Speech is a unique and rich health signal: no other signal contains its singular combination of cognitive, neuromuscular and physiological information. However, its highly personal and complex nature also means that there are several significant challenges to overcome to build a reliable, useful and ethical AI tool suitable for widespread use in health research and clinical practice. This presentation will highlight and discuss future challenges in relation to the translation of AI-generated speech analysis into clinical practice.

Reserve your space on Eventbrite for in-person or online attendance. This seminar is part of the King’s Institute for Artificial Intelligence’s seminar series.

Dr Nicholas (Nick) Cummins is a Lecturer in AI for speech analysis for health at the Department of Biostatistics and Health Informatics at King’s College London, where he leads the Voice and Speech Processing for Health group. The group conduct pioneering research to advance the integration of speech technologies and biomarkers into clinical research and practice. Nick is also the Chief Science Officer for Thymia, a start-up developing technologies to ​​analyse facial microexpressions & speech patterns to make mental health assessments faster, more accurate and objective. Guided by a responsible AI framework, Nick’s research combines cutting-edge speech processing techniques, patient and public involvement and engagement (PPI-E), advanced statistical analytics, and machine learning. This multidisciplinary approach aims to harness the transformative potential of speech technologies, creating reliable tools that drive innovation in health research and clinical applications.