Pattern Recognition systems are not error-free. Human intervention is typically needed to verify and/or correct the result of such systems. To formalize this fact, a new framework, which integrates the human activity into the recognition process taking advantage of the user's feedback, is described. Several applications, involving Interactive Speech Transcription and Multimodal Interactive Machine Translation, have recently been considered under this framework. These applications are reviewed in this paper, and some experiments, showing that the proposed framework can save significant amounts of human effort, are also presented.
展开▼
