise-robust methods in order to compensate for noise effects in automatic speech recognition (ASR) systems and enhance their performance. In this paper, we propose a feature-based noise-robust method that employs a novel data analysis technique—robust principal component analysis (RPCA). In the proposed scenario, RPCA is employed to process a noise-corrupted speech feature matrix, and the obtained sparse partition is shown to reveal speech-dominant characteristics. One apparent advantage of using RPCA for enhancing noise robustness is that no prior knowledge about the noise is required. The proposed RPCA-based method is evaluated with the Aurora-4 database and a task using a state-of-the-art deep neural network (DNN) architecture as the acoustic models. The evaluation results indicate that the newly proposed method can provide the original speech feature with significant recognition accuracy improvement, and can be cascaded with mean normalization (MN), mean and variance normalization (MVN), and relative spectral (RASTA)—three well-known and widely used feature robustness algorithms—to achieve better performance compared with the individual component method.

This paper presents a self-driving system for automatic parallel parking, integrating obstacle avoidance for enhanced safety. The vehicle platform employs three primary sensors—a web camera, a Zed depth camera, and LiDAR—to perceive its surroundings, including sidewalks and potential obstacles. By processing camera and LiDAR data, the system determines the vehicle’s position and assesses parking space availability, with LiDAR also aiding in malfunction detection. The system operates in three stages: parking space identification, path planning using geometric circles, and fine-tuning with fuzzy control if misalignment is detected. Experimental results, evaluated visually in a model-scale setup, confirm the system’s ability to achieve smooth and reliable parallel parking maneuvers. Quantitative performance metrics, such as precise parking accuracy or total execution time, were not recorded in this study but will be included in future work to further support the system’s effectiveness.

This paper presents the design and implementation of an autonomous mobile robot system able to deliver objects from one location to another with minimal hardware requirements. Unlike most existing systems, our robot uses only a single camera—mounted on its robotic arm—to guide both its movements and the pick-and-place process. The robot detects target signs and objects, automatically navigates to desired locations, and accurately grasps and delivers items without the need for complex sensor arrays or multiple cameras. The main innovation of this work is a unified visual control strategy that coordinates both the vehicle and the robotic arm through homography-based visual servoing. Our experimental results demonstrate that the system can reliably locate, pick up, and place objects, achieving a high success rate in real-world tests. This approach offers a simple yet effective solution for object delivery tasks and lays the groundwork for practical, cost-efficient mobile robots in automation and logistics.

Personal voice activity detection (PVAD) identifies whether each detected speech frame originates from a designated target speaker. Modern PVAD systems are typically trained offline and then deployed with frozen model parameters and a fixed, pre-enrolled speaker embedding, leaving them unable to adapt to distribution shifts at inference time such as unseen acoustic environments, changing speaking styles, or mismatches between enrollment and test conditions. Test-time training (TTT) and test-time adaptation have shown promise in language, vision, and several speech tasks, yet their behavior on PVAD has not been studied. In this work, we present an empirical study of two complementary test-time adaptation mechanisms built on top of the recently proposed FDE-Mamba backbone. The first is a VAD-gated TTT adapter, which instantiates the TTT-Linear formulation within the personalization pathway and augments it with a VAD-probability gate and exponential moving-average stabilization, adapting an internal weight matrix on the speaker-conditioned feature stream of each test utterance. The second is TEA (Test-time Embedding Adaptation), a scheme that keeps all model parameters frozen and instead adapts the target speaker d-vector itself via self-supervised objectives at inference time, directly targeting enrollment–test mismatch. We evaluate both mechanisms on the LibriSpeech PVAD benchmark across two backbones (LSTM-based FDE-RNN and Mamba-based FDE-Mamba), reporting category-wise average precision, mean average precision (mAP), accuracy, recall, precision, and real-time factor. We further isolate the effect of a post-hoc Gaussian smoothing step and report that, of all the components we examine, this task-agnostic smoothing accounts for the largest single accuracy gain on the FDE-Mamba backbone (accuracy \( 89.87\% \rightarrow 90.47\% \)); the test-time adaptation mechanisms contribute a separate, smaller gain that is concentrated on speaker-discrimination metrics (mAP, precision) rather than on accuracy. Overall, the proposed test-time adaptation yields a consistent but modest improvement over the FDE-Mamba baseline (mAP \( 0.9605 \rightarrow 0.9641 \), precision \( 0.881 \rightarrow 0.899 \)), while slightly reducing recall and increasing inference cost when TEA is enabled. Through ablation studies, we quantify the independent and combined contribution of each component and characterize the recall–precision trade-off introduced by adaptation. These findings, together with a discussion of their limitations and cost–benefit profile, provide a measured baseline and design insights for future work on adaptive PVAD, particularly under stronger acoustic and enrollment mismatches than those captured by the LibriSpeech protocol.