logo Idiap Research Institute        
 [BibTeX] [Marc21]
Type of publication: Idiap-RR
Citation: Motlicek_Idiap-RR-16-2015
Number: Idiap-RR-16-2015
Year: 2015
Month: 6
Institution: Idiap
Address: Rue Marconi 19, Martigny
Abstract: 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.
Keywords: Automatic Speech Recognition, i-vectors, speaker recognition, subspace Gaussian mixture models
Projects Idiap
Authors Motlicek, Petr
Dey, Subhadeep
Madikeri, Srikanth
Burget, Lukas
Crossref by Motlicek_ICASSP_2015
Added by: [ADM]
Total mark: 0
  • Motlicek_Idiap-RR-16-2015.pdf (MD5: 36fe1275520cec7f9f0f2250e3c9396e)