Conversation conveys important social signals of human interaction that indicates interest, service-awareness, persuasiveness, etc. In this paper, the authors employ the most common setting of using microphones to capture spontaneous conversation, and introduce a privacy-preserving and languageindependent speech processing approach that can detect speaking and separate speakers in high accuracy for such setting. Experimental results have validated that the approach can deliver accurate speaking recognition results in Japanese, English and Chinese conversation, and can be processed in real time applications.
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.