Towards reduced false-alarms using cohorts

Zahi N. Karam, William M. Campbell, Najim DehakICASSP 2011 · OpenReview

Abstract

The focus of the 2010 NIST Speaker Recognition Evaluation (SRE) [1] was the low false alarm regime of the detection error trade-off (DET) curve. This paper presents several approaches that specifically target this issue. It begins by highlighting the main problem with operating in the low-false alarm regime. Two sets of methods to tackle this issue are presented that require a large and diverse impostor set: the first set penalizes trials whose enrollment and test utterances are not nearest neighbors of each other while the second takes an adaptive score normalization approach similar to TopNorm [2] and ATNorm [3].
BibTeX
@inproceedings{karam2011towards,
  author = {Zahi N. Karam and William M. Campbell and Najim Dehak},
  title = {{Towards reduced false-alarms using cohorts}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2011},
  url = {https://openreview.net/forum?id=TwcWPUj75O},
}

Loading related content...

Figure