Conference paper

PLCHOT Oldřich, KARAFIÁT Martin, BRUMMER Niko, GLEMBEK Ondřej, MATĚJKA Pavel, DE Villiers Edward and ČERNOCKÝ Jan. Speaker vectors from Subspace Gaussian Mixture Model as complementary features for Language Identification. In: Proceedings of Odyssey 2012, The Speaker and Language Recognition Workshop. Singapur: International Speech Communication Association, 2012, pp. 330-333. ISBN 978-981-07-3093-2.
Publication language:english
Original title:Speaker vectors from Subspace Gaussian Mixture Model as complementary features for Language Identification
Title (cs):Adaptační vektory mluvčího ze Subspace Gaussian Mixture modelu jako komplementární příznaky pro identifikaci jazyka
Pages:330-333
Proceedings:Proceedings of Odyssey 2012, The Speaker and Language Recognition Workshop
Conference:Odyssey 2012: The Speaker and Language Recognition Workshop
Place:Singapur, SG
Year:2012
ISBN:978-981-07-3093-2
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2012/plchot_odyssey2012_330-333-41.pdf [PDF]
Keywords
speaker recognition, Gaussian Mixture Model, speaker vectors, language identification
Annotation
In this paper we have presented new features for language identification, based on speaker adaptation vectors from sub-space Gaussian Mixture Models.
Abstract
In this paper, we explore new high-level features for language identification. The recently introduced Subspace Gaussian Mixture Models (SGMM) provide an elegant and efficient way for GMM acoustic modelling, with mean supervectors represented in a low-dimensional representative subspace. SGMMs also provide an efficient way of speaker adaptation by means of lowdimensional vectors. In our framework, these vectors are used as features for language identification. They are compared with our acoustic iVector system, which architecture is currently considered state-of-the-art for Language Identification and Speaker Verification. The results of both systems and their fusion are reported on the NIST LRE2009 dataset.
BibTeX:
@INPROCEEDINGS{
   author = {Old{\v{r}}ich Plchot and Martin Karafi{\'{a}}t and Niko
	Brummer and Ond{\v{r}}ej Glembek and Pavel Mat{\v{e}}jka and
	Edward Villiers de and Jan {\v{C}}ernock{\'{y}}},
   title = {Speaker vectors from Subspace Gaussian Mixture Model as
	complementary features for Language Identification},
   pages = {330--333},
   booktitle = {Proceedings of Odyssey 2012, The Speaker and Language
	Recognition Workshop},
   year = {2012},
   location = {Singapur, SG},
   publisher = {International Speech Communication Association},
   ISBN = {978-981-07-3093-2},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10056}
}

Your IPv4 address: 54.196.107.247
Switch to IPv6 connection

DNSSEC [dnssec]