Collaborative Real-Time Speaker Identification for Wearable Systems

Publication Type Conference Paper
Authors Mirco Rossi, Oliver Amft, Martin Kusserow, Gerhard Tröster
Title Collaborative Real-Time Speaker Identification for Wearable Systems
Abstract We present an unsupervised speaker identification system for personal annotations of conversations and meetings. The system dynamically learns new speakers and recognizes already known speakers using one audio channel and speech-independent modeling. Multiple personal systems could collaborate in robust unsupervised speaker identification and online learning. The system was optimized for real-time operation on a DSP system that can be worn during daily activities. The system was evaluated on the freely available 24-speaker Augmented Multiparty Interaction dataset. For 5s recognition time, the system achieves 81% recognition rate. Collaboration between four identification systems resulted in a performance increase of up to 17%, however even two collaborating systems yield an performance improvement. A prototypical wearable DSP implementation could continuously operate for more than 8hours from a 4.1Ah battery.
Date 2010
Proceedings Title PerCom 2010: Proceedings of the 8th Annual IEEE International Conference on Pervasive Computing and Communications
Publisher IEEE
Pages 180–189
DOI 10.1109/PERCOM.2010.5466976
Extra Acceptance rate: 12%
Full Text PDF
Friedrich-Alexander-Universität Erlangen-Nürnberg