pith. sign in

arxiv: 1609.08419 · v1 · pith:LDWCVWHVnew · submitted 2016-09-27 · 💻 cs.SD · cs.AI· cs.LO

Decision Making Based on Cohort Scores for Speaker Verification

classification 💻 cs.SD cs.AIcs.LO
keywords decisioncohortscoresmakingspeakerconventionalderivedmaker
0
0 comments X p. Extension
pith:LDWCVWHV Add to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{LDWCVWHV}

Prints a linked pith:LDWCVWHV badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

Decision making is an important component in a speaker verification system. For the conventional GMM-UBM architecture, the decision is usually conducted based on the log likelihood ratio of the test utterance against the GMM of the claimed speaker and the UBM. This single-score decision is simple but tends to be sensitive to the complex variations in speech signals (e.g. text content, channel, speaking style, etc.). In this paper, we propose a decision making approach based on multiple scores derived from a set of cohort GMMs (cohort scores). Importantly, these cohort scores are not simply averaged as in conventional cohort methods; instead, we employ a powerful discriminative model as the decision maker. Experimental results show that the proposed method delivers substantial performance improvement over the baseline system, especially when a deep neural network (DNN) is used as the decision maker, and the DNN input involves some statistical features derived from the cohort scores.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.