Publications
You can also find my articles on my Google Scholar profile.
/ publications
- A Lightweight Neural Speech Compression Method for Edge DevicesActa Electronica Sinica (电子学报 CCF T1) · 2025We redesign the encoder module using a streamlined convolutional neural network architecture and introduce a multi-objective knowledge distillation strategy that integrates perceptual alignment, spectral constraints and adversarial training.
- Aucom: Extreme Compression for Real-Time Edge-to-Server Universal Audio StreamingIEEE TMC (CCF A) · 2025We propose a novel edge-to-server audio streaming architecture that leverages Mel filter bank spectral features to achieve ultra-high compression efficiency. Our system integrates audio denoising, Mel feature extraction,and quantization-based compression at the edge, effectively suppressing environmental and device-induced noise while achieving an extreme compression ratio relative to the original uncompressed audio.
- MODepth: Benchmarking Mobile Multi-frame Monocular Depth Estimation with Optical Image StabilizationACM SIGGRAPH Asia (CCF A) · 2025Leveraging multiframe images captured under OIS-controlled lens movements, we design a high-precision depth estimation network, MODNet, and introduce the principal point offset estimation module and pose estimation modules to fully exploit geometric information across frames.
- STELLAR: Pacemaker Recognition Using 12-Lead ECG and Spatio-Temporal Harmonic MechanismIEEE BIBM (CCF B) · 2025We propose STELLAR, a novel deep learning framework that integrates a Spatio-Temporal Lead-Harmonic Mechanism to model both the temporal dynamics of ECG waveforms and the spatial coherence across leads.
- A Transform-Domain Approach with Symmetric and Edge Constraints for MRI Super-ResolutionIEEE BIBM (CCF B) · 2025In this paper, we propose a novel super-resolution up-sampling pipeline that enhances both the high-frequency and low-frequency components of magnetic resonance imaging.
- Toward High Spatial Resolution and Low Ambiguity in Wideband Signal Receiver Beamforming for VR/ARACM Ubicomp (CCF A) Workshop MIMSVAI · 2025We propose a novel receiver beamforming system that employs a dynamically reconfigurable circular microphone array with an adjustable radius, paired with a frequency-adaptive ambiguity suppression algorithm.
- High-resolution mmWave Imaging using Metasurface and DiffusionACM Mobisys (CCF B) · 2025In this paper, we propose a novel high-resolution mmWave imaging technique that operates with a small, off-the-shelf mmWave module and eliminates the need for any mechanical movement, offering a streamlined, portable solution.
- Moir´eComm: Secure Screen-camera Communication based on Moir´e CryptographyIEEE TDSC(CCF A) · 2025Addressing this, we propose a novel Moire encryption technique-based secure screen-camera communication system, named MoireComm. The Moire encryption can enhance security by using distinct spatial frequency patterns for camouflage.
- Effective Local Texture Estimation Using Wavelet Transforms for Arbitrary-Scale Super-ResolutionSpringer ICIC (CCF C) Poster · 2025In this work, we propose a novel Local Wavelet Transformer (LWT) framework that leverages the Discrete Wavelet Transform (DWT) to capture both local textures and global structures, improving the accuracy of fine grained detail restoration.
- Amser+: Accelerating Mobile Speech Emotion Recognition in IoT Environments with Mel Feature CompressionIEEE IoTJ (CCF C & JCR Q1) · 2025This article proposes Amser+, a real-time SER framework using signal compression and task offloading. Amser+ utilizes logarithmic Mel-filter bank coefficients (Fbank) and singular value decomposition (SVD) for feature extraction and compression.
- TouchHBC: Touch-based Human Body Communication via Leakage CurrentIEEE TMC (CCF A) · 2025This study introduces TouchHBC, a secure and reliable communication scheme leveraging a smartwatch’s built-in electrodes. This system establishes a touch-based human communication system utilizing a laptop’s leakage current.
- M2Silent: Enabling Multi-user Silent Speech Interactions via Multi-directional Speakers in Shared SpacesACM CHI (CCF A) · 2025M2Silent addresses this by allowing users to communicate silently, without producing audible speech, using acoustic sensing integrated into directional speakers. We leverage FMCW signals as audio carriers, simultaneously playing audio and sensing the user’s silent speech.
- AMSER: Accelerate Mobile Speech Emotion Recognition with Signal CompressionIEEE ICASSP (CCF B) · 2025This paper proposes AMSER, a real-time speech emotion recognition framework using signal compression and task offloading. AMSER utilizes logarithmic Mel-filter bank coefficients (Fbank) and singular value decomposition (SVD) for feature extraction and compression.
- DASIV: Directional Acoustic Sensing based Intelligent Vehicle Interaction SystemIEEE IPCCC (CCF C) · 2025In this paper, we propose DASIV, which utilizes the highly directional nature of ultrasonic signals to achieve fine-grained directional acoustic sensing in vehicle environments.
- M3Cam: Extreme Super-resolution via Multi-Modal Optical Flow for Mobile CamerasACM SENSYS (CCF B) · 2024Our proposed system can generate a 16× SR image from four captured low-resolution images in real-time, with low computational load, low inference latency, and minimal reliance on runtime RAM.
- HandPad: Make Your Hand an On-the-go Writing Pad via Human CapacitanceACM UIST (CCF A) · 2024This paper introduces HandPad, the system that turns the hand into an on-the-go touchscreen, which realizes interaction on the hand via human capacitance. HandPad achieves keystroke and handwriting inputs for letters, numbers, and Chinese characters, reducing the dependency on capacitive or pressure sensor arrays.
- Enable Touch-based Communication between Laptop and SmartwatchACM Ubicomp (CCF A) Poster · 2024This study introduces TouchHBC, a secure and reliable communication scheme leveraging a smartwatch built-in electrodes. This system establishes a touch-based human communication system utilizing a laptop leakage current.
- HCMG: Human-Capacitance based Micro Gesture for VR/ARACM Ubicomp (CCF A) Workshop MIMSVAI · 2024Building on the foundation of human capacitance, this paper introduces a novel approach termed human capacitance-based micro gesture (HCMG) recognition.
- Visar: Projecting Virtual Sound Spots for Acoustic Augmented Reality Using Air NonlinearityACM IMWUT (CCF A) · 2024This paper proposes Visar, a device-free virtual sound spots projection system leveraging air nonlinearity. Visar achieves simultaneous tracking and sound spot generation while suppressing unintended audio leakages caused by grating lobes and nonlinear effects in mixing lobes through optimization.
- CarbonNet: Enterprise-Level Carbon Emission Prediction with Large-Scale DatasetsSpringer ICIC (CCF C) · 2024We propose CarbonNet, a novel firm-level carbon emission prediction scheme. To build large-scale firm-level datasets, we crawled carbon emission data and reporting data (e.g., financial statements) of 3346 companies over 31 years containing 688 data fields, and combined them together.
- VCEMO: Multi-Modal Emotion Recognition for Chinese VoiceprintsSpringer ICIC (CCF C) Poster · 2024This paper introduces the VCEMO dataset to address this deficiency. The proposed dataset is constructed from everyday conversations and comprises over 100 users and 7,747 textual samples.
- Adaptive Metasurface-Based Acoustic Imaging using Joint OptimizationACM Mobisys (CCF B) · 2024We leverage a 3D-printed passive acoustic metasurface to significantly enhance the diversity of the measurement data, thereby improving the imaging quality. Specifically, we jointly design the transmission signal, transceivers beamforming weights, metasurface, and imaging algorithm to minimize the imaging reconstruction error in an end-to-end manner.
- Pushing the Limits of Acoustic Spatial Perception via Incident Angle EncodingACM IMWUT (CCF A) · 2024In this paper, we introduce MetaAng, a system designed to augment microphone arrays by enabling wideband spatial perception across both speech signals and inaudible sounds by leveraging the spatial encoding capabilities of acoustic metasurfaces.
- Effectively Learning Moiré QR Code Decryption from Simulated DataIEEE INFOCOM (CCF A) · 2023In this work, we propose a deep learning-based Moiré QR code decryption framework and achieve an excellent decryption performance.
- Addressing Practical Challenges in Acoustic Sensing To Enable Fast Motion TrackingACM IPSN (CCF B) · 2023Motivated by many potential applications that could be enabled by acoustic motion tracking, in this paper we systematically examine the factors that limit the accuracy of acoustic tracking in practical scenarios.