A5100450332- Music and Audio Processing
- Speech and Audio Processing
- Delphi Technique in Research
- Time Series Analysis and Forecasting
- Music Technology and Sound Studies
- Speech Recognition and Synthesis
- Data Management and Algorithms
- Disaster Management and Resilience
- Health disparities and outcomes
- Natural Language Processing Techniques
- Data Quality and Management
- Handwritten Text Recognition Techniques
- Human Mobility and Location-Based Analysis
- Speech and dialogue systems
- Chronic Disease Management Strategies
- Discourse Analysis and Cultural Communication
- Advanced Text Analysis Techniques
- Complex Network Analysis Techniques
- Knowledge Management and Sharing
- Anomaly Detection Techniques and Applications
- Intergenerational Family Dynamics and Caregiving
- Digital Marketing and Social Media
- Data Mining Algorithms and Applications
- Neuroscience and Music Perception
- Digital Imaging for Blood Diseases
Xuzhou Medical College
2023-2025
Bose (United States)
2023-2025
Beijing Tongren Hospital
2024
Capital Medical University
1999-2024
Peter the Great St. Petersburg Polytechnic University
2024
Duke University
2024
Nanchang University
2024
Xi'an University of Technology
2023
Harbin Institute of Technology
2021-2023
North China Electric Power University
2012-2023
The expanding feature set of modern headphones puts a challenge on the design their control interface. Users may want to separately each or quickly switch between modes that activate different features. Traditional approach physical buttons no longer be feasible when is large. Keyword spotting with voice commands promising solution issue. Most existing methods keyword only support spoken in regular voice. However, not desirable quiet places public settings. In this paper, we investigate...
This study aimed to evaluate the role of social participation in relationship between internet use and depressive symptoms among Chinese older adults investigate how interact with reduce risk symptoms.
Abstract Purpose To compare the image quality, examination time, and total energy release of a standardized pediatric brain tumor magnetic resonance imaging (MRI) protocol performed with without compressed sensitivity encoding (C-SENSE). Recently introduced as an acceleration technique in MRI, we hypothesized that C‑SENSE would improve reduce time radiofrequency-induced compared conventional protocol. Methods This retrospective study included 22 patients aged 2.33–18.83 years different types...
We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as foundation model for generation and excels in in-context learning, achieving performance speaker similarity naturalness matches ground truth both objective subjective evaluations. With fine-tuning, we achieve even higher scores across these metrics. offers superior controllability over various attributes...
Traditional route planning methods usually plan the “fastest” or “lowest cost” travel for users with goal of finding shortest path lowest cost, but this method cannot meet needs tourism personalized and multifunctional routes. Given phenomenon, paper proposes a model based on urgency. First, uses visitor’s historical data public road network to extract their preferences, POI (point interest) relationships, edge scenic values other information. Then, planned function is determined according...
The relation of social deprivation with single cardiometabolic disease (CMD) was widely investigated, whereas the association multi-morbidity (CMM), defined as experiencing more than two CMDs during lifetime, is poorly understood.We analyzed 345,417 UK Biobank participants without any at recruitment to study between and four including type II diabetes (T2D), coronary artery (CAD), stroke hypertension. Social measured by Townsend index (TDI), CMM occurrence or above diseases. Multivariable...
Abstract Background To investigate the association between cigarette smoking, smoking cessation and trajectory of cardiometabolic multimorbidity (CMM), further to examine age at initiation with CMM. Methods This study included 298,984 UK Biobank participants without diseases (CMDs) (including type 2 diabetes, coronary heart diseases, stroke, hypertension) baseline. Smoking status was categorized into former, current, never smokers, as a proxy for current former smokers. The multi-state model...
Chinese outward foreign direct investment (OFDI) in Africa has attracted much discussion on the competitive relations between companies and their or local counterparts. There is however limited research examining increasingly relationships among business actors themselves complex implications of activities for African economic development. Existing studies often either treat as a homogeneous entity pursuing collective, state-directed agenda emphasize collaborative networks groups during...
The problem of understanding people's participation in real-world events has been a subject active research and can offer valuable insights for human behavior analysis event-related recommendation/advertisement. In this work, we study the latent factors determining event popularity using large-scale datasets collected from popular Meetup.com EBSN three major cities around world. We have conducted modeling four contextual (spatial, group, temporal, semantic), also developed group-based social...
Under the “Internet+” environment, R&D intensity of products and services has increased; hence, organizations need to improve their ability integrate knowledge technology resources. Knowledge gaps will arise when an organization’s reserves fail meet needs innovation activities. This research established a network complete topics under environment based on Word2Vec model. The word vectors frequencies organizational reserve texts were analyzed establish topic network. Term...
As wearable devices gain widespread acceptance among the general population, there is a crying need to ensure that relevant privacy and security vulnerabilities are minimize hazards. Biometrics become very important in our daily lives due its relative convenience compared with traditional personal identification data. In this paper, We propose live biometric recognition method of ECG for devices. Specifically, we locate feature points recognize Q-R-S wave, P R wave respectively. Then analyze...
Modern noise-cancelling headphones have significantly improved users' auditory experiences by removing unwanted background noise, but they can also block out sounds that matter to users. Machine learning (ML) models for sound event detection (SED) and speaker identification (SID) enable selectively pass through important sounds; however, implementing these a user-centric experience presents several unique challenges. First, most people spend limited time customizing their headphones, so the...
This paper conceptualizes speech prosody data mining and its potential application in data-driven phonology/phonetics research.We first conceptualize Speech Prosody Mining (SPM) a time-series framework.Specifically, we propose using efficient symbolic representations for similarity computation.We experiment with both numeric distance measures series of classification clustering experiments on dataset Mandarin tones.Evaluation results show that representation performs comparably other at...