Recent Developments in Voice Biometrics: Robustness and High Accuracy

Supplement: IEEE 2013 Conference on Technology for Homeland Security: Best Papers

Nicolas Scheffer, Luciana Ferrer, Aaron Lawson, Yun Lei, and Mitchell McLaren

ABSTRACT: Awarded Best Paper in the Biometrics and Forensics track.

Recently, researchers have tackled difficult voice biometrics
problems that resonate with the defense and research
communities. These problems include non-ideal recording
conditions that are frequently found in operational scenarios,
such as noise, reverberation, degraded channels, and compressed
audio. In this article, we highlight SRI’s innovations that resulted
from the IARPA Biometrics Exploitation Science & Technology
(BEST) and the DARPA Robust Automatic Transcription of
Speech (RATS) programs, as well as SRI’s approach for codecdegraded
speech. We show how these advancements support the
case for the biometrics community adopting the use of speaker
recognition. Download the full article.

Keywords: voice biometrics, speaker recognition, forensics

SUGGESTED CITATION:
Scheffer, Nicolas et al. “Recent Developments in Voice Biometrics: Robustness and High Accuracy.” Homeland Security Affairs, IEEE 2013 Conference on Technology for Homeland Security: Best Papers (April 2014) https://www.hsaj.org/articles/260


This article was originally published at the URL https://www.hsaj.org/?special:article=0.7.3.

No Comments

Post a Comment