Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130790" target="_blank" >RIV/00216305:26230/18:PU130790 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2128.html" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2128.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2018-2128" target="_blank" >10.21437/Interspeech.2018-2128</a>
Alternative languages
Result language
angličtina
Original language name
Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors
Original language description
The standard state-of-the-art backend for text-independent speaker recognizers that use i-vectors or x-vectors, is Gaussian PLDA (G-PLDA), assisted by a Gaussianization step involving length normalization. G-PLDA can be trained with both generative or discriminative methods. It has long been known that heavy-tailed PLDA (HT-PLDA), applied without length normalization, gives similar accuracy, but at considerable extra computational cost. We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend. This paper extends that work by introducing a fast, variational Bayes, generative training algorithm. We compare old and new backends, with and without length-normalization, with i-vectors and x-vectors, on SRE10, SRE16 and SITW.
Czech name
—
Czech description
—
Classification
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)
Result continuities
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)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of Interspeech 2018
ISBN
—
ISSN
1990-9772
e-ISSN
—
Number of pages
5
Pages from-to
72-76
Publisher name
International Speech Communication Association
Place of publication
Hyderabad
Event location
Hyderabad, India
Event date
Sep 2, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—