I’m currently a PhD candidate at MuSAE Lab, Institut national de la recherche scientifique (INRS), which is located at Montreal, Canada (a city with THE MOST beautiful summer and thankfully not the most freezing winter). My research focuses at the intersection between multimodal signal processing and machine learning, and how to use them to develop trustworthy, generalizable, and safe audio/speech applications.
My CV can be seen here. Recent new are updated at posts.
- PhD candidate (2021-Current)
- Institut national de la recherche scientifique (Canada)
- Major: Telecommunications
- Advisor: Dr. Tiago H. Falk
- Master of Science (2018-2020)
- University of Minnesota - Twin Cities (U.S.)
- Major: Biomedical Engineering
- Minor: Movement Science
- Advisor: Dr. Juergen Konczak
- Undergraduate (2014-2018)
- Southeast University (China)
- ICASSP 2023 Rising Star
Summary of ongoing and previous projects
- Disentangling speaker information from other paralinguistic attributes for speech anonymization/conversion
- Generalizable and interpretable audio-based diagnostics using speech, cough, and breathing
- Spoofing, deepfake, and adversarial attack detection via signal processing and deep learning
- Beehive survivability prediction using multi-modal sensor data (acoustics, temperature, humidity)
I also have internal and external collaborations with reserachers in many other fields, for example, all-optical neural network for robust and sustainable diagnostics, detection of exacerbation in chronic obstructive pulmonary disease, etc.
Publications (in 2023)
For the full list, click here to go to my google scholar profile.
- Yi Zhu, Mohamed Imoussaïne-Aïkous, Carolyn Côté-Lussierand, Tiago H. Falk, “On the impact of voice anonymization for speech based diagnostics”, IEEE-TIFS, 2023, under review.
- Yi Zhu and Tiago H. Falk, “On the importance of different cough phases for COVID-19 detection”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, accepted.
- Yi Zhu, and Tiago H. Falk. “Spectral-temporal saliency maps for generalizable speech-based COVID-19 detection”, JBHI, under review