Academic works

I am Wan Ziyu, a current doctoral course student at Human-Computer Interaction Laboratory, Hokkaido University. I have relatively formal education on opto-electrical engineering and some computer science, and informal self-education on linguistics and phonetics.

I am not very proud to say that I have no publications as of now (whenever you are looking at this page, that is).

However, I feel that it is equally important to introduce what I am currently doing and what I have done in the slight case that you are interested.

Research strengths and, well, abilities

I don't have any specifically notable certificates or qualifications so take everything I list here with a pinch of salt.

• Digital signal processing, with Python (librosa / numpy / scipy) and a some C++ (iPlug2 for creating VST apps)
• Neural network (rather basic) with Tensorflow / Keras. Also a tad of PyTorch, but I hate migrating between toolkits.
• Some HTML / JavaScript for unpretty utility webpages.
• Some bash / Python for task automation.
• LLM prompt composition, generic LLM utilisation.
• Basic welding and electrician skills.

Research topics / interests

Language-independent speech recognition

To capture the phonemes (sound) rather than text, a language-independent speech recognition system is proposed.

See: Language-independent speech recognition

LLM powered conversational (car) navigation agent

Based on the half-faith, half-fact (proportions may vary) that vehicle navigation is a social, conversational task, I think it might be good to enable navigation softwares to have some conversation with the driver as well.

See: LLM navigation agent

(Pro?)active agent guidance

A spin-off from the navigator idea. Make the agent capable of actively asking for information might help the human user form more structured, concise and solid input.

See: Active agent guidance