Computational Speech Group at UEF will be hosting a summer school (2024) on Introduction to Speech and Machine Learning

NEWS – New Funding Available

New PhD position opening: “Explainable Speech Deepfake Characterization”, funded by Doctoral Education pilot “AI-DOC” (The Finnish Doctoral Program Network in Artificial Intelligence) – Apply no later than 2 April 2024!

A funded PhD position available in Tomi’s 2022-2026 Academy of Finland funded project Generalized Voice Anti-Spoofing and Voice Biometrics (SPEECHFAKES)

If you’re interested, please contact Tomi by e-mail <tomi.kinnunen@uef.fi> along with your resume and publication list.

Home

Main research areas: Digital speech processing, machine learning, speech science

Current research topics: Automatic speaker verification (ASV), spoofing and countermeasures (CM) for ASV, spoken language identification, voice conversion (VC)

The main topic of our group is speaker recognition: the task of connecting speech samples to an identity (who is speaking?). We work on improving both robustness (improved accuracy under varied channels, noise, and other disturbances) and security of such systems (detection of representation attacks, also known as spoofing attacks). Our research group not only takes regularly part in the technology evaluations in our field but also contributes to open data science as a co-organizer of public evaluation benchmarks (including ASVspoof and VC challenge) and collection of other data, such as the AVOID corpus.

In our view, understanding the limits of ASV requires a deep understanding of the attacks as well; we, therefore, work also on related problems such as voice conversion (conversion of speaker identity) and disguise (avoiding being identified as oneself). We believe in keeping the mind open for new, unexpected research directions through multidisciplinary research to address fundamental problems in the computer processing of speech. In our view, one should not build only data-driven black boxes but aim at understanding what characterizes speaker, language, and ‘spoof’ cues relevant for machine and human observers. Besides our core focus on computational speech processing methods that rely on machine learning and statistics, we also apply perceptual and acoustic methods in our research. As most of the problems within the speech field are beyond the reach of any single individual or a research group, we also believe in the importance of research collaboration that expands across borders and continent.

Interested to collaborate or work with us? Feel free to drop an e-mail to associate professor Tomi Kinnunen (tomi.kinnunen@uef.fi) to discuss further.