Scientific School

In the mid-1970s DSc in Engineering B.M. Lobanav established the Speech Synthesis and Recognition Scientific School in Belarus. Since 1974 till 1988 Lobanav headed the Speech Technology Laboratory in Minsk department of Central Research Institute of Communications, and since 1988 till 2011 –  the Speech Synthesis and Recognition Laboratory of United Institute of Informatics Problems, NAS of Belarus. At different times among the school participants were PhD in Philosophy professor A.B. Karneuskaja, PhD in Engineering B.V. Panchanka, DSc in Engineering A.S. Rylou, PhD in Engineering T.V. Leukouskaja, DSc in Pedagogics G.V. Losic, PhD in Engineering L.I. Tsirulnik, PhD in Engineering A.G. Davydau, PhD in Engineering I.A. Kheydarau, M.P. Degtyarou, V.U. Kisyaliou and many others.

The main research areas of the Speech Synthesis and Recognition Scientific School include:

  • Multilingual and multi-voiced text-to-speech synthesis;
  • Person’s voice and diction computer cloning;
  • Robust recognition of discrete and connected speech;
  • Identification of key words in the speech flow;
  • Computer-assisted rehabilitation systems for people who are deaf, hard of hearing or are visually impaired.

Over the period up to 2008, the theoretical and practical activity of the School is described in the article by B.M. Labanau About the development of speech technology in Belarus

If you have found a spelling error, please, notify us by selecting that text and pressing Ctrl+Enter.