A5066130866- Speech Recognition and Synthesis
- Speech and Audio Processing
- Mobile Ad Hoc Networks
- Music and Audio Processing
- Cooperative Communication and Network Coding
- Wireless Networks and Protocols
- IoT and Edge/Fog Computing
- Energy Efficient Wireless Sensor Networks
- Software-Defined Networks and 5G
- Opportunistic and Delay-Tolerant Networks
- Wireless Body Area Networks
- Fault Detection and Control Systems
- Cloud Computing and Resource Management
- Voice and Speech Disorders
- Natural Language Processing Techniques
- Advanced MIMO Systems Optimization
- Distributed and Parallel Computing Systems
- Advanced Optical Network Technologies
- Machine Fault Diagnosis Techniques
- Advanced Photonic Communication Systems
- Caching and Content Delivery
- Advanced Wireless Communication Technologies
- Advanced Data Compression Techniques
- Advanced Measurement and Detection Methods
- Smart Grid Security and Resilience
Northeastern University
2016-2025
Southwest University of Science and Technology
2024
Institute of Information Science, Academia Sinica
2018-2022
Academia Sinica
2019-2021
National Tsing Hua University
2017
Wuhan Textile University
2013
Northeastern University
2012
United States Geological Survey
2008
As an effective distributed renewable energy utilization paradigm, a microgrid is expected to realize the high integration of industrial cyber-physical systems (CPS), which has attracted extensive attention from academia and industry. However, real-time interaction feedback loop between physical cyber have posed severe challenges reliability, determinacy, efficiency multiway flow information communication transmission. In order solve problem slot scheduling data transmission (SSDT) in...
The convergence of transformative technologies, including the Internet Things (IoT), Big Data, and Artificial Intelligence (AI), has driven private edge cloud systems to forefront research efforts. access massive terminals emergence personalized services pose serious challenges for efficient resource management in power systems. To address challenge inequitable allocation cloud, this work proposes an intelligent strategy with a slicing auction approach. By formalizing problem as Mixed...
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features different properties, improve performance VAE-VC. We believed that success came more disentangled latent representations. article, extend...
Every year, many people around the world die because of mining accidents. Industrial Internet Things (IIoT) can be employed to sense public safety hazards and provide early warning accidents, thereby ensuring safe operations at underground mining, personnel positioning, specific items supervision emergency response. Real-time data anomaly detection predict probability occurrence abnormal event. However, massive heterogeneous monitoring data, poor wireless environment spatio-temporal...
As a key technology in smart healthcare monitoring systems, wireless body area networks (WBANs) can pre-embed sensors and sinks on surface or inside bodies for collecting different vital signs parameters, such as human Electrocardiograph (ECG), Electroencephalograph (EEG), Electromyogram (EMG), temperature, blood pressure, sugar, oxygen, etc. Using real-time online healthcare, patients be tracked monitored normal emergency conditions at their homes, hospital rooms, Intensive Care Units...
An effective approach to non-parallel voice conversion (VC) is utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), model the latent structure of speech in an unsupervised manner. A previous study has confirmed ef- fectiveness VAE using STRAIGHT spectra for VC. How- ever, other types spectral features such as mel- cepstral coefficients (MCCs), which are related human per- ception and have been widely used VC, not prop- erly investigated. Instead one specific...
The demand for improving productivity in manufacturing systems makes the industrial Internet of things (IIoT) an important research area spawned by (IoT). In IIoT systems, there is increasing different types equipment to exchange stream data with delays. Communications between massive heterogeneous devices and clouds will cause high latency require network bandwidth. introduction edge computing can address unacceptable processing reduce heavy link burden. However, limited resources servers...
As an essential part of next generation Internet, Wireless Mesh Networks (WMNs) have attracted much research attention due to its potential advantages including low up-front cost, ease deployment, enhanced capacity and service coverage. However, the inherit features wireless multi-hop networks put forward a severe challenge for traffic engineering problem. Conventional techniques either locally manipulate network or adopt unreliable best-effort delivery mechanism. Software Defined Networking...
At present, sensor-based E-Healthcare systems are attracting more and attention from academia industry. usually a Wireless Body Area Network (WBANs), which can monitor or diagnose human health by placing miniaturized, low-power sensor nodes in on patient’s bodies to measure various physiological parameters. However, this process, WBAN use batteries, especially for implantable flexible nodes, it is difficult accomplish the battery replacement, so energy that node carry very limited, making...
Internet of Things (IoT) is a key enabler for many industrial applications. Through the IoT, safety risk analysis and early warning management underground mining can effectively reduce frequency accidents failures, to save loss personnel property. Therefore, based on IoT great significance. However, requires deployment large number energy-constrained sensors sensing units, wireless signals they send are lost due data collisions, consuming node energy reducing efficiency. real-time reliable...
The next generation wireless network (NGWN) is undergoing an unprecedented revolution, in which trillions of machines, people, and objects are interconnected to realize the Internet Everything (IoE). with emergence IoE services such as virtual reality, augmented industrial 5 G, scarcity radio resources becomes more serious. Moreover, there hidden dangers untrusted terminals accessing system illegally manipulating devices. To tackle these challenges, this paper proposes a securing allocation...
Abstract As a critical component of space-air-ground integrated IoT, the aerial network provides highly reliable, low-latency and ubiquitous information services to ground users by virtue their high mobility, easy deployment low cost. However, current computation resource management model air-ground networks are insufficient meet latency demanding emerging intelligent such as autonomous systems, extended reality haptic feedback. To tackle these challenges, we propose offloading optimization...
Automatic speaker verification (ASV) is one of the most natural and convenient means biometric person recognition. Unfortunately, just like all other systems, ASV vulnerable to spoofing, also referred as "presentation attacks." These vulnerabilities are generally unacceptable call for spoofing countermeasures or attack detection" systems. In addition impersonation, systems replay, speech synthesis, voice conversion attacks. The ASVspoof 2019 edition first consider three types within a single...