Ivan Tampel, Speech Technology Center, (812) 325-88-48

Abstracts:

Sound pattern recognition is one of the perspective areas in multimedia technology development. Speech Technology Center has great experience in sound signal recognition technology for various multimedia applications. Speech recognition technology enables to facilitate and accelerate access to the database and work with the system. Examples of such systems developed by STC are VoiceCom SDK, voice Navigator, Truffaldino. VoiceCom SDK is voice command (single-word) recognition technology. This software toolkit is meant to be embedded into any of business, medical, educational and multimedia software in order to enable voice control feature. VoiceCom SDK allows also to check pronunciation in foreign language acquisition systems. Voice Navigator performs search and instant execution of any Windows application by voice commands. The Truffaldino system allows you to control all your home equipment by voice commands. This systems makes our life more comfortable and convenient, helps people with disabilities. Biometric speaker verification technology is realized in Voice Key SDK. The technology is used for any software application with security features. The music samples recognition technology is used in the Music Spotting System. The system is real-time software for identifying music samples in a sound stream. It is designed for advertising agencies, music copyright owners, broadcasting companies.