Gauss karışım modeli genel arka plan modeli (GKM-GAM) ve vektör nicemleme genel arka plan modeli (VN-GAM) konuşmacı doğrulamada sık kullanılan iki yöntemdir. Genellikle GAM modeli fazla sayıda farklı konuşmacının bulunduğu bir kümeden seçilen saatlerce uzunluktaki ses işaretleri kullanılarak eğitilir. Bu çalışmada, GAM modelinin eğitiminde kullanılan veri miktarının metinden bağımsız konuşmacı doğrulama performansına etkisi incelenmektedir. NIST 2002 konuşmacı tanıma değerlendirme veritabanı ile GKM-GAM ve VN-GAM yöntemleri kullanılarak yapılan deneysel çalışmalar arka plan modelini eğitmek için kullanılan veri miktarının konuşmacı tanıma performansına çok fazla etkisinin olmadığı görülmüştür
Gaussian mixture models with universal background model (GMM-UBM) and vector quantization with universal background model (VQ-UBM) are the two well-known classifiers used for speaker verification. Generally, UBM is trained with many hours of speech from a large pool of different speakers. In this study, we analyze the effect of data duration used to train UBM on text-independent speaker verification performance using GMM-UBM and VQ-UBM modeling techniques. Experiments carried out NIST 2002 speaker recognition evaluation (SRE) corpus show that background data duration to train UBM has small impact on recognition performance for GMM-UBM and VQ-UBM classifiers
Primary Language | Turkish |
---|---|
Journal Section | Research Articles |
Authors | |
Publication Date | April 1, 2013 |
Submission Date | December 19, 2014 |
Published in Issue | Year 2013 Volume: 18 Issue: 1 |
Announcements:
30.03.2021-Beginning with our April 2021 (26/1) issue, in accordance with the new criteria of TR-Dizin, the Declaration of Conflict of Interest and the Declaration of Author Contribution forms fulfilled and signed by all authors are required as well as the Copyright form during the initial submission of the manuscript. Furthermore two new sections, i.e. ‘Conflict of Interest’ and ‘Author Contribution’, should be added to the manuscript. Links of those forms that should be submitted with the initial manuscript can be found in our 'Author Guidelines' and 'Submission Procedure' pages. The manuscript template is also updated. For articles reviewed and accepted for publication in our 2021 and ongoing issues and for articles currently under review process, those forms should also be fulfilled, signed and uploaded to the system by authors.