Xiangyu Zhang
University of New South Wales
Biography
I am a Ph.D. student at University of New South Wales supervised by Julien Epps and Beena Ahmed. Previous to this, I am a master’s student at CLSP at Johns Hopkins University majoring in Human Language Technology.
My research interests: Speech and Language Technology, Multimodal, Digital Health
Interests
- Speech and Language Technology
- Multimodal
- Digital Health
Education
Doctor of Philosophy in Electrical Engineering
University of New South Wales
Master of Science in Electrical Engineering(Human Language Technology)
Johns Hopkins University
Bachelor of Science(Honours) in Engineering Science with First Class Honours
University of Western Australia
Bachelor of Science in Engineering Science and Finance
University of Western Australia
Skills
Pytorch
Tensorflow
Espnet
Experience
Research Assistant
CLSP, Johns Hopkins University
Research in Speech processing and Quantum Machine Learning
Research Assistant
University of Western Australia
Research in Natural Language Processing
Accomplishments
TensorFlow 2 for Deep Learning
Algorithms
Natural Language Processing
Deep Learning
Machine Learning
Projects
*
To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns.
Purpose: Digital twins are virtual interactive models of the real world, exhibiting identical behavior and properties. In surgical applications, computational analysis from digital twins can be used, for example, to enhance situational awareness.
With careful manipulation, malicious agents can reverse engineer private information encoded in pre-trained language models. Security concerns motivate the development of quantum pre-training. In this work, we propose a highly portable quantum language model (PQLM) that can easily transmit information to downstream tasks on classical machines.
The detection of abnormal fetal heartbeats during pregnancy is important for monitoring the health conditions of the fetus. While adult ECG has made several advances in modern medicine, noninvasive fetal electrocardiography (FECG) re- mains a great challenge.
Lyrics recognition is an important task in music processing. Despite traditional algorithms such as the hybrid HMM- TDNN model achieving good performance, studies on applying end-to-end models and self-supervised learning (SSL) are limited.
Gallery
Recent Publications
Quickly discover relevant content by filtering publications.