Detail výsledku

i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge

ZEINALI, H.; SAMETI, H.; BURGET, L.; ČERNOCKÝ, J.; MAGHSOODI, N.; MATĚJKA, P. i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge. In Proceedings of Interspeech 2016. San Francisco: International Speech Communication Association, 2016. p. 440-444. ISBN: 978-1-5108-3313-5.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Zeinali Hossein, Ph.D., UPGM (FIT)
Sameti Hossein
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Maghsoodi Nooshin
Matějka Pavel, Ing., Ph.D., UPGM (FIT)
Abstrakt

Recently, a new data collection was initiated within the RedDotsproject in order to evaluate text-dependent and text-promptedspeaker recognition technology on data from a wider speakerpopulation and with more realistic noise, channel and phoneticvariability. This paper analyses our systems built for RedDotschallenge - the effort to collect and compare the initial resultson this new evaluation data set obtained at different sites.We use our recently introduced HMM based i-vector approach,where, instead of the traditional GMM, a set of phone specificHMMs is used to collect the sufficient statistics for i-vectorextraction. Our systems are trained in a completely phraseindependentway on the data from RSR2015 and Libri speechdatabases. We compare systems making use of standard cepstralfeatures and their combination with neural network basedbottle-neck features. The best results are obtained with a scorelevelfusion of such systems.

Klíčová slova

text-dependent speaker verification, i-vector,HMM, RedDots challenge

URL
Rok
2016
Strany
440–444
Sborník
Proceedings of Interspeech 2016
Konference
Interspeech Conference
ISBN
978-1-5108-3313-5
Vydavatel
International Speech Communication Association
Místo
San Francisco
DOI
10.21437/Interspeech.2016-1174
UT WoS
000409394400093
EID Scopus
2-s2.0-84994259825
BibTeX 
@inproceedings{BUT131018,
  author="Hossein {Zeinali} and Hossein {Sameti} and Lukáš {Burget} and Jan {Černocký} and Nooshin {Maghsoodi} and Pavel {Matějka}",
  title="i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge",
  booktitle="Proceedings of Interspeech 2016",
  year="2016",
  pages="440--444",
  publisher="International Speech Communication Association",
  address="San Francisco",
  doi="10.21437/Interspeech.2016-1174",
  isbn="978-1-5108-3313-5",
  url="https://www.researchgate.net/publication/303895014_i-VectorHMM_Based_Text-Dependent_Speaker_Verification_System_for_RedDots_Challenge"
}
Soubory
Projekty
Dolování infoRmAcí z řeči Pořízené vzdÁlenými miKrofony, MV, Bezpečnostní výzkum České republiky 2015-2020, VI20152020025, zahájení: 2015-10-01, ukončení: 2020-09-30, ukončen
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, zahájení: 2016-01-01, ukončení: 2020-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru