Speech and Multimodal Interfaces Laboratory
Established in 2008 on the basis of the Group for Speech Informatics, formed in 1984.
We carry out fundamental and applied research and development within the framework of projects funded by the Ministry of Science and Higher Education of the Russian Federation, the Russian Academy of Sciences, the Government of St. Petersburg, the Russian Federation President Council on Grants, the Russian Foundation for Basic Research and the Russian Foundation for Humanitarian Research, FP6/7, and a range of Russian and foreign companies.
Currently we are developing:
- Speech technologies, including automatic recognition and speech synthesis in Russian
- Methods for computer vision and their applications
- Audiovisual signal processing, including bimodal speech recognition and synthesis
- Intelligent human-machine interfaces and dialog systems
- Assistive information technologies
- Multimodal user interfaces combining audio, video, gesture, and text information
- Smart rooms and intelligent spaces
The laboratory has been the founder and the lead organizer of a series of annual International Conferences “Speech and Computer” (SPECOM) since 1996 till the present time.
The laboratory also hosted the international seminar on speech technologies for low-resource languages (SLTU-2014) and was one of the initiators of the series of interdisciplinary seminar “Analysis of spoken Russian” AP3 in St. Petersburg
The laboratory established a scientific and educational center "Technologies of intellectual space" in 2010
The laboratory staff members are participants of ISCA, IAPR, IEEE, EURASIP, and other international associations, as well as belong to scientific journals editorial boards and program/scientific/organizing committees of international conferences
The laboratory has published over 300 scientific works (almost half of them are in English, including jointly with scientists from Japan, France, Germany, the Czech Republic, Turkey, Greece, Poland, Switzerland, the USA, South Africa, Mexico, Belarus, Ukraine and etc.), among them more than 100 publications in leading foreign and Russian journals included in the Web of Science and Scopus lists, as well as 3 monographs, 3 textbooks and 2 patents.
Our staff members regularly participate in international scientific conferences and congresses INTERSPEECH, ICPR, EUSIPCO, HCI International, TSD, LREC, ICPhS, ICA, eNTERFACE, Speech Prosody, GRAPP, SLTU, SPECOM, PRIA, Graphicon, NEW2AN, ICUMT, and others.