Speech and Multimodal Interfaces Laboratory

Projects

2017-18
Development of a neural network based acoustic model for a Russian speech-to-text conversion system
MK-1000.2017.8
2017-18
Development and research of an automatic system for recognition of human’s natural emotions from speech
MD-254.2017.8
2016-18
Principles for the allocation of tasks between service robots and means of cyber-physical intelligent environment for the multimodal user support
16-19-00044
2016-19
Development of methods and software for estimating deception of transmitted voice messages
16-37-60085-mol_a_dk
2016-19
Development of a universal assistive information technology based on multimodal human-computer interfaces
16-37-60100-mol_a_dk
2016-17
Mathematical and programming software for evaluating speech truthfulness
MK-7925.2016.9
2015-17
Development of methods of multimedia data processing and exchange in peer-to-peer web application of multipoint videoconferencing
15-07-06774-а
2015-17
Research of acoustic and language models based on artificial neural networks for an automatic large vocabulary Russian speech recognition system
15-07-04322-а
2015-17
Models and methods of audio-visual signal processing for bimodal Russian speech recognition
15-07-04415-а
2015-17
Study of the acoustical cues differentiating phonational speech disfluencies in the spontaneous speech
15-06-04465-а