Publication Details

Analysis of Speaker Recognition Systems in Realistic Scenarios of the SITW 2016 Challenge

NOVOTNÝ Ondřej, MATĚJKA Pavel, PLCHOT Oldřich, GLEMBEK Ondřej, BURGET Lukáš and ČERNOCKÝ Jan. Analysis of Speaker Recognition Systems in Realistic Scenarios of the SITW 2016 Challenge. In: Proceedings of Interspeech 2016. San Francisco: International Speech Communication Association, 2016, pp. 828-832. ISBN 978-1-5108-3313-5. Available from: https://www.researchgate.net/publication/307889224_Analysis_of_Speaker_Recognition_Systems_in_Realistic_Scenarios_of_the_SITW_2016_Challenge
Czech title
Analýza systémů pro ověřování mluvčího v realistických podmínkách SITW 2016 Challenge
Type
conference paper
Language
english
Authors
Novotný Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

speaker recognition, SRE systems, diarization

Abstract

In this paper, we summarize our efforts for the Speakers In The Wild (SITW) challenge, and we present our findings with this new dataset for speaker recognition. Apart from the standard comparison of different SRE systems, we analyze the use of diarization for dealing with audio segments containing multiple speakers, as in part of the newly introduced enrollment and test protocols, diarization is a necessary system component. Our state-of-the-art systems used in this work utilize both cepstral and DNN-based bottleneck features and are based on i-vectors followed by Probabilistic Linear Discriminant Analysis (PLDA) classifier and logistic regression calibration/fusion. We present both narrow-band (8 kHz) and wide-band (16 kHz) systems together with their fusions.

Annotation

In this paper, we summarize our efforts for the Speakers In The Wild (SITW) challenge, and we present our findings with this new dataset for speaker recognition. Apart from the standard comparison of different SRE systems, we analyze the use of diarization for dealing with audio segments containing multiple speakers, as in part of the newly introduced enrollment and test protocols, diarization is a necessary system component. Our state-of-the-art systems used in this work utilize both cepstral and DNN-based bottleneck features and are based on i-vectors followed by Probabilistic Linear Discriminant Analysis (PLDA) classifier and logistic regression calibration/fusion. We present both narrow-band (8 kHz) and wide-band (16 kHz) systems together with their fusions.

Published
2016
Pages
828-832
Proceedings
Proceedings of Interspeech 2016
Conference
Interspeech Conference, San Francisco, US
ISBN
978-1-5108-3313-5
Publisher
International Speech Communication Association
Place
San Francisco, US
DOI
10.21437/Interspeech.2016-981
UT WoS
000409394400173
EID Scopus
2-s2.0-84994201390
BibTeX 
@INPROCEEDINGS{FITPUB11270,
   author = "Ond\v{r}ej Novotn\'{y} and Pavel Mat\v{e}jka and Old\v{r}ich Plchot and Ond\v{r}ej Glembek and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Analysis of Speaker Recognition Systems in Realistic Scenarios of the SITW 2016 Challenge",
   pages = "828--832",
   booktitle = "Proceedings of Interspeech 2016",
   year = 2016,
   location = "San Francisco, US",
   publisher = "International Speech Communication Association",
   ISBN = "978-1-5108-3313-5",
   doi = "10.21437/Interspeech.2016-981",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11270"
}
Back to top