profile picture

Guangzhi Sun

University of Cambridge, Cambridge, UK

dataset

zero-shot

pre-trained language model

crowdsourcing

slot filling

vae

language model

multimodal

speech processing

knowledge injection

speech synthesis

large language model

nlp evaluation

spoken dialogue understanding

academic video

4

presentations

SHORT BIO

Guangzhi Sun received his B.A. and M.Eng. from the University of Cambridge (2019). He completed his PhD in 2023 supervised by Professor Phil Woodland in the Department of Engineering, University of Cambridge. He currently holds a junior research fellowship at Trinity College, Cambridge. His research focuses on safe and controllable multimodal large language models and contextual speech processing and understanding. He received the best student paper prize at Interspeech 2022.

Presentations

SkillAggregation: Reference-free LLM-Dependent Aggregation

Guangzhi Sun and 4 other authors

Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs

Keqi Deng and 2 other authors

M$^3$AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset

Zhe Chen and 8 other authors

Speech-based Slot Filling using Large Language Models

Guangzhi Sun and 5 other authors

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved