Andreas Liesenfeld


The art, science and engineering of talk.

CURRENT: The limits of automation in Conversational AI

CURRENT: Formal representations of talk

FORMER: Chinese framenets and constructicons

FORMER: Malaysia Cantonese speech corpus

BLOG: Conversational AI and conversation analysis

MISC: Tools, tutorials and links

FIND ME: Twitter

FIND ME: Google scholar

★★★ Video recording of my recent talk on linking frame semantics with behavioural profiling (in Mandarin) ★★★ ★★★ Upcoming: Looking forward to presenting at CUI2021 this summer.★★★

Picture I am a Conversational AI researcher studying voice technology in real-world contexts. I aspire to produce useful insights for anyone who designs, builds, uses or regulates talking machines. Late naturalist under pressure. "You must collect things for reasons you don’t yet understand." —Daniel J. Boorstin


My research interests originate in the study of human-human conversation and story-telling based on video-recordings. Then I became interested in how people aspire to build voice bots that can participate in these activities. What theoretical and computational tools would we need to build voice user interfaces that can hold up their end of conversations? Increasingly, I am also interested in speech processing to analyse various aspects of social intelligence such as turn-taking coordination, stance, rapport, and humor. What tools, pipelines, and representations would enable us to build voice bots that interact with humans in more useful ways? I hope my work will contribute to systems design innovation for voice tech. Currently, I'm concerned with two problems. How can we improve turn-taking coordination in voice bots? How can we move away from intent-based NLU?
I also work as a conversation design consultant in the Greater Bay Area and currently write a book chapter on crowd-sourcing talk for voice technology.

My Erdős number is 0 4.

Postdoctoral Research Fellow, Linguistics Theory and Language Technology group (LTT), The Hong Kong Polytechnic University, Hong Kong.
PhD researcher, Nanyang Technological University, Singapore
Visiting fellow, Computational Linguistics, Düsseldorf University, Germany
Data scientist, Industry, Berlin, Germany
Journalist, Industry, Hong Kong/London.
Get full CV

Visit Google scholar
For the video corpus of spoken Chinese see also: MYCanCor
For publications in Chinese see CNKI

Cause Chi (Tagger for causal discourse markers in spoken Chinese)
MV parser (Argument structure tagger for Chinese)

Conversation analytic transcription in LaTeX
Multilayed phonetic annotation with Praat

♦ ♦ ♦ Website recently moved from I know its ugly. Sorry about that. ♦ ♦ ♦