Dr Catherine Lai

Lecturer in Speech and Language Technology
Linguistics and English Language
School of Philosophy, Psychology and Language Sciences
University of Edinburgh

Catherine Lai

I am a lecturer (~assistant professor) based in the Centre for Speech Technology Research at the University of Edinburgh. I work in Linguistics and English Language in the School of Philosophy, Psychology and Language Sciences, at the University of Edinburgh, and am also affliated with the Institute for Language, Cognition and Computation in the School of Informatics where I was previously a post-doc and senior researcher.

My research focuses on how we can use the non-lexical aspects of speech (e.g. speech prosody) to get at what speakers actually mean. I'm currently working mainly on topical and affective information extraction from conversational speech. I'm interested in this for both theoretical and practical reasons. On the one hand, I'm interested in developing speech technologies that can better take account of contextual variation. I recently worked on this topic with researchers at Toyota (in Europe and Japan) on the project 'Spoken Dialogue Processing for Robot companions'. The hope is that this sort of research will help make assistive technologies more robust, as well as provide new ways for linguists andother social scientists to explore speech and video data. On the other hand, I'm interested generally in understanding where non-lexical aspects of speech fit into linguistic theories. This means that I'm usual, in some way or another, working more generally on developing models of prosody in dialogue. I'm particularly interested in how we can use idea from topic modeling to get a more robust idea of the relationship between prosody, discourse structure, and information structure. Hopefully this will build some bridges between more theoretical and empirical approaches understanding to this complicated aspect of spoken communication.

I'm currently supervising Sarenne Wallbridge (computational approaches to multimodal discourse analysis), and second supervisor to Pilar Oplustil (conversational text-to-speech synthesis), Emelie van der Vreken (affective speech synthesis), and Nina Markl (computational sociolinguistics), and Jie Chi (automatic speech synthesis and code switching). I recently co-supervised Leimin Tian, who worked on emotion recognition in dialogue.

I originally came to Edinburgh to work on the EU FP project InEvent, which looked at how automatic processing of audiovisual data could be used to aid browsing of large video archives. I mainly worked on how to features often associated with speaker affect, e.g. prosody and measures of participation, can be used for summarization and affect detection. I also ended up doing a bit of HCI evaluation. I was also a co-organizer of an IAD funded interdisciplinary network on Speech, Image and Social Media Data for the Social Sciences.

Before that, I was graduate student in the Department of Linguistics at the University of Pennsylvania. At Penn, I worked in the phonetics lab where I took advice from Jiahong Yuan, Mark Liberman, Florian Schwarz, and many other people. My dissertation was about where intonational features, particularly final pitch rises, fit in with semantic and pragmatic theories. I also worked on various other topics ranging from iterated learning in language change, gradability and modality in semantics, tone and stress in Chinese, and prosody of second language learners.

I'm currently part of the UKSpeech organizing committee. In the past, I have served on the Student Advisory Committee of the International Speech Communication Association (ISCA-SAC). I helped organize a workshop on New Tools and Methods for Very-Large-Scale Phonetics. I have also served of the organizing committee of the 2010 Young Researcher's Roundtable on Spoken Dialogue Systems (YRRSDS).

Quite a long time ago, I did a research masters at the University of Melbourne, Australia. I was part of the Language Technology Group where my supervisor was Steven Bird. Back in the day, I researched querying and manipulating linguistically annotated structured data.

Research Interests

Prosody, discourse and dialogue structure
Affective Computing (emotion recognition)
Multimodal language processing
Speech processing for social science research and assistive technologies

Contact

Office hours by appointment

email: <c . lai at ed ac uk>

Publications and Presentations

Catherine Lai, Mireia Farrús and Johanna D. Moore. in Speech Communication (accepted, in press)
[ paper ]

Zack Hodari, Catherine Lai, Simon King. Proceedings of Speech Prosody, Tokyo, Japan, May 2020 (held online)
[ paper ]

Catherine Lai, Beatrice Alex, Johanna D. Moore, Leimin Tian, Tatsuro Hori, Gianpiero Francesca. Proceedings of Interspeech 2019, Graz, Austria, September 2019
[ paper ]

Taylor Mahler, Marie-Catherine de Marneffe, Catherine Lai. Presented at Sinn und Bedeutung 2019 (SuB24), Osnabrück, Germany, September 2019
[ abstract ] [ poster ]

Aurora Constantin, Catherine Lai, Elaine Farrow, Beatrice Alex, Ruth Pel-Littel, Henk Herman Nap and Johan Jeuring. Proceedings of CHI 2019, Glasgow, UK, May 2019
[ paper ]

Michal Muszynski, Leimin Tian, Catherine Lai, Johanna D. Moore, Theodoros Kostoulas, Patrizia Lombardo, Thierry Pun, Guillaume Chanel. IEEE Transactions on Affective Computing (early access Feb 2019).
[ paper ] [ IEEE ]

Catherine Lai and Gabriel Murray. Workshop on Modeling Cognitive Processes from Multimodal Data (MCPMD'18), Boulder, USA, October 2018.
[ paper ]

Gabriel Murray and Catherine Lai. Group Interaction Frontiers in Technology (GIFT'18), Boulder, USA, October 2018.
[ paper ]

Leimin Tian, Catherine Lai, Johanna Moore. Proceedings of Grand Challenge and Workshop on Human Multimodal Language, Melbourne, Australia, July 2018.
[ paper ]

Leimin Tian, Michal Muszynski, Catherine Lai, Johanna Moore, Theodoros Kostoulas, Patrizia Lombardo, Thierry Pun, and Guillaume Chanel. Proceedings of ACII 2017, San Antonio, USA, October 2017
[ paper ] Best paper finalist!

Peter Bell, Joachim Fainberg, Catherine Lai, and Mark Sinclair. Proceedings of Interspeech 2017, Stockholm, Sweden, August 2017
[ paper ]

Janine Kleinhans, Mireia Farrús, Agustín Gravano, Juan Manuel Pérez, Catherine Lai, and Leo Wanner. Proceedings of Interspeech 2017, Stockholm, Sweden, August 2017
[ paper ]

Leimin Tian, Johanna D. Moore, Catherine Lai. Proceedings of SLT 2016, San Diego, USA, December 2016
[ paper ]

Catherine Lai, Mireia Farrús and Johanna D. Moore. Proceedings of Interspeech 2016, San Francisco, USA, September 2016
[ paper ] [ poster ]

Mireia Farrús, Catherine Lai and Johanna D. Moore. Proceedings of Speech Prosody 2016, Boston, USA, June 2016
[ paper ] [ poster ]

Catherine Lai and Johanna D. Moore. Presented at the Workshop on Identification and Annotation of Discourse Relations in Spoken Language (DiSpoL 2015), Saarbruecken, Germany, October 2015.
[ abstract ] [ poster ]

Leimin Tian, Johanna D. Moore, Catherine Lai. Proceedings of Affective Computing and Intelligent Interaction (ACII), Xi'an, China, September 2015.
[ paper ]

Alessandra Cervone, Catherine Lai, Silvia Pareti, Peter Bell. Proceedings of Interspeech 2015, Dresden, September 2015.
[ paper ]

Peter Bell, Catherine Lai, Clare Llewellyn, Alexandra Birch, Mark Sinclair. Proceedings of Interspeech 2015, Dresden, September 2015.
[ paper ]

Leimin Tian, Johanna Moore, Catherine Lai. Proceedings of The 4th Interdisciplinary Workshop on Laughter and other Non-Verbal Vocalisations in Speech, Twente, the Netherlands, April 2015.
[ paper ]

Catherine Lai and Steve Renals. Proceedings of Interspeech 2014, Singapore, September 2014.
[ paper ] [ slides ]

Catherine Lai. Proceedings of Speech Prosody 2014, Dublin, Ireland, May 2014.
[ paper ] [ poster ]

Johanna Moore, Leimin Tian and Catherine Lai. Computational Linguistics and Intelligent Text Processing, Lecture Notes in Computer Science, Volume 8404, pp 17-31, 2014.
[ paper ]

Catherine Lai, Jean Carletta and Steve Renals. Proceedings of Interspeech 2013, Lyon, France, August 2013.
[ paper ] [ slides ]

Catherine Lai, Jean Carletta and Steve Renals. Proceedings of the Workshop on Affective Social Speech Signals 2013, Grenoble, France, August 2013.
[ paper ]

Catherine Lai, Keelan Evanini, Klaus Zechner. Proceedings of SLaTE 2013, Grenoble, France, August 2013.
[ paper ]

Catherine Lai. Proceedings of Speech Prosody 2012, Shanghai, China, May 2012.
[ paper ]

Catherine Lai. Dissertation, University of Pennsylvania, April 2012.
[ pdf (18 MB!) ] [ Abstract ]

Keelan Evanini, Catherine Lai and Klaus Zechner. Proceedings on Meetings on Acoustics. 2011.
[ paper ] [ poster ]

Catherine Lai, Keelan Evanini and Klaus Zechner. Presented at New Tools and Methods for Very-Large-Scale Phonetics, Philadelphia, January, 2011.
[ abstract ] [ poster ]

Catherine Lai. Accepted for the 85th Annual Meeting of the Linguistic Society of America (LSA), Pittsburgh, January 6-9, 2011.
[ abstract ] The account of verum focus is fleshed out in my dissertation. Email me if you want further opinions on NPQs:)

Catherine Lai. Presented at NELS 41, Philadelphia, October 2010.

Catherine Lai. In Proceedings of Interspeech 2010, Makuhari, Japan, September 2010.
[ paper ] [ slides ]

Catherine Lai, Yanyan Sui and Jiahong Yuan. In Proceedings of Speech Prosody 2010, Chicago, USA, May 2010.
[ paper ]

Aviad Eilam and Catherine Lai. Presented at CONSOLE'09, Barcelona, Spain, Dec 2009.
[ slides ]

Catherine Lai. Proceedings of Interspeech'09, Brighton, UK, Sept 2009.
[ paper ] [ poster ]

Catherine Lai and Steven Bird. Journal of Logic, Language and Information, 19(1), pp 53-73, 2010.

Catherine Lai. Presented at at Psychocomputational Models of Human Language Acquisition (Workshop at Cog Sci 2008), Washington D.C, July 2008.
[ slides ] The working paper is below but needs some fixes.

Catherine Lai. In Proceedings of Speech Prosody 2008, Campinas, Brazil, May 2008.
[ paper ] [ slides ] NB: I updated the analysis for this quite a lot for the dissertation. I'd suggest you look at that if you are interested in this topic.

Catherine Lai, Kyle Gorman, Jiahong Yuan, Mark Liberman. In Proceedings of Interspeech'07, Antwerp, Belgium, August 2007
[ paper ] [ poster ] [ ISCA ]

Catherine Lai and Steven Bird. Proceedings of the 19th Pacific Asia Conference on Language, Information and Computation (PACLIC). pp 1-12, Taipei, Taiwan. Taipei: Academia Sinica. December 2005.
[ pdf ]

Catherine Lai. MSc (Research) Thesis, Department of Computer Science & Software Engineering, University of Melbourne, 2005
[ ps ] [ pdf ] [ slides ]

Catherine Lai and Steven Bird. Proceedings of the Australasian Language Technology Workshop, December 2004
(If you are interested in this, you are better off looking at my masters thesis...)

Working Papers and Other Business

Dialogue with attitude: The contribution of cue words and prosodic meaning in conversational speech
Catherine Lai. April 2011.
[ slides ]
Some slides about the cue word part of my dissertation.

Bayesian Iterated Learning and Portuguese Clitics
Catherine Lai. Paper for Ling-575 Mental Lexicon, University of Pennsylvania, 2007
[ paper ]

"Strange women lying in ponds distributing swords is no basis for a system of government"
-- Dennis (Monty Python's Holy Grail)