Conference paper

MATĚJKA Pavel, GLEMBEK Ondřej, NOVOTNÝ Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš and ČERNOCKÝ Jan. Analysis Of DNN Approaches To Speaker Identification. In: Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016, pp. 5100-5104. ISBN 978-1-4799-9988-0.
Publication language:english
Original title:Analysis Of DNN Approaches To Speaker Identification
Title (cs):Analýza DNN přístupů k identifikaci mluvčího
Pages:5100-5104
Proceedings:Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016
Conference:41th IEEE International Conference on Acoustics, Speech and Signal Processing
Place:Shanghai, CN
Year:2016
ISBN:978-1-4799-9988-0
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/matejka_icassp2016_0005100.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconmatejka_icassp2016_0005100.pdf86,4 KB2017-03-01 18:15:01
^ Select all
With selected:
Keywords
automatic speaker identification, deep neural networks, bottleneck features, i-vector
Annotation
We have analyzed the i-vector based systems with Deep Neural Network (DNN) Bottleneck (BN) features together with the traditional MFCC features, and we have demonstrated substantial gain for NIST SRE 2010, telephone condition.
Abstract
This work studies the usage of the Deep Neural Network (DNN) Bottleneck (BN) features together with the traditional MFCC features in the task of i-vector-based speaker recognition. We decouple the sufficient statistics extraction by using separate GMM models for frame alignment, and for statistics normalization and we analyze the usage of BN and MFCC features (and their concatenation) in the two stages. We also show the effect of using full-covariance GMM models, and, as a contrast, we compare the result to the recent DNNalignment approach. On the NIST SRE2010, telephone condition, we show 60% relative gain over the traditional MFCC baseline for EER (and similar for the NIST DCF metrics), resulting in 0.94% EER.
BibTeX:
@INPROCEEDINGS{
   author = {Pavel Mat{\v{e}}jka and Ond{\v{r}}ej Glembek and
	Ond{\v{r}}ej Novotn{\'{y}} and Old{\v{r}}ich Plchot and
	Franti{\v{s}}ek Gr{\'{e}}zl and Luk{\'{a}}{\v{s}} Burget and
	Jan {\v{C}}ernock{\'{y}}},
   title = {Analysis Of DNN Approaches To Speaker Identification},
   pages = {5100--5104},
   booktitle = {Proceedings of the 41th IEEE International Conference on
	Acoustics, Speech and Signal Processing (ICASSP 2016), 2016},
   year = {2016},
   location = {Shanghai, CN},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-9988-0},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en?id=11140}
}

Your IPv4 address: 54.196.201.241
Switch to IPv6 connection

DNSSEC [dnssec]