This web-based REST Service integrates the LinkedTV techniques for audio, visual and textual analysis of multimedia content. Its communication with the LinkedTV platform is fully automatic, while the analysis is performed by three interconnected services that communicate via established synchronous and asynchronous communication channels between them. Specifically, the audio analysis sub-service performs Automatic Speech Recognition (ASR) and Speaker Identification on the audio channel, the visual analysis sub-service performs Shot Segmentation, Concept Detection, Chapter Segmentation and Face Detection and Tracking on the visual channel, and the text analysis sub-service performs Keyword Extraction on the video’s subtitles or meta-data, or using the output of the audio analysis (i.e. the created ASR transcripts).
