- Improving Numerical Stability of Normalized Mutual Information Estimator on High Dimensions, IEEE Signal Processing Letters, 2025.
- Inferring personal intake recommendations of phosphorous and potassium for end-stage renal failure patients by simulating with Bayesian hierarchical multivariate model, Plos ONE, 2024 (accepted).
- Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs, IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 31, p. 1706-1719, 2023.
- GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters, IEEE Transactions on Games, vol. 15, no. 4, pp. 566-579, Dec. 2023.
- Optimizing Tandem Speaker Verification and Anti-Spoofing Systems, IEEE Transactions on Audio, Speech and Language Processing, Vol. 30, pp. 477-488, January, 2022.
- Mixed-Effect Bayesian Network Reveals Personal Effects of Nutrition, Scientific Reports, Vol. 11, No. 12016, 2021.
- Maximal Figure-of-Merit Framework to Detect Multi-label Phonetic Features for Spoken Language Recognition, IEEE Transactions on Audio, Speech and Language Processing, Vol. 28, pp. 682-695, January, 2020.
- Semi-Supervised generative Autoencoder for single cell data, Journal of Computational Biology, 2019 (accepted).
- On Limits of Automatic Speaker Verification: Explaining Degraded Recognizer Score Through Acoustic Changes Resulting from Voice Disguise, Journal of the Acoustic Society of America, 2019 (accepted).
- Hemap: An interactive online resource for characterizing molecular phenotypes across hematologic malignancies, Cancer Research, doi: 10.1158/0008-5472.CAN-18-2970, 2019.
- Data-driven characterization of molecular phenotypes across heterogenous sample collections, Nucleic Acids Research, doi: 10.1093/nar/gkz281, 2019.
- Acoustical and perceptual study of voice disguise by age modification in speaker verification, Speech Communication, Vol. 95, pp. 1-15, December 2017.
Research Experience
- 2022-2023: Finnish PI of the mobility project: 'Planning with Deep Graph Neural Networks' funded by Academy of Finland.
- 2019: PI of a MATINE funded deepfake detection project.
- 2018-2019: co-PI of consortium of 'Deep reinforcement learning for physical agents (DEEPEN)' project funded by Academy of Finland.
- 2015: PI in a one year foreign accent recognition project funded by MATINE, The Finnish Defence Forces.
- 2011-2014: PI in a 3-year dialect and accent recognition post-doc project funded by Academy of Finland.
Background
Research interests include Artificial Intelligence, Reinforcement Learning, Machine Learning, Bayesian Inference, Bioinformatics, and Speech technology in general, but particularly speaker recognition and language recognition.