Conference paper

POVEY Daniel, KARAFIÁT Martin, GHOSHAL Arnab and SCHWARZ Petr. A Symmetrization of the Subspace Gaussian Mixture Model. In: Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing. Praha: IEEE Signal Processing Society, 2011, pp. 4504-4507. ISBN 978-1-4577-0537-3.
Publication language:english
Original title:A Symmetrization of the Subspace Gaussian Mixture Model
Title (cs):Symetrizace Subspace Gaussian Mixture Modelů
Pages:4504-4507
Proceedings:Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing
Conference:International Conference on Acoustics, Speech and Signal Processing 2011
Place:Praha, CZ
Year:2011
ISBN:978-1-4577-0537-3
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/povey_icassp2011_4504.pdf [PDF]
Keywords
Speech Recognition, Hidden Markov Models, Subspace Gaussian Mixture Models
Annotation
We have described a modification to the Subspace Gaussian Mixture Model which we call the Symmetric SGMM. This is a very natural extension which removes an asymmetry in the way the Gaussian mixture weights were previously computed. The extra computation is minimal but the memory used for the acoustic model is nearly doubled. Our experimental results were inconsistent: on one setup we got a large improvement of 1.5% absolute, and on another setup it was much smaller.
Abstract
Last year we introduced the Subspace Gaussian Mixture Model (SGMM), and we demonstrated Word Error Rate improvements on a fairly small-scale task. Here we describe an extension to the SGMM, which we call the symmetric SGMM. It makes the model fully symmetric between the "speech-state vectors" and "speaker vectors" by making the mixture weights depend on the speaker as well as the speech state. We had previously avoided this as it introduces difficulties for efficient likelihood evaluation and parameter estimation, but we have found a way to overcome those difficulties. We find that the symmetric SGMM can give a very worthwhile improvement over the previously described model. We will also describe some larger-scale experiments with the SGMM, and report on progress toward releasing open-source software that supports SGMMs.
BibTeX:
@INPROCEEDINGS{
   author = {Daniel Povey and Martin Karafi{\'{a}}t and Arnab Ghoshal and
	Petr Schwarz},
   title = {A Symmetrization of the Subspace Gaussian Mixture Model},
   pages = {4504--4507},
   booktitle = {Proceedings of 2011 IEEE International Conference on
	Acoustics, Speech, and Signal Processing},
   year = {2011},
   location = {Praha, CZ},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4577-0537-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9652}
}

Your IPv4 address: 54.158.152.80
Switch to IPv6 connection

DNSSEC [dnssec]