A speaker verification backend with robust performance across conditions

L Ferrer, M McLaren, N Brümmer - Computer Speech & Language, 2022 - Elsevier
In this paper, we address the problem of speaker verification in conditions unseen or
unknown during development. A standard method for speaker verification consists of …

Toward fail-safe speaker recognition: Trial-based calibration with a reject option

L Ferrer, MK Nandwana, M McLaren… - … on Audio, Speech …, 2018 - ieeexplore.ieee.org
The output scores of most of the speaker recognition systems are not directly interpretable
as stand-alone values. For this reason, a calibration step is usually performed on the scores …

A discriminative condition-aware backend for speaker verification

L Ferrer, M McLaren - ICASSP 2020-2020 IEEE International …, 2020 - ieeexplore.ieee.org
We present a scoring approach for speaker verification that mimics the standard PLDA-
based backend process used in most current speaker verification systems. However, unlike …

System combination using auxiliary information for speaker verification

L Ferrer, M Graciarena, A Zymnis… - 2008 IEEE International …, 2008 - ieeexplore.ieee.org
Recent studies in speaker recognition have shown that score-level combination of
subsystems can yield significant performance gains over individual subsystems. We explore …

A speaker verification backend for improved calibration performance across varying conditions

L Ferrer, M McLaren - arXiv preprint arXiv:2002.03802, 2020 - arxiv.org
In a recent work, we presented a discriminative backend for speaker verification that
achieved good out-of-the-box calibration performance on most tested conditions containing …

Reliability estimation of the speaker verification decisions using Bayesian networks to combine information from multiple speech quality measures

J Villalba, E Lleida, A Ortega, A Miguel - Advances in Speech and …, 2012 - Springer
In some situations the quality of the signals involved in a speaker verification trial is not as
good as needed to take a reliable decision. In this work, we use Bayesian networks to model …

Using post-classifiers to enhance fusion of low-and high-level speaker recognition

YA Solewicz, M Koppel - IEEE Transactions on Audio, Speech …, 2007 - ieeexplore.ieee.org
This paper proposes a method for automatic correction of bias in speaker recognition
systems, especially fusion-based systems. The method is based on a post-classifier which …

Voice-based speaker recognition combining acoustic and stylistic features

SS Kajarekar, L Ferrer, A Stolcke, E Shriberg - Advances in Biometrics …, 2008 - Springer
We present a survey of the state of the art in voice-based speaker identification research. We
describe the general framework of a text-independent speaker verification system, and, as …

[PDF][PDF] Robust Diarization For Speaker Characterization﴾ Diarizacion Robusta Para Caracterizacion De Locutores

CV Avilés-Casco - 2011 - zaguan.unizar.es
The task of speaker characterization, which aims at describing the particular and distinctive
peculiarities of a person's speech, is essential for several speech based technologies and …

[PDF][PDF] A new Bayesian network to assess the reliability of speaker verification decisions

J Villalba, E Lleida, A Ortega, A Miguel - Proc. InterSpeech, 2013 - isca-archive.org
In some situations the quality of the signals involved in a speaker verification trial is not as
good as needed to take a reliable decision. In this work, we present a new method based on …