WEBSTEN TEXT SPONTANEOUS SPEECH CONVERSION SYSTEM
Purpose of the development:
Web-based system for converting audio information into text.
Recommended application field:
Potential users: television and radio studios, analytical centers, special services.
Technical characteristic:
Languages: Ukrainian, Russian and English (with the possibility of expansion); word-by-word reliability - 60-90% (depending on the recording quality); the informational stream width of the primary audio data is not less than 60 Kbps.
Advantages over analogues:
Foreign analogues are intended for other languages; finding fragments of speech corresponding to various persons; search for a suitable fragment by text, face and the like; regulation of the speed of obtaining the recognition result depending on the priority of the task; viewing text synchronously with sound and video and vice versa; the ability to edit the recognition result to obtain a verified transcript.
The development stage readiness:
Ready for application
Description of the development:
() Input data includes audio and video files downloaded from a user's computer or from the Internet.
corresponds technical description
Ready for implementation
Possibility of transfer abroad:
Combinated reduction to industrial level Joint production, sale, exploitation
Photo
Country
Ukraine
For additional information turn to: E-mail: gal@uintei.kiev.ua
|