Established in 2016, the International Research Laboratory “Multimodal Biometric and Speech Systems” supervises Master’s and PhD students in their research and trains top-tier specialists in the processing and analysis of text, audio, and video data, as well as machine learning. 

The laboratory conducts research in the following fields:

• dialogue systems: the development of hybrid solutions based on search and generative approaches to model contextualized dialogues, assess the mode of users by their voice in argumentative dialog systems.

• automatic recognition of a person's psychophysiological state: the recognition of one’s emotional state, leadership skills and personality dominance, engagement in the interaction between a human and a robot, and stress level. The results of the study are applicable in a range of fields, from education to smart house control.

• speech synthesis: the generation of expressive and emotional speech.

Available equipment

• Vital Voice Tools software for lab projects in speech synthesis;

• SIS II – a specialized sound editor for lab projects in the digital processing of speech signals.

Educational programs

• A double-degree PhD program with the University of Ulm (Germany);

• The Leonhard Euler Scholarship Program with the University of Ulm (Germany) for Master’s students.

Partners

• University of Ulm (Germany);

• St. Petersburg State University;

• St. Petersburg Federal Research Center of the Russian Academy of Sciences.