The Speech Recognizing System of ALL is a standalone software product that is prepared for converting digitally recorded speeches to the corresponding sequences of words. The domain of the recognizable speeches is practically non-constrained, as the software is enabled to manage more than 300 000 spoken words. The system can automate the bulk of the work whenever digitally recorded speeches (the events/minutes of an assembly, meeting, hearing or trial, etc.) are to put into writing.
At present the Speech Recognizing System of ALL works in English and Hungarian. However, it can be adapted to other languages in a straightforward manner – by replacing the linguistic knowledge being embodied as data components into the system.
Formal evaluations of the effectiveness of the Speech Recognition System of ALL have demonstrated that its quality characteristics (Accuracy and Word Error Rate) are close to the high-quality standards of continuous speech recognition when working with open domains.