Search Results (73)

Long-term sports assessment is a challenging task in video understanding, since it requires judging subtle movement variations over minutes and evaluating action–music coordination. However, in many sporting events the background music is only weakly related to the performed movements, and the cues that matter for synchrony are often temporal and structural, such as small phase or tempo deviations that occur around decisive moments, rather than semantic correspondences between audio content and action categories. Prior approaches typically rely on implicit cross-modal fusion over dense sequences to learn such weak associations, which can smooth out near-miss misalignment and become brittle under tempo or phase shifts. To address this issue, we propose BEATSCORE, a beat-guided audio–visual learning framework that explicitly models action–music alignment at the beat level and performs event-centric sparse grading for long videos. In our framework, we first convert audio and motion into beat-synchronous tokens, enabling direct comparison on a unified rhythmic timeline. We then introduce a beat-level contrastive objective with near-offset hard negatives to sharpen sensitivity to misalignment. To handle the sparsity of decisive moments, we further design an event proposal and grading module that scores a small set of key segments and aggregates them via learnable multiple-instance pooling into a final assessment score. We evaluate BEATSCORE on public long-term sports benchmarks to demonstrate improved accuracy with competitive efficiency. Full article

Advanced mobile communication standards of the fifth and subsequent generations widely use beamforming technology. While many publications on this topic rely on simulation tools, some work has been dedicated to experimental testing using software-defined radio (SDR) platforms. These platforms are often expensive and require significant expertise to configure. This paper proposes a novel cost-effective method for combining a pair of dual-channel Universal Software Radio Peripheral (USRP) B210 boards into a four-element antenna array direction of arrival estimation testbed using Metronom synchronization devices. The hardware and developed software implementation is detailed, including the antenna layout and software modules, based on USRP Hardware Driver, that provide the frequency and time synchronization necessary for amplitude-phase processing. Experimental validation of the testbed using the MUltiple SIgnal Classification (MUSIC) algorithm demonstrates high stability of angle of arrival estimates, with a standard deviation not exceeding 0.4°. The algorithm achieved a resolution of 16.1° for two sources, which surpasses the half-power beamwidth of 25.6°. The theoretical significance of this work lies in the scientific validation of combining SDR devices with the precise synchronization required for beamforming. Its practical value is in enabling the experimental testing of beamforming without the need for costly multichannel SDR hardware. Full article

Objective: The purpose of this research is to examine how motivational music immediately impacts the brain’s functional connectivity patterns in male athletes following a single session of intense endurance exercise, utilizing resting-state electroencephalography (EEG) and brain network analysis methods. Methods: The study involved 34 healthy male athletes who were tasked with performing incremental cycling exercises until exhaustion, both with and without music. Their resting-state EEG was recorded before and after the exercise. Brain functional networks were analyzed in the theta, alpha, and beta frequency bands based on changes in phase locking value (PLV). Specifically, the study examined the central executive network (CEN), default mode network (DMN), salience network (SN), sensorimotor network (SMN), and dorsal attention network (DAN), assessing their topological properties using graph theory methods. Results: Music significantly prolonged the time to exhaustion. Across frequency bands, the music condition exhibited higher global and local efficiency compared with the no-music condition. Following exhaustion without music, beta-band connectivity significantly increased, suggesting compensatory hyper-synchronization under fatigue. In contrast, music led to reduced alpha- and beta-band global connectivity post-exercise, accompanied by selective strengthening of functionally relevant couplings, particularly between SMN and CEN, and enhanced DAN–DMN coordination. Additionally, music prevented maladaptive connectivity shifts observed under fatigue, including excessive SN–CEN coupling. Conclusions: Exhaustive exercise without music induces widespread beta-band hyper-connectivity, reflecting increased neural cost under central fatigue. Music, however, promotes a more efficient and selectively integrated network configuration, supporting the neural efficiency hypothesis. These findings provide neurophysiological evidence that music optimizes large-scale brain network organization under physical stress, thereby contributing to enhanced endurance performance. Full article

Background: This study addresses a common challenge in music education: students’ limited emotional engagement during music listening. Objectives: This study compared two teaching methods—externally guided augmented reality (AR) integration and internally generated simulation—in terms of their neural and behavioral differences in guiding students’ visual mental imagery and influencing their musical affect processing. Methods: Using Chinese Pipa music appreciation as our experimental paradigm, we employed fNIRS hyperscanning to record inter-brain synchronization (IBS) during teacher–student interactions across three instructional conditions (AR group, n = 27; visual imagery group, n = 27; no-instruction group, n = 27), while simultaneously assessing students’ performance in music–emotion processing tasks (emotion recognition and experience). Results: At the behavioral level, both instructional methods significantly enhanced students’ ability to differentiate emotional valence in music compared to the control condition. Crucially, the AR approach demonstrated a unique advantage in augmenting emotional arousal. Neurally, both teaching methods significantly enhanced IBS in brain regions associated with emotion evaluation (lOFC) and imaginative reasoning (bilateral dlPFC). Beyond these shared neural correlates, AR instruction specifically engaged additional brain networks supporting social cognition (lFPC) and multisensory integration (rANG). Furthermore, we identified a significant positive correlation between lFPC-IBS and improved emotional arousal exclusively in the AR group. Conclusions: The visual imagery group primarily enhances emotional music processing through neural alignment in core emotional brain regions, while augmented reality instruction creates unique advantages by additionally activating brain networks associated with social cognition and cross-modal integration. This research provides neuroscientific evidence for the dissociable mechanisms through which different teaching approaches enhance music–emotion learning, offering important implications for developing evidence-based educational technologies. Full article

Background: Rhythmic sensory stimulation, including structured musical interventions, has gained renewed interest as a non-pharmacological strategy that may modulate cortical excitability and network stability in focal epilepsy. Although several small studies have reported changes in seizure frequency or epileptiform activity during rhythmic or music exposure, the underlying mechanisms and translational relevance remain insufficiently synthesized. Objective: This narrative review summarizes clinical evidence on music-based and rhythmic sensory interventions in focal epilepsy, outlines plausible neurophysiological mechanisms related to neural entrainment and large-scale network regulation, and discusses emerging opportunities for digital delivery of rhythmic protocols in everyday self-management. Methods: A structured search of recent clinical, neurophysiological, and rehabilitation literature was performed with emphasis on rhythmic auditory, tactile, and multimodal stimulation in epilepsy or related conditions. Additional theoretical and translational sources addressing oscillatory dynamics, entrainment, timing networks, and patient-centered digital tools were reviewed to establish a mechanistic framework. Results: Existing studies—although limited by small cohorts and heterogeneous methodology—suggest that certain rhythmic structures, including specific musical compositions, may transiently modulate cortical synchronization, reduce epileptiform discharges, or alleviate seizure-related symptoms in selected patients. Evidence from neurologic music therapy and rhythmic stimulation in other neurological disorders further supports the concept that externally delivered rhythms can influence timing networks, attentional control, and interhemispheric coordination. Advances in mobile health platforms enable structured rhythmic exercises to be delivered and monitored in real-world settings. Conclusions: Music-based and rhythmic sensory interventions represent a promising but underexplored adjunctive approach for focal epilepsy. Their effectiveness likely depends on individual network characteristics and on the structure of the applied rhythm. Digital integration may enhance personalization and adherence. Rigorous clinical trials and mechanistic studies are required to define optimal parameters, identify responders, and clarify the role of rhythmic stimulation within modern epilepsy care. Full article

In natural systems, astrophysics, biological physics, and social physics, 1/f fluctuations are observed across a wide range of systems. Focusing on the case of music, we propose and verify a physical mechanism for generating these fluctuations. This mechanism is based on amplitude modulation (AM) and demodulation (DM), where the 1/f spectral law appears not in the raw waveform but in its demodulated amplitude envelope. Two distinct yet complementary processes generate the required AM: (i) stochastic synchronization among oscillators, modeled via an extended Kuramoto framework that captures perpetual synchronization–desynchronization cycles, and (ii) frequency-selective resonance, modeled by spectral accumulation of eigenmodes in acoustic or structural environments. Numerical simulations demonstrate that both mechanisms, acting alone or in combination, robustly generate 1/f spectra spanning several digits when demodulation is applied and that the classical Kuramoto critical point is not essential for its emergence. While this analysis focuses on 1/f fluctuations in musical performance and acoustics, we also note that 1/f fluctuations inherent in musical scores may be similarly described by the AM/DM mechanism. Full article

As a vital carrier of human intangible culture, dance plays an important role in cultural transmission through digital generation. However, existing dance generation methods rely heavily on high-precision motion capture and manually annotated datasets, and they fail to effectively model the culturally distinctive movements of Chinese ethnic folk dance, resulting in semantic distortion and cross-modal mismatch. Building on the Chinese traditional ethnic Helou Dance, this paper proposes a culture-aware Chinese ethnic folk dance generation framework, CAFE-Dance, which dispenses with manual annotation and automatically generates dance sequences that achieve high cultural fidelity, precise music synchronization, and natural, fluent motion. To address the high cost and poor scalability of cultural annotation, we introduce a Zero-Manual-Label Cultural Data Construction Module (ZDCM) that performs self-supervised cultural learning from raw dance videos, using cross-modal semantic alignment and a knowledge-base-guided automatic annotation mechanism to construct a high-quality dataset of Chinese ethnic folk dance covering 108 classes of curated cultural attributes without any frame-level manual labels. To address the difficulty of modeling cultural semantics and the weak interpretability, we propose a Culture-Aware Attention Mechanism (CAAM) that incorporates cultural gating and co-attention to adaptively enhance culturally key movements. To address the challenge of aligning the music–motion–culture tri-modalities, we propose a Tri-Modal Alignment Network (TMA-Net) that achieves dynamic coupling and temporal synchronization of tri-modal semantics under weak supervision. Experimental results show that our framework improves Beat Alignment and Cultural Accuracy by 4.0–5.0 percentage points and over 30 percentage points, respectively, compared with the strongest baseline (Music2Dance), and it reveals an intrinsic coupling between cultural embedding density and motion stability. The code and the curated Helouwu dataset are publicly available. Full article

Background: Although the Shared Affective Movement Experience (SAME) model suggests the crucial role of imitation and synchronization in music-induced emotion, their application in teaching settings remains largely unexplored. Objectives: This study compared the “Body Rhythm Teaching Method,” based on the principle of mimicking musical elements through bodily movements, with traditional lecture-based instruction. It examined the effects of both teaching approaches on brain activation patterns, measured via functional Near-Infrared Spectroscopy (fNIRS) hyperscanning and instructional outcomes (assessed through musical emotion processing and teaching quality evaluations). The aim was to investigate their efficacy in enhancing students’ musical emotional processing abilities. Methods: A total of 3 teachers and 103 student participants were randomly assigned to the lecture teaching group (n = 35), the body rhythm teaching group (n = 35), or the control group (n = 33). The musical materials used across all three groups were identical, with only the teaching methods differing. fNIRS hyperscanning imaging was employed throughout the process to record brain activity. Results: Results indicate that the body rhythm group significantly outperformed other groups in both behavioral and neural metrics. Specifically, during the post-test music-listening phase, participants in this group not only reported higher emotional arousal but also exhibited stronger activation levels in the bilateral frontopolar cortex (FPC) associated with multisensory integration—both significantly higher than those in the lecture group and control group. Furthermore, during instruction, students in the body rhythm group rated teaching quality higher and exhibited significantly stronger teacher–student IBS across multiple brain regions involved in socio-emotional processing. These included the left orbitofrontal cortex (lOFC) for interoceptive emotion processing, the left frontopolar cortex (lFPC) for multisensory integration, and the right superior temporal gyrus (rSTG) for social interaction. In contrast, the lecture teaching group only showed significantly higher emotional valence ratings compared to the control group. Conclusions: This study confirms the role of imitation and synchronization mechanisms in the SAME model for music-induced emotional responses, providing a neuroscientific basis for teaching practice. Full article

This paper presents the development of a 32-degree-of-freedom (DoF) humanoid robotic system designed for autonomous piano performance. The system integrates a vision-based music sheet reader with a YOLOv8 neural network for real-time detection and classification of musical symbols, achieving a mean average precision (mAP) of 96% at IoU 0.5. A heuristic-based synchronization and motion planning module computes optimal finger trajectories and hand placements, enabling expressive and temporally accurate performances. The robotic hardware comprises two anthropomorphic hands mounted on linear rails, each with independently actuated fingers capable of vertical, horizontal, and rotational movements. Experimental validation demonstrates the system’s ability to execute complex musical passages with precision and synchronization. Limitations related to dynamic expressiveness and symbol generalization are discussed, along with proposed enhancements for future iterations. The results highlight the potential of AI-driven robotic systems in musical applications and contribute to the broader field of intelligent robotic performance. Full article

This work presents a mixed reality application for drum learning that combines the PocketDrum virtual drumming device with the Meta Quest 3 headset, integrating hand tracking to provide an immersive, responsive experience without the need for a physical drum set. The system features a modular architecture for real-time strike detection, visual guidance synchronized with music, spatial calibration, and audio rendering. The system additionally makes use of the headset’s color Passthrough during the calibration stage to align the virtual drum kit with the player’s position. To evaluate the system’s performance, a technical analysis was conducted to measure latency, jitter, and sampling rate across the technologies involved. Additionally, a functional validation experiment assessed how spatial hand tracking from Meta Quest 3 improved PocketDrum’s classification accuracy. Results showed that the fused system corrected 19.1% of drum assignment errors made by the inertial-only setup, enhancing consistency in complex rhythmic patterns. These findings demonstrate the effectiveness of sensor fusion for immersive percussion training and support its potential use in accessible, feedback-rich musical learning environments. Full article

With the increasing number of construction machinery operations near high-voltage power facilities, determining how to improve operational safety has become an urgent issue that needs to be addressed. To address safety hazards when autocranes operate near live high-voltage power lines, this study proposes a high-voltage proximity safety early warning method for autocranes. The method collects the electric field signals of high-voltage power lines in real time via an electromagnetic sensor array, calculates the azimuth angle of the live conductor using the MUSIC algorithm, and acquires the 3D point cloud data of the high-voltage power lines through high-density scanning with a LiDAR. By achieving time synchronization and coordinate registration of the electromagnetic sensor data and LiDAR data, a 3D spatial model of the high-voltage power lines is established, and the minimum distance between the crane boom and the live conductor is calculated. It identifies the voltage level, computes the basic safety distance, modifies the distance with environmental factors, and then multiplies it by a safety factor to obtain the dynamic safety threshold. Finally, based on the real-time distance between the crane boom and the live conductor, hierarchical early warnings and control actions are triggered. Full article

Time-domain signal models have been widely applied to single-channel music source separation tasks due to their ability to overcome the limitations of fixed spectral representations and phase information loss. However, the high acoustic similarity and synchronous temporal evolution between vocals and accompaniment make accurate separation challenging for existing time-domain models. These challenges are mainly reflected in two aspects: (1) the lack of a dynamic mechanism to evaluate the contribution of each source during feature fusion, and (2) difficulty in capturing fine-grained temporal details, often resulting in local artifacts in the output. To address these issues, we propose an attention-driven time-domain convolutional network for vocal and accompaniment source separation. Specifically, we design an embedding attention module to perform adaptive source weighting, enabling the network to emphasize components more relevant to the target mask during training. In addition, an efficient convolutional block attention module is developed to enhance local feature extraction. This module integrates an efficient channel attention mechanism based on one-dimensional convolution while preserving spatial attention, thereby improving the ability to learn discriminative features from the target audio. Comprehensive evaluations on public music datasets demonstrate the effectiveness of the proposed model and its significant improvements over existing approaches. Full article

Objective: This paper examines how rhythm-enhanced digital dance affects children’s motor abilities, cognitive performance, and neuromuscular synchronization. Methods: In a randomized repeated-measures study, 38 children (7–12 years) underwent three conditions: groove music-accompanied dance (GODA), conventional music dance (CODA), and non-musical physical activity (CON). Assessments of gross motor skills (using TGMD-3), executive function (using BRIEF and Stroop Test), and muscle coordination (using sEMG) were conducted. Results: Gross motor skills: GODA showed significantly higher TGMD scores in locomotor (p = 0.03) and ball skills (p = 0.02) compared to both CODA and CON (p < 0.001). Executive function: Inhibition and shifting dimensions showed significant post-intervention condition differences (p < 0.05). Muscle coordination: GODA exhibited greater β- and γ-band COH areas in the standing long jump compared to both CODA (p = 0.02) and CON (p < 0.001), and increased γ-band COH areas in single-leg balance compared to CODA (p = 0.02) and CON (p < 0.001). Conclusions: Combining rhythmic auditory stimulation with movement training offers a promising approach for integrated motor-cognitive development in children. Full article

Objectives: Sub-second motor timing is critical for skilled performance in domains such as sport, music, and safety-critical multitasking; however, its robustness under cognitive load remains unresolved. Dual-task paradigms offer a method to test whether attentional demands selectively disrupt temporal precision. This study intended to investigate the effects of cognitive load on rhythmic finger tapping at a sub-second interval. Methods: A sample of 103 college students (19–25 years) performed a synchronization–continuation tapping task at 500 ms intervals under single- and dual-task conditions across five trials. The dual-task condition included a distracting letter-span task imposing working memory load. Inter-response intervals (IRIs), their variability (IRI SD), and accuracy (AI) were analyzed using linear mixed-effects models. Results: Tapping intervals were consistently shorter than the 500 ms target by approximately 70 ms in both conditions, showing anticipatory mechanisms that remained stable under cognitive load. Mean accuracy did not vary between single- and dual-task conditions. By contrast, temporal variability was significantly higher in the dual-task condition, reflecting diminished trial-to-trial consistency. These effects continued throughout trials and were supported by model estimates, which indicated robust between-subject variability but selective disruption of consistency rather than mean performance. Conclusions: Dual-tasking selectively hinders temporal stability in sub-second motor timing while ensuring that the reproduction and accuracy of the mean interval remain unchanged. This pattern supports dual-process accounts of timing, suggesting distinct roles for predictive control and attentional allocation. The results have applied relevance for situations requiring precise rhythmic performance under cognitive load, including sports, ensemble music, and safety-critical tasks. Full article

Vibrotactile feedback synchronized with audio through haptic music players (HMPs) creates a synergistic effect that has been shown to improve the music listening experience. However, current HMPs are still unable to efficiently retrieve multiple music features, decelerating app scalability and jeopardizing long-term user engagement. This study introduces a wearable HMP that utilizes piezoelectric actuators and a novel audio-tactile rendering algorithm that uses YIN to extract pitch and spectral flux for rhythm. Building upon prior work, the system additionally features a modified discretization step and software optimization to improve multi-feature extraction and tactile display of music. The pitch, melody/timbre, and rhythm displays, respectively, were validated using Mean Average Error (MAE), Dynamic Time Warping (DTW) distance, and accuracy, yielding normalized averages of MAE = 0.1020 and DTW = 0.1518, and a rhythmic pattern accuracy of 97.56%. The Yin algorithm was shown to greatly improve the tactile display of vocals, with slight improvements for bass and accompaniments, while spectral flux and software optimizations significantly improved rhythm display. The wearable HMP effectively communicates multiple music features without the pitfalls of prior approaches. Future research can improve the system’s audio-tactile signal fidelity and explore the qualitative merits of multi-feature extraction in HMPs. Full article