SYSTEM FOR AUTOMATIC ASSESSMENT OF FLUENCY IN SPOKEN LANGUAGE AND A METHOD THEREOF

摘要

The present invention proposes an invention for acoustic analyses of recorded speech, carried out to rate a speaker's oral skills. In the disclosed system, the prosodic features of the speech signal are used to rate spoken language fluency. This is achieved differently in each of the two possible scenarios: (i) Text-dependent: where the speaker reads out presented text and (ii) Text- independent: where the speaker utters a monologue using words of her choice. The disclosed system comprises a user attributes extraction block (1) to accept input, a model attributes extraction block (2) to extract corresponding set of model attributes and an attributes comparison block (3) for comparison and for obtaining of fluency report (9).