期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：12
页码：20260
DOI：10.15680/IJIRSET.2016.0512002
出版社：S&S Publications
摘要：Behind any cloud-based service there is a complex infrastructure that varies greatly depending on theindustry and the types of services provided. Storing, searching and finding data through deep learning and artificialintelligence is the logical and necessary way forward. In the entertainment industry for example, digital media librariesoffer massive amounts of media materials to the public where the big issues are finding, accessing and recommendingspecific content out of enormous set of choices. One way to approach the issue is through media-descriptive metadata,which comes as plain text (synopsis), sounds (narration), images (cover shots, etc.) or short videos (trailers). Thishowever, is the conventional way that is building even more around the problem of finding specific content easily,hence not directly solving the main issue. This is so not only because specific applications must be developed, but alsobecause they require physical human interaction with the system by using user dependent keystrokes in most cases.This in turn makes the access and extraction of digital content cumbersome and slow. Hence a better, morepersonalized automatic behind the scenes approach is needed.
关键词：Personalization; Emotion; Speech; Voice; Recognition; Digital Asset Ecosystem; Cloud Services
