Stand out as a speaker

How humans stand out in frontal lobe scaling.

All studies from the last 15 y of collecting data on primate frontal lobe volumes share one central result: allometric scaling of the human frontal lobe is not larger than expected. Recent studies collecting data on the prefrontal cortex confirm this result, but additionally indicate human prefrontal white matter specialization. A recent publication by Barton and Venditti (1) reanalyzed data fr...

neurotoxicity perspective: stand behind prograf® (tacrolimus) as a pharmacist

Germany: Merkel does not stand out but holds

Germany went to the polls on Sunday, May 25 to elect 96 members of the European Parliament, by far the country in Europe that elects most delegates. The 96 members were elected by a pure proportional electoral system, a real novelty for nationwide elections in Germany, where the minimum threshold has always been 5% for the national elections and 3% for the European elections. This change was th...

Towards Fully Bayesian Speaker Recognition: Integrating Out the Between-Speaker Covariance

We propose a variational Bayes solution to integrate out the model parameters in a generative i-vector speaker recognizer. The existing state-of-the-art in generative i-vector modelling plugs in fixed maximum-likelihood point-estimates of model parameters. This recipe may suffer from over-fitting of especially the between-speaker covariance. We show how to integrate out the between-speaker cova...

Dataset-invariant covariance normalization for out-domain PLDA speaker verification

In this paper we introduce a novel domain-invariant covariance normalization (DICN) technique to relocate both in-domain and out-domain i-vectors into a third dataset-invariant space, providing an improvement for out-domain PLDA speaker verification with a very small number of unlabelled in-domain adaptation i-vectors. By capturing the dataset variance from a global mean using both development ...