Cantao Su (Tao)52.09N 5.12E

I’m a PhD candidate, supervised by Dr. Dong Nguyen in the NLP and Society Lab at Utrecht University in the Netherlands. More specifically, I work on themes like embedding models and data diversity measurement, within the DataDivers project.

Previously, I obtained my master’s degree in Voice Technology from University of Groningen, where I worked on dysarthric speech recognition, and my bachelor’s degree in Korean Language and Literature from Beijing International Studies University.

More broadly, I’m drawn to language itself — how people perceive it, how they learn it, and how it marks who they are. The Research page has the specifics.

Cantao Su
Tromsø, Norway2024

News

Oct. 2026 EMNLP 2026 Budapest, Hungary
Jan. 2026 UniDive Yerevan, Armenia
Sep. 2025 AthNLP Athens, Greece
Reading
Babel, or the Necessity of ViolenceR. F. Kuang
Watching
国际市场국제시장 · Ode to My Father

Selected

2 of 337
Jul. 2026 emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity C. Su, M. Velayuthan, E. Ploeger, D. Nguyen, A. Wegmann · arXiv preprint Paper
Jun. 2024 Enhancing English Dysarthric Speech Recognition with Age-Matched Healthy Speech: A Fine-Tuning Approach Using wav2vec 2.0 MSc thesis · University of Groningen Thesis