In recent years, advancements in artificial intelligence, speech, and natural language processing technology have enhanced spoken dialogue systems (SDSs), enabling natural, voice-based human–computer interaction. However, discrete, token-based LLMs in emotionally adaptive SDSs focus on lexical content while overlooking essential paralinguistic cues for emotion expression. Existing methods use external emotion predictors to compensate for this but introduce computational overhead and fail to fully integrate paralinguistic features with linguistic context. Moreover, the lack of high-quality emotional speech datasets limits models’ ability to learn expressive emotional cues. To address these challenges, we propose EmoSDS, a unified SDS framework that integrates speech and emotion recognition by leveraging self-supervised learning (SSL) features. Our three-stage training pipeline enables the LLM to learn both discrete linguistic content and continuous paralinguistic features, improving emotional expressiveness and response naturalness. Additionally, we construct EmoSC, a dataset combining GPT-generated dialogues with emotional voice conversion data, ensuring greater emotional diversity and a balanced sample distribution across emotion categories. The experimental results show that EmoSDS outperforms existing models in emotional alignment and response generation, achieving a minimum 2.9% increase in text generation metrics, enhancing the LLM’s ability to interpret emotional and textual cues for more expressive and contextually appropriate responses.
Belt conveyor systems are essential across various industries but are prone to faults due to their distinctive design and challenging operational environments. Various approaches have been explored for fault detection and diagnosis (FDD) in belt conveyor systems, but research specifically addressing the unique features of these systems and providing a comprehensive analysis remains limited. In this paper, we propose a deep learning-based two-stage FDD approach specifically tailored to address the challenges associated with belt conveyor systems. Challenges in applying deep learning-based FDD include managing the vast number of features collected from large-scale systems, the scarcity of diverse fault data, and distribution shifts between training and testing environments. To address these issues, we developed a FDD approach that integrates open-set recognition and domain generalization, leveraging multivariate sensor data. Our two-stage design effectively mitigates the limitations posed by insufficient faulty samples while enhancing overall FDD performance. To properly assess the proposed method, we utilized datasets collected from a testbed that simulates the actual operational conditions of belt conveyor systems. The evaluation results demonstrate that the proposed FDD method exhibits robust performance in real-world applications on belt conveyor systems.
Accurate heading direction tracking is essential for immersive VR/AR, spatial audio rendering, and robotic navigation. Existing IMU-based methods suffer from drift and vibration artifacts, vision-based approaches require LoS and raise privacy concerns, and RF techniques often need dedicated infrastructure. We propose UDirEar, a COTS UWB device-based system that estimates user heading using solely high-level UWB information like distance and unit direction. By initializing an EKF with each user’s constant interaural distance, UDirEar compensates for the earbuds’ roto-translational motion without additional sensors. We evaluate UDirEar on a step-motor-driven dummy head against an IMU-only baseline (MAE 30.8°), examining robustness across dummy head–initiator distances, elapsed time, EKF calibration conditions, and NLoS scenarios. UDirEar achieves a mean absolute error of 3.84° and maintains stable performance under all tested conditions.