Lawrence Cavedon is an Associate Professor in the School of Science, and the Associate Dean and Discipline Head of Computer Science and IT.His research interests include spoken dialogue and speech interfaces, biomedical and health analytics, and Artificial Intelligence in general.
Associate Professor Lawrence Cavedon's career has spanned academia and the IT industry as both res earcher and engineer, leaving him with a strong interest in industry-focused problems. Much of his recent and current research projects are performed in collaboration with industry and domain partners, including SEEK, Elsevier, IBM Research, Real Thing Entertainment, and health organisations Alfred Health, Melbourne Health, Peter MacCallum Cancer Centre, and the Victorian Dept. of Health.
While at Stanford, he collaborated on funded projects with NASA, Bosch Corp, VW America, and Boeing. He has also led software product teams at Verticalnet Inc in Silicon Valley.
More information about his activities and research can be found on his personal webpage.
Lawrence is the Discipline Head for Computer Science and IT.
Lawrence's teaching activities are focused on advanced Software Engineering courses, such as Software Engineering: Process and Tools (COSC2299) and Systems Architecture (ISYS1088/89).
Lawrence has been a Chief Investigator on 5 past or current ARC Linkage grants, including 2 as Lead CI, as well as other grants totaling approx. $2.5million since 2014. He is also a CI on a new ARC Industry Transformational Training Centre in conjunction with UniMelb and IBM Research, on Cognitive Computing for Medical Technologies.
See his Google scholar page for a complete list of his publications.
- Ph.D. Cognitive Science, The University of Edinburgh (UK)
- M. Sc. Computer Science, The University of Melbourne
- B. Sc. (Honours), Computer Science, The University of Melbourne
- 2005-2014: NICTA (National ICT Australia), Victoria Research Lab
- 2002-2005: Stanford University, Center for the Study of Language and information
- 2000-2002: Verticalnet Inc. (California), Advanced Technologies Group
- 1987-1990: Australian Artificial Intelligence Institute
Lawrence has worked in the tech industry in both Australia and Silicon Valley in California.
In Silicon Valley, he was a Scientist and a Lead Engineer in the Advanced Technologies Group at Verticalnet Inc., the first Business-to-Business technology company to IPO. In Australia, he worked for the Australian Artificial Intelligence Institute, a contract R&D organisation applying AI techniques to industry problems.
Lawrence also collaborates extensively with industry in his research. At NICTA (National ICT Australia, Australia's Centre for ICT Research Excellence), he led projects on the topic of biomedical and health analytics, in collaboration with Alfred Health, Melbourne Health, Barwon Health and the Peter MacCallum Cancer Centre. At Stanford University, he collaborated closely on joint projects with Bosch Corp, VW America, Boeing, and NASA.
At RMIT, he has research projects with SEEK, IBM Research, Elsevier, Real Thing Entertainment, and other companies and organisations.
Lawrence also likes to engage industry in his teaching and regularly organises presenters large corporations (e.g., IBM, Amazon Web Services), mid-sized innovative technology companies (Redbubble, Zendesk), and startups.
- Led team that developed first commercial Semantic Web Services platform
- NSW Engineering Excellence Award (R&D) for Thinking Head project
- Stanford CSLI dialogue system, commercially licensed by major corporations
- F. Weng, L. Cavedon, et al: Method and system for interactive conversational dialogue for cognitively overloaded device users; US Patent 7,716,056.
- D. Mirkovic, L. Cavedon: Dialogue management using scripts; US Patent 8,041,570
- D. Mirkovic, L. Cavedon, et al: Dialogue management using scripts and combined confidence scores; US Patent 7,904,297.
- H. Cheng, L. Cavedon, et al: Method and system for adaptive navigation using a driver's route knowledge; US Patent 7,424,363
- Spina, D.,Trippas, J.,Cavedon, L.,Sanderson, M. (2017). Extracting audio summaries to support effective spoken document search In: Journal of the Association for Information Science and Technology, 68, 2101 - 2115
- Trippas, J.,Spina, D.,Cavedon, L.,Sanderson, M. (2017). How do people interact in conversational speech-only search tasks: A preliminary analysis In: Proceedings of the Second ACM SIGIR Conference on Information Interaction and Retrieval (CHIIR 2017), Oslo, Norway, 7-11 March 2017
- Fayek, H.,Lech, M.,Cavedon, L. (2017). Evaluating deep learning architectures for Speech Emotion Recognition In: Neural Networks, 92, 60 - 68
- Pitson, G.,Banks, P.,Cavedon, L.,Verspoor, K. (2017). Developing a manually annotated corpus of clinical letters for breast cancer patients on routine follow-up In: Studies in Health Technology and Informatics, 235, 196 - 200
- Spina, D.,Maistro, M.,Ren, Y.,Sadeghi, S.,Wong, W.,Baldwin, T.,Cavedon, L.,Moffat, A.,Sanderson, M.,Scholer, F.,Zobel, J. (2017). Understanding User Behavior in Job and Talent Search: An Initial Investigation In: 2017 SIGIR Workshop on eCommerce, Tokyo, Japan, 11 August 2017
- Pereira-salgado, A.,Westwood, J.,Russell, L.,Ugalde, A.,Bronwen, O.,Seymour, J.,Butow, P.,Cavedon, L.,Ong, K.,Aranda, S.,Breen, S.,Kirsa, S.,Dunlevie, A.,Schofield, P. (2017). Mobile health intervention to increase oral cancer therapy adherence in patients with chronic myeloid leukemia (the REMIND system): Clinical feasibility and acceptability assessment In: JMIR mHealth and uHealth, 5, 1 - 15
- Fayek, H.,Lech, M.,Cavedon, L. (2016). On the correlation and transferability of features between automatic speech recognition and speech emotion recognition In: Proceedings of the Interspeech 2016 Conference, San Francisco, United States, 8-12 September 2016
- Fayek, H.,Lech, M.,Cavedon, L. (2016). Modeling subjectiveness in emotion recognition with deep neural networks: Ensembles vs soft labels In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2016), Vancouver, Canada, 24-29 July 2016
- Kocbek, S.,Cavedon, L.,Martinez, D.,Bain, C.,MacManus, C.,Haffari, G.,Zukerman, I.,Verspoor, K. (2016). Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources In: Journal of Biomedical Informatics, 64, 158 - 167
- Fayek, H.,Lech, M.,Cavedon, L. (2015). Towards real-time speech emotion recognition using deep neural networks In: Proceedings of the 9th International Conference on Signal Processing and Communication Systems (ICSPCS 2015), Cairns, Australia, 14-16 December 2015
- Industrial Transformation Training Centre in Cognitive Computing for Medical Technologies (administered by University of Melbourne). Funded by: ARC Industrial Transformation Training Centre 2018 from (2017 to 2021)
- User-Adaptive Search and Evaluation for Complex Information-Seeking Tasks. Funded by: ARC Linkage Grant 2015 Round 1 from (2016 to 2019)
- Biomedical Informatics for effective health decision making. Funded by: Department of Health (State of Victoria) Contract from (2015 to 2016)
- ASTROID: Active Surveillance and other Treatment Options for prostate cancer - Administered by Swinburne University of Technology. Funded by: National Health and Medical Research Council (NHMRC) Project Grants 2015 from (2015 to 2019)
- Real-time mental state tracker: a mobile phone based approach. Funded by: Defence Science Institute Collaborative Research Scheme 2015, Round 1 from (2015 to 2016)
3 PhD Completions and 1 Masters by Research Completions5 PhD Current Supervisions