no code implementations • 19 Mar 2022 • Anna Silnova, Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Pavel Matejka, Lukas Burget, Ondrej Glembek, Niko Brummer
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch.
1 code implementation • 2 Feb 2021 • Luciana Ferrer, Mitchell McLaren, Niko Brummer
When trained on a number of diverse datasets that are labeled only with respect to speaker, the proposed backend consistently and, in some cases, dramatically improves calibration, compared to the standard PLDA approach, on a number of held-out datasets, some of which are markedly different from the training data.
no code implementations • 19 Jun 2019 • Emre Yilmaz, Adem Derinel, Zhou Kun, Henk van den Heuvel, Niko Brummer, Haizhou Li, David A. van Leeuwen
This paper describes our initial efforts to build a large-scale speaker diarization (SD) and identification system on a recently digitized radio broadcast archive from the Netherlands which has more than 6500 audio tapes with 3000 hours of Frisian-Dutch speech recorded between 1950-2016.
1 code implementation • 24 Mar 2018 • Anna Silnova, Niko Brummer, Daniel Garcia-Romero, David Snyder, Lukas Burget
We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend.
no code implementations • 27 Feb 2018 • Niko Brummer, Anna Silnova, Lukas Burget, Themos Stafylakis
Embeddings in machine learning are low-dimensional representations of complex input patterns, with the property that simple geometric operations like Euclidean distances and dot products can be used for classification and comparison tasks.
no code implementations • 28 Sep 2017 • Albert Swart, Niko Brummer
We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions.
no code implementations • 23 Jul 2013 • Niko Brummer
This report works out the details of a closed-form, fully Bayesian, multiclass, openset, generative pattern classifier using multivariate Gaussian likelihoods, with conjugate priors.
no code implementations • 8 Apr 2013 • Niko Brummer, Johan du Preez
There has been much recent interest in application of the pool-adjacent-violators (PAV) algorithm for the purpose of calibrating the probabilistic outputs of automatic pattern recognition and machine learning algorithms.