Publication Details

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

ZEINALI Hossein, SAMETI Hossein, BURGET Lukáš and ČERNOCKÝ Jan. Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models. Computer Speech and Language, vol. 2017, no. 46, pp. 53-71. ISSN 0885-2308. Available from: http://www.sciencedirect.com/science/article/pii/S0885230816303199
Czech title
Ověřování mluvčího závislé na textu založené na i-vektorech, neuronových sítích a skrytých Markovových modelech
Type
journal article
Language
english
Authors
Zeinali Hossein, Ph.D. (DCGM FIT BUT)
Sameti Hossein (SHARIF)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

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

Abstract

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.

Published
2017
Pages
53-71
Journal
Computer Speech and Language, vol. 2017, no. 46, ISSN 0885-2308
Publisher
Elsevier Science
DOI
UT WoS
000407609600003
EID Scopus
BibTeX
@ARTICLE{FITPUB11529,
   author = "Hossein Zeinali and Hossein Sameti and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models",
   pages = "53--71",
   journal = "Computer Speech and Language",
   volume = 2017,
   number = 46,
   year = 2017,
   ISSN = "0885-2308",
   doi = "10.1016/j.csl.2017.04.005",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11529"
}
Back to top