Currently, I am a Senior Research Scientist at Yandex Research in Moscow, Russia. Prior to this I completed my PhD in Uncertainty Estimation and Speech Processing at Cambridge University under the supervision of Professor Mark Gales.
My primary research interest is Bayesian-inspired approaches for Uncertainty estimation for Deep Learning and their practical application at-scale to tasks in NLP, NMT, Speech and computer vision. Additionally, I am also interested in Speech Recogntion and Synthesis.
One of my hobbies is to use generative neural models, such as Flows, Variational Auto-encoders and Generative Adversarial Networks to create digital generative neural art. Furthermore, I have a general interest in architectures, optimisers and adaptation methods for Deep Learning. Additionally, my broad research interests include Artificial Intelligence, Machine Learning, Natural Language Processing, Speech Recognition and related technologies.
Andrey Malinin, Bruno Mlodozeniec, Mark J.F. Gales "Ensemble Distribution Distillation". 2020. In Proceedings of the 8th International Conference on Learning Representations (ICLR 2020). ( .pdf ) ( bibtex )
Andrey Malinin, Mark J.F. Gales "Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness". 2019. In Advanaces of Neural Information Processing Systems (NeurIPS) 2019. ( .pdf ) ( bibtex ) ( Presentation ) ( poster )
Andrey Malinin, Mark J.F. Gales "Predictive Uncertainty Esimtation via Prior Networks". 2018. In Advanaces of Neural Information Processing Systems (NeurIPS) 2018. ( .pdf ) ( bibtex )
Andrey Malinin, Kate Knill, Mark J.F. Gales "A Hierarchical attention based model for off-topic spontaneous spoken response detection". 2017. In Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). ( .pdf ) ( bibtex ) ( poster )
Andrey Malinin, Kate Knill, Anton Ragni, Yu Wang and Mark J.F. Gales "An attention based model for off-topic spontaneous spoken response detection: An Initial Study". 2017. In Proceedings of the ISCA Workshop on Speech and Language Technology for Education (SLaTE). ( .pdf ) ( bibtex ) ( talk )
Andrey Malinin, Anton Ragni, Kate Knill, Mark J.F. Gales "Incorporating Uncertainty into Deep Learning for Spoken Language Assessment". 2017. In Proceedings of the 2017 Association for Computational Linguistics (ACL). ( .pdf ) ( bibtex )
Andrey Malinin, Rogier C Van Dalen, Yu Wang, Kate Knill, Mark J.F. Gales "Off-topic Response Detection for Spontaneous Spoken English Assessment". 2016. In Proceedings of the 2016 Association for Computational Linguistics (ACL). ( .pdf ) ( bibtex ) ( poster )
Google NLP Summit 2017 "Incorporating Uncertainty into Deep Learning for Spoken Language Assessment" .
UK Speech 2017 Conference "Attention based models for off-topic spontaneous spoken response detection" .
UK Speech 2017 Conference "Incorporating Uncertainty into Deep Learning for Spoken Language Assessment" .
SLaTE 2017 Workshop "An attention based model for off-topic spontaneous spoken response detection: An Initial Study" .
Association for Computational Linguistics 2017 Conference "Incorporating Uncertainty into Deep Learning for Spoken Language Assessment" .
Cambridge Language Sciences Annual Symposium 2016. "Deep Density Networks with Uncertainty for spontaneous spoken language assessment". ( poster )
ALTA Institute Seminar 2016. "Deep Learning for Automatic Assessment of Spoken English". ( talk )
Association for Computational Linguistics 2016 Conference "Off-topic Response Detection for Spontaneous Spoken English Assessment" . ( poster )
Uk Speech Conference 2016 "Off-topic spoken response detection for language assessment" . ( poster )
ALTA Institute Seminar 2016. "Off-topic spoken response detection for language assessment". ( talk )
Cambridge Language Sciences Annual Symposium 2015. "Rejection Methods for Automatic Assessment of Spoken English".