Publication detail

Employment of Subspace Gaussian Mixture Models in Speaker Recognition

MOTLÍČEK, P. DEY, S. MADIKERI, S. BURGET, L.

Original Title

Employment of Subspace Gaussian Mixture Models in Speaker Recognition

Type

conference paper

Language

English

Original 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

speaker recognition, i-vectors, subspace Gaussian mixture models, automatic speech recognition

Authors

MOTLÍČEK, P.; DEY, S.; MADIKERI, S.; BURGET, L.

RIV year

2015

Released

19. 4. 2015

Publisher

IEEE Signal Processing Society

Location

South Brisbane, Queensland

ISBN

978-1-4673-6997-8

Book

Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing

Pages from

4445

Pages to

4449

Pages count

5

URL

BibTex

@inproceedings{BUT119895,
  author="Petr {Motlíček} and Subhadeep {Dey} and Srikanth {Madikeri} and Lukáš {Burget}",
  title="Employment of Subspace Gaussian Mixture Models in Speaker Recognition",
  booktitle="Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing",
  year="2015",
  pages="4445--4449",
  publisher="IEEE Signal Processing Society",
  address="South Brisbane, Queensland",
  doi="10.1109/ICASSP.2015.7178811",
  isbn="978-1-4673-6997-8",
  url="https://ieeexplore.ieee.org/document/7178811"
}