Unsupervised Adaptation of SPLDA

11/20/2015
by   Jesús Villalba, et al.
0

State-of-the-art speaker recognition relays on models that need a large amount of training data. This models are successful in tasks like NIST SRE because there is sufficient data available. However, in real applications, we usually do not have so much data and, in many cases, the speaker labels are unknown. We present a method to adapt a PLDA model from a domain with a large amount of labeled data to another with unlabeled data. We describe a generative model that produces both sets of data where the unknown labels are modeled like latent variables. We used variational Bayes to estimate the hidden variables. Here, we derive the equations for this model. This model has been used in the papers: "UNSUPERVISED ADAPTATION OF PLDA BY USING VARIATIONAL BAYES METHODS" publised at ICASSP 2014, "Unsupervised Training of PLDA with Variational Bayes" published at Iberspeech 2014, and "VARIATIONAL BAYESIAN PLDA FOR SPEAKER DIARIZATION IN THE MGB CHALLENGE" published at ASRU 2015.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2018

Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition

The current trend in automatic speech recognition is to leverage large a...
research
12/26/2018

The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA

State-of-the-art speaker recognition systems comprise an x-vector (or i-...
research
11/20/2015

Bayesian SPLDA

In this document we are going to derive the equations needed to implemen...
research
12/14/2020

Bayesian Learning for Deep Neural Network Adaptation

A key task for speech recognition systems is to reduce the mismatch betw...
research
02/02/2022

The CORAL++ Algorithm for Unsupervised Domain Adaptation of Speaker Recogntion

State-of-the-art speaker recognition systems are trained with a large am...
research
11/20/2015

Variational Bayes Factor Analysis for i-Vector Extraction

In this document we are going to derive the equations needed to implemen...
research
10/24/2016

UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation

This document briefly describes the systems submitted by the Center for ...

Please sign up or login with your details

Forgot password? Click here to reset