Preserving privacy in speaker and speech characterisation
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 …
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
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 …
(DNNs) have been proposed. These systems have been proven to be competitive for text …
A speaker verification backend with robust performance across conditions
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 …
unknown during development. A standard method for speaker verification consists of …
NPLDA: A deep neural PLDA model for speaker verification
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 …
embedding extractor along with a backend generative model such as the Probabilistic …
[BUCH][B] Machine learning for speaker recognition
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 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 …
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
The availability of multiple utterances (and hence, i-vectors) for speaker enrollment brings
up several alternatives for their utilization with probabilistic linear discriminant analysis …
up several alternatives for their utilization with probabilistic linear discriminant analysis …
Large-scale training of pairwise support vector machines for speaker recognition
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 …
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
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 …
acoustic content of the observed features, the channel mismatch between the training …
Privacy-preserving PLDA speaker verification using outsourced secure computation
The usage of biometric recognition has become prevalent in various verification processes,
ranging from unlocking mobile devices to verifying bank transactions. Automatic speaker …
ranging from unlocking mobile devices to verifying bank transactions. Automatic speaker …