2001: A Speaker Odyssey - The Speaker Recognition Workshop

June 18-22, 2001
Crete, Greece

Speaker Recognition and the ETSI Standard Distributed Speech Recognition Front-End

Charles C. Broun (1), William M. Campbell (1), David Pearce (2), Holly Kelleher (2)

(1) Motorola Human Interface Lab, Tempe, Arizona, USA
(2) Motorola Limited, Basingstoke, UK

With the advent of Wireless Application Protocol (WAP) and 2.5/3G communication systems, the mobile device has become a window to the Internet. A natural interface to this mobile device is through speech. To address this need, a new European Telecommunications Standards Institute (ETSI) standard front-end has evolved for Distributed Speech Recognition (DSR). The goal of the ETSI DSR front-end is to standardize client-server speech recognition applications with a common feature set and quantization method. Although originally evolved as a speech recognition standard, we propose it is also a method of standardizing distributed speaker recognition authentication. To this end, we perform experiments using the DSR parameterization for a speaker recognition application. Results indicate excellent preservation of speaker identity in the DSR standard. This testing shows that DSR brings the potential for a promising new era of portable authentication for applications in personalization and security.

Full Paper   Presentation

Bibliographic reference.  Broun, Charles C. / Campbell, William M. / Pearce, David / Kelleher, Holly (2001): "Speaker recognition and the ETSI Standard Distributed Speech Recognition Front-End", In ODYSSEY-2001, 121-124.