%Aigaion2 BibTeX export from Idiap Publications
%Saturday 19 July 2025 01:22:22 AM

@INPROCEEDINGS{Motlicek_ICASSP_2015,
                      author = {Motlicek, Petr and Dey, Subhadeep and Madikeri, Srikanth and Burget, Lukas},
                    projects = {Idiap, SIIP},
                       month = may,
                       title = {EMPLOYMENT OF SUBSPACE GAUSSIAN MIXTURE MODELS IN SPEAKER RECOGNITION},
                   booktitle = {2015 IEEE International Conference on Acoustics, Speech, and Signal Processing},
                        year = {2015},
                       pages = {4445-4449},
                    location = {Brisbane, Australia},
                organization = {IEEE},
                        isbn = {978-1-4673-6996-1},
                         url = {http://icassp2015.org/},
                    crossref = {Motlicek_Idiap-RR-16-2015},
                    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.},
                         pdf = {https://publications.idiap.ch/attachments/papers/2015/Motlicek_ICASSP_2015.pdf}
}



crossreferenced publications: 
@TECHREPORT{Motlicek_Idiap-RR-16-2015,
                      author = {Motlicek, Petr and Dey, Subhadeep and Madikeri, Srikanth and Burget, Lukas},
                    keywords = {Automatic Speech Recognition, i-vectors, speaker recognition, subspace Gaussian mixture models},
                    projects = {Idiap, SIIP},
                       month = {6},
                       title = {EMPLOYMENT OF SUBSPACE GAUSSIAN MIXTURE MODELS IN SPEAKER RECOGNITION},
                        type = {Idiap-RR},
                      number = {Idiap-RR-16-2015},
                        year = {2015},
                 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.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2015/Motlicek_Idiap-RR-16-2015.pdf}
}