Keynote Speakers
Tomi H. Kinnunen
Tomi H. Kinnunen is full professor of speech technology at the University of Eastern Finland (UEF) where he leads Computational Speech Group. He received his Ph.D. degree (computer science) from the University of Joensuu in 2005. From 2005 to 2007, he was an Associate Scientist at the Institute for Infocomm Research, Singapore. In addition, he was a visiting researcher at National Institute of Informatics, Japan (2015-16) for 6 months, under a mobility grant from the Academy of Finland. His group has received funding from multiple large Academy of Finland projects, in addition to one EU H2020 funded project, and a recently started Voice Communication Sciences (VoCS) project funded by the prestigious Marie Skłodowska-Curie Action (MSCA). He chaired the Odyssey: Speaker and Language Recognition workshop in 2014. He has served in editorial tasks in IEEE/ACM Transactions on Audio, Speech, and Language Processing; Speech Communication; and Digital Signal Processing. He is one of the Technical Program Chairs of Interspeech 2025 (Rotterdam). His research group focuses on speech deepfakes (spoofing attacks), speaker recognition, children speech processing, speech database design, and performance benchmarking. He is one of the co-founders of the ASVspoof challenge series that has contributed to multiple large open speech databases for benchmarking deepfake detectors and spoofing-robust speaker verification systems.
Dr. Cassia Valentini
Dr. Cassia Valentini is a Senior Researcher at the Centre for Speech Technology Research (CSTR) at the University of Edinburgh. She holds positions in both the University and at SpeakUnique, a UK-based company specialising in voice banking and repair services that enable individuals to create personalised synthetic voices for communication aids. Cassia obtained her PhD from CSTR in 2013 as a Marie Curie Fellow, focusing on enhancing the intelligibility of synthetic speech in noisy environments. Since then, she has contributed to numerous national and international research projects, both academic and industry-funded. Her work spans various topics, including text-to-speech (TTS) for blind children, voice banking and reconstruction, TTS for navigational systems for the elderly, neural speech synthesis, spoken content production, and speech generation for indigenous language education. She chaired the UK Speech committee from 2015 to 2016 and co-coordinated two editions of the Hurricane Challenge on speech intelligibility enhancement in adverse conditions.
