Detail výsledku

Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models

ZEINALI, H.; SAMETI, H.; BURGET, L.; ČERNOCKÝ, J. Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models. COMPUTER SPEECH AND LANGUAGE, 2017, vol. 2017, no. 46, p. 53-71. ISSN: 0885-2308.
Typ
článek v časopise
Jazyk
anglicky
Autoři
Zeinali Hossein, Ph.D.
Sameti Hossein, FIT (FIT)
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Abstrakt

Inspired by the success of Deep Neural Networks (DNN) in text-independent speaker recognition, we have recently demonstrated that similar ideas can also be applied to the text-dependent speaker verification task. In this paper, we describe new advances with our state-of-the-art i-vector based approach to text-dependent speaker verification, which also makes use of different DNN techniques. In order to collect sufficient statistics for i-vector extraction, different frame alignment models are compared such as GMMs, phonemic HMMs or DNNs trained for senone classification. We also experiment with DNN based bottleneck features and their combinations with standard MFCC features. We experiment with few different DNN configurations and investigate the importance of training DNNs on 16 kHz speech. The results are reported on RSR2015 dataset, where training material is available for all possible enrollment and test phrases. Additionally, we report results also on more challenging RedDots dataset, where the system is built in truly phrase-independent way.

Klíčová slova

Deep Neural Network; Text-dependent; Speaker verification; i-Vector; Frame alignment; Bottleneck features

URL
Rok
2017
Strany
53–71
Časopis
COMPUTER SPEECH AND LANGUAGE, roč. 2017, č. 46, ISSN 0885-2308
DOI
10.1016/j.csl.2017.04.005
UT WoS
000407609600003
EID Scopus
2-s2.0-85019904410
BibTeX 
@article{BUT144474,
  author="Hossein {Zeinali} and Hossein {Sameti} and Lukáš {Burget} and Jan {Černocký}",
  title="Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models",
  journal="COMPUTER SPEECH AND LANGUAGE",
  year="2017",
  volume="2017",
  number="46",
  pages="53--71",
  doi="10.1016/j.csl.2017.04.005",
  issn="0885-2308",
  url="http://www.sciencedirect.com/science/article/pii/S0885230816303199"
}
Soubory
Projekty
Analytika velkých řečových dat pro kontaktní centra, EU, Horizon 2020, zahájení: 2015-01-01, ukončení: 2017-12-31, ukončen
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