A Privacy-Sensitive Approach to Modeling Multi-Person Conversations
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1769-1774.
Abstract
In this paper we introduce a new dynamic Bayesian network that separates the speakers and their speaking turns in a multi-person conversation. We protect the speakers' privacy by using only features from which intelligible speech cannot be reconstructed. The model we present combines data from multiple audio streams, segments the streams into speech and silence, separates the different speakers, and detects when other nearby individuals who are not wearing microphones are speaking. No pre-trained speaker specific models are used, so the system can be easily applied in new and different environments. We show promising results in two very different datasets that vary in background noise, microphone placement and quality, and conversational dynamics.
@inproceedings{ijcai2007p286,
title = {A Privacy-Sensitive Approach to Modeling Multi-Person Conversations},
author = {Wyatt, Danny and Choudhury, Tanzeem and Bilmes, Jeff A. and Kautz, Henry A.},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {1769--1774},
year = {2007},
url = {https://ijcai.org/proceedings/2007/286},
}
TY - CPAPER TI - A Privacy-Sensitive Approach to Modeling Multi-Person Conversations AU - Wyatt, Danny AU - Choudhury, Tanzeem AU - Bilmes, Jeff A. AU - Kautz, Henry A. T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 1769 EP - 1774 UR - https://ijcai.org/proceedings/2007/286 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
