Faculty of Information Technology, BUT

Publication Details

Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors

SILNOVA Anna, BRUMMER Niko, GARCÍA-ROMERO Daniel, SNYDER David and BURGET Lukáš. Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors. In: Proceedings of Interspeech 2018. Hyderabad: International Speech Communication Association, 2018, pp. 72-76. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2128.html
Czech title
Rychlý variační Bayes pro PLDA model s těžkým chvostem aplikovaný na i-vektory a x-vektory
Type
conference paper
Language
english
Authors
Silnova Anna, MSc. (DCGM FIT BUT)
Brummer Niko (NUANCE)
García-Romero Daniel (JHU)
Snyder David (JHU)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords
peaker recognition, variational Bayes, heavytailed PLDA
Abstract
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.
Published
2018
Pages
72-76
Journal
Proceedings of Interspeech, vol. 2018, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2018
Conference
Interspeech 2018, Hyderabad, India, IN
Publisher
International Speech Communication Association
Place
Hyderabad, IN
DOI
BibTeX
@INPROCEEDINGS{FITPUB11837,
   author = "Anna Silnova and Niko Brummer and Daniel Garc\'{i}a-Romero and David Snyder and Luk\'{a}\v{s} Burget",
   title = "Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors",
   pages = "72--76",
   booktitle = "Proceedings of Interspeech 2018",
   journal = "Proceedings of Interspeech",
   volume = 2018,
   number = 9,
   year = 2018,
   location = "Hyderabad, IN",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2018-2128",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11837"
}
Back to top