%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:38:06 PM @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} }