DocumentCode
1897179
Title
Data sampling approaches for GMM supervector based speaker verification
Author
Dikici, Erinç ; Saraçlar, Murat
Author_Institution
Elektrik ve Elektron. Muhendisligi Bolumu, Bogazici Univ., Istanbul, Turkey
fYear
2011
fDate
20-22 April 2011
Firstpage
562
Lastpage
565
Abstract
GMM supervectors are among the most popular feature sets used in SVM-based text-independent speaker verification. Most of the studies represent speaker characteristics obtained from a long recording with a single supervector in the SVM space. Working on the NIST SRE´10 dataset, this study compares the effect of two sampling methods to increase the number of supervectors, on the verification performance. Dominance of positive and negative classes on model construction is investigated.
Keywords
Gaussian processes; speaker recognition; support vector machines; GMM supervector based speaker verification; SVM-based text-independent speaker verification; data sampling approaches; Adaptation model; Conferences; NIST; Signal processing; Speaker recognition; Speech; Support vector machines;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing and Communications Applications (SIU), 2011 IEEE 19th Conference on
Conference_Location
Antalya
Print_ISBN
978-1-4577-0462-8
Electronic_ISBN
978-1-4577-0461-1
Type
conf
DOI
10.1109/SIU.2011.5929712
Filename
5929712
Link To Document