Summer school
of machine learning

Enhance your skills in deep learning practicing on sound and pictures analysis,
and audiovisual affect recognition

Summer school partners:

The main advantages of learning

Knowledge

You will improve your knowledge of Machine Learning for the tasks of analyzing audio and video information

Real project

You will participate in a real project of the STC Group, which is the international leader in speech recognition

Qualification

You can improve your skills in modern tools for developing algorithms for artificial intelligence and neural networks

Science

You will be able to solve an actual scientific and technical problem

Practice

You will immediately apply the acquired knowledge in practice

About the School

The summer school will be held in St. Petersburg
from 2 to 15 August.

The doors of the school are open to all senior students and young IT specialists from Russia and the Republic of Belarus. The possibility of participation of candidates from other countries will be considered individually. Participation in the event is free! Meals and accommodation in the hostel of the University ITMO is paid by the school's organizers, and the most distinguished students by the results of the test task will be reimbursed transportation costs.

Lecturers

Prof.Dr. habil. Björn W. Schuller

Full Professor & Head of the Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany; Reader (Associate Professor) in Machine Learning, Group on Language, Audio & Music, Imperial College London, London/U.K.; Chief Executive Officer (CEO) and Co-Founder, audEERING GmbH, Gilching/Germany; Visiting Professor, School of Computer Science and Technology, Harbin Institute of Technology, Harbin/P.R. China. Dr. Schuller is Fellow of the IEEE for contributions to Computer Audition, elected member of the IEEE Speech and Language Processing Technical Committee, and Senior Member of the ACM. He (co-)authored 5 books and more than 700 publications in peer reviewed journals (>100).

Dr. Heysem Kaya

Heysem Kaya completed his PhD thesis on computational paralinguistics and multimodal affective computing at Computer Engineering Department, Boğaziçi University in 2015. His works won two Computational Paralinguistics Challenge Prizes: Physical Load Sub-challenge at INTERSPEECH 2014, Eating Condition Sub-challenge at INTERSPEECH 2015, Sincerity Sub-Challenge at INTERSPEECH 2016. He also was runner up in video based emotion recognition in the wild challenge (EmotiW 2015 @ ICMI). His research interests include mixture model selection, speech processing, computational paralinguistics, affective computing, multi-view/multi-modal learning and intelligent biomedical applications.

Prof. Aleksei Potapov

PhD., Professor of the Department of Computational Photonics and Videomatics at ITMO University. Winner of a competition of grants for young scientific and pedagogical workers of universities of St. Petersburg. The winner of the grant competition of the President of the Russian Federation for the state support of young Russian scientists - doctors of sciences in the category "Information and Communication Systems and Technologies".

The summer school program

Affect recognition

  1. Paralinguistics: challenges, recent trends and hints
  2. Leveraging deep transfer learning for multi-modal affect recognition in the wild
  3. Explainable machine learning: a neglected frontier and an emerging research direction

Audio data analysis, classification algorithms

  1. Audio data analysis tasks
  2. Speech feature extraction techniques
  3. Multimodal information fusion
  4. Classification algorithms

Deep learning

  1. GAN, VAE
  2. Person re-identification, semantic vision

Practical classes will be devoted to solving problems of audiovisual affect recognition.

Contact us

49 Kronverksky Pr., St. Petersburg, 197101, Russia

Birzhevaya line, 14-16, of.335, Saint-Petersburg, Russia, 199034

Isaev Ilia Vladimirovich

+7 981 834 40 99

ivisaev@corp.ifmo.ru

2018 © Speech Technology Center.
All rights reserved.

Privacy policy

Registration rules