The purpose of this study is to search shot clip' using variables influencing on the VOD purchase intention and watching intention of real-time broadcasting. This research focused on usage motivation, usage experience such as use time, time of utilization, genre, utilization pattern.Controlling demographic factors, results show that personal relation, benefit against whole broadcast, education genre, watching video, video sharing and recommendation were statistically influential to VOD purchase intention. And, results show that flexibility of use, drama/movie genre, read and write comments were statistically influential to watching intention of real-time broadcasting.
Encoding speaker-specific characteristics from speech signals into fixed length vectors is a key component of speaker identification and verification systems. This paper presents a deep neural network architecture for speaker embedding models where similarity in embedded utterance vectors explicitly approximates the similarity in vocal patterns of speakers. The proposed architecture contains an additional speaker embedding lookup table to compute loss based on embedding similarities. Furthermore, we propose a new feature sampling method for data augmentation. Experimentation based on two databases demonstrates that our model is more effective at speaker identification and verification when compared to a fully connected classifier and an end-to-end verification model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.