Publication result detail

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

ZEINALI, H.; SAMETI, H.; BURGET, L.; ČERNOCKÝ, J.

Original Title

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

English Title

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

Type

WoS Article

Original 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.

English 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.

Keywords

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

Key words in English

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

Authors

ZEINALI, H.; SAMETI, H.; BURGET, L.; ČERNOCKÝ, J.

RIV year

2018

Released

12.05.2017

ISBN

0885-2308

Periodical

COMPUTER SPEECH AND LANGUAGE

Volume

2017

Number

46

State

United Kingdom of Great Britain and Northern Ireland

Pages from

53

Pages to

71

Pages count

19

URL

http://www.sciencedirect.com/science/article/pii/S0885230816303199

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"
}

Documents

zeinali_CSL2017