Preserving privacy in speaker and speech characterisation

A Nautsch, A Jiménez, A Treiber, J Kolberg… - Computer Speech & …, 2019 - Elsevier
Speech recordings are a rich source of personal, sensitive data that can be used to support
a plethora of diverse applications, from health profiling to biometric recognition. It is therefore …

End-to-end DNN based speaker recognition inspired by i-vector and PLDA

J Rohdin, A Silnova, M Diez, O Plchot… - … on acoustics, speech …, 2018 - ieeexplore.ieee.org
Recently, several end-to-end speaker verification systems based on deep neural networks
(DNNs) have been proposed. These systems have been proven to be competitive for text …

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 …

NPLDA: A deep neural PLDA model for speaker verification

S Ramoji, P Krishnan, S Ganapathy - arxiv preprint arxiv:2002.03562, 2020 - arxiv.org
The state-of-art approach for speaker verification consists of a neural network based
embedding extractor along with a backend generative model such as the Probabilistic …

[BUCH][B] Machine learning for speaker recognition

MW Mak, JT Chien - 2020 - books.google.com
This book will help readers understand fundamental and advanced statistical models and
deep learning models for robust speaker recognition and domain adaptation. This useful …

Deep bayes factor scoring for authorship verification

B Boenninghoff, J Rupp, RM Nickel… - arxiv preprint arxiv …, 2020 - arxiv.org
The PAN 2020 authorship verification (AV) challenge focuses on a cross-topic/closed-set AV
task over a collection of fanfiction texts. Fanfiction is a fan-written extension of a storyline in …

From single to multiple enrollment i-vectors: Practical PLDA scoring variants for speaker verification

P Rajan, A Afanasyev, V Hautamäki… - Digital Signal Processing, 2014 - Elsevier
The availability of multiple utterances (and hence, i-vectors) for speaker enrollment brings
up several alternatives for their utilization with probabilistic linear discriminant analysis …

Large-scale training of pairwise support vector machines for speaker recognition

S Cumani, P Laface - IEEE/ACM transactions on audio, speech …, 2014 - ieeexplore.ieee.org
State–of–the–art systems for text–independent speaker recognition use as their features a
compact representation of a speaker utterance, known as “i–vector.” We recently presented …

On the use of i–vector posterior distributions in Probabilistic Linear Discriminant Analysis

S Cumani, O Plchot, P Laface - IEEE/ACM Transactions on …, 2014 - ieeexplore.ieee.org
The i-vector extraction process is affected by several factors such as the noise level, the
acoustic content of the observed features, the channel mismatch between the training …

Privacy-preserving PLDA speaker verification using outsourced secure computation

A Treiber, A Nautsch, J Kolberg, T Schneider… - Speech …, 2019 - Elsevier
The usage of biometric recognition has become prevalent in various verification processes,
ranging from unlocking mobile devices to verifying bank transactions. Automatic speaker …