Employment of Subspace Gaussian Mixture Models in Speaker Recognition
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F15%3APU117038" target="_blank" >RIV/00216305:26230/15:PU117038 - isvavai.cz</a>
Výsledek na webu
<a href="https://ieeexplore.ieee.org/document/7178811" target="_blank" >https://ieeexplore.ieee.org/document/7178811</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2015.7178811" target="_blank" >10.1109/ICASSP.2015.7178811</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Employment of Subspace Gaussian Mixture Models in Speaker Recognition
Popis výsledku v původním jazyce
This paper presents Subspace Gaussian Mixture Model (SGMM) approach employed as a probabilistic generative model to estimate speaker vector representations to be subsequently used in the speaker verification task. SGMMs have already been shown to significantly outperform traditional HMM/GMMs in Automatic Speech Recognition (ASR) applications. An extension to the basic SGMM framework allows to robustly estimate low-dimensional speaker vectors and exploit them for speaker adaptation. We propose a speaker verification framework based on low-dimensional speaker vectors estimated using SGMMs, trained in ASR manner using manual transcriptions. To test the robustness of the system, we evaluate the proposed approach with respect to the state-of-the-art i-vector extractor on the NIST SRE 2010 evaluation set and on four different length-utterance conditions: 3sec-10sec, 10 sec-30 sec, 30 sec-60 sec and full (untruncated) utterances. Experimental results reveal that while i-vector system performs better on truncated 3sec to 10sec and 10 sec to 30 sec utterances, noticeable improvements are observed with SGMMs especially on full length-utterance durations. Eventually, the proposed SGMM approach exhibits complementary properties and can thus be efficiently fused with i-vector based speaker verification system.
Název v anglickém jazyce
Employment of Subspace Gaussian Mixture Models in Speaker Recognition
Popis výsledku anglicky
This paper presents Subspace Gaussian Mixture Model (SGMM) approach employed as a probabilistic generative model to estimate speaker vector representations to be subsequently used in the speaker verification task. SGMMs have already been shown to significantly outperform traditional HMM/GMMs in Automatic Speech Recognition (ASR) applications. An extension to the basic SGMM framework allows to robustly estimate low-dimensional speaker vectors and exploit them for speaker adaptation. We propose a speaker verification framework based on low-dimensional speaker vectors estimated using SGMMs, trained in ASR manner using manual transcriptions. To test the robustness of the system, we evaluate the proposed approach with respect to the state-of-the-art i-vector extractor on the NIST SRE 2010 evaluation set and on four different length-utterance conditions: 3sec-10sec, 10 sec-30 sec, 30 sec-60 sec and full (untruncated) utterances. Experimental results reveal that while i-vector system performs better on truncated 3sec to 10sec and 10 sec to 30 sec utterances, noticeable improvements are observed with SGMMs especially on full length-utterance durations. Eventually, the proposed SGMM approach exhibits complementary properties and can thus be efficiently fused with i-vector based speaker verification system.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
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)
Ostatní
Rok uplatnění
2015
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing
ISBN
978-1-4673-6997-8
ISSN
—
e-ISSN
—
Počet stran výsledku
5
Strana od-do
4445-4449
Název nakladatele
IEEE Signal Processing Society
Místo vydání
South Brisbane, Queensland
Místo konání akce
Brisbane
Datum konání akce
19. 4. 2015
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000427402904111