Four-phase re-speaker training system

Abstract

Since the re-speaker approach to the automatic captioning of TV broadcastings using large vocabulary continuous speech recognition (LVCSR) is on the increase, there is also a growing demand for training systems that would allow new speakers to learn the procedure. This paper describes a specially designed re-speaker training system that provides gradual four-phase tutoring process with quantitative indicators of a trainee progress to enable faster (and thus cheaper) training of the re-speakers. The performance evaluation of three re-speakers who were trained on the proposed system is also reported.