Evaluation of improved components of amis project for speech recognition, machine translation and video/audio/text summarization

Abstract

To evaluate a system that automatically summarizes video files (image and audio) and text, how the system works, and the quality of the results should be considered. With this objective, the authors have performed two types of evaluation: objective and subjective. The actual assessment is performed mainly automatically, while the individual assessment is based directly on the opinion of people, who evaluate the system by answering a set of questions, which are then processed to obtain the targeted conclusions. One of the purposes of the described research is to try to narrow the space of possible summarization scenarios. Meanwhile, in the light of individual results obtained, the researchers cannot unambiguously indicate one single scenario, recommended as the only one for further development. However, the researchers can state with certainty that the new development of scene 1, which has received many negative evaluations among professionals, should be discontinued. Considering the results of the set of questions about the quality of the complete system, the end-users have evaluated the scenario 3, and they think that the quality is excellent, obtaining results over 70% on a scale of 0 to 100.