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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126451" target="_blank" >RIV/00216305:26230/17:PU126451 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.sciencedirect.com/science/article/pii/S0885230816303199" target="_blank" >http://www.sciencedirect.com/science/article/pii/S0885230816303199</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2017.04.005" target="_blank" >10.1016/j.csl.2017.04.005</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

COMPUTER SPEECH AND LANGUAGE

ISSN

0885-2308

e-ISSN

1095-8363

Svazek periodika

2017

Číslo periodika v rámci svazku

46

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

19

Strana od-do

53-71

Kód UT WoS článku

000407609600003

EID výsledku v databázi Scopus

2-s2.0-85019904410