Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130769" target="_blank" >RIV/00216305:26230/18:PU130769 - isvavai.cz</a>

Result on the web

<a href="https://www.fit.vut.cz/research/publication/11790/" target="_blank" >https://www.fit.vut.cz/research/publication/11790/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Odyssey.2018-49" target="_blank" >10.21437/Odyssey.2018-49</a>

Result language

angličtina

Original language name

Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model

Original language description

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. We introduce meta-embeddings, which live in more general inner product spaces and which are designed to better propagate uncertainty through the embedding bottleneck. Traditional embeddings are trained to maximize between-class and minimize within-class distances. Meta-embeddings are trained to maximize relevant information throughput. As a proof of concept in speaker recognition, we derive an extractor from the familiar generative Gaussian PLDA model (GPLDA). We show that GPLDA likelihood ratio scores are given by Hilbert space inner products between Gaussian likelihood functions, which we term Gaussian meta-embeddings (GMEs). Meta-embedding extractors can be generatively or discriminatively trained. GMEs extracted by GPLDA have fixed precisions and do not propagate uncertainty. We show that a generalization to heavy-tailed PLDA gives GMEs with variable precisions, which do propagate uncertainty. Experiments on NIST SRE 2010 and 2016 show that the proposed method applied to i-vectors without length normalization is up to 20% more accurate than GPLDA applied to length-normalized i-vectors.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of Odyssey 2018

ISBN

—

ISSN

2312-2846

e-ISSN

—

Number of pages

8

Pages from-to

349-356

Publisher name

International Speech Communication Association

Place of publication

Les Sables d'Olonne

Event location

Les Sables d'Olonne, France

Event date

Jun 26, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—