A privacy-preserving and language-independent speaking detecting and speaker diarization approach for spontaneous conversation using microphones

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 language-inde...

Full description

Saved in:
Bibliographic Details
Main Authors: Ni Zhang, Yaginuma, Y.
Format: Conference Proceeding
Language:English
Subjects:
conversation characteristics measuring
Hidden Markov Model
interaction pattern analysis
speaking style
speech processing
voiced/unvoiced sound
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 language-independent 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.
ISSN:2164-5221
DOI:10.1109/ICoSP.2012.6491534